Skip to content
AISubHub.
English
English简体中文EspañolPortuguêsFrançaisDeutsch日本語한국어हिन्दीالعربيةРусский
AISubHubRankings
AISUBHUB INTELLIGENCE

Global AI model rankings

Compare task performance, text preferences and coding agents separately. Each source measures a different kind of result.

Start here

General task performance

Official results · external site

For models such as Claude Opus 5.5 or GPT-6 Astra, start with evaluations that combine several kinds of tasks. Keep the exact model version and test settings in view.

LiveBench 2.0

LiveBench 2.0 combines seven task suites, from short reasoning questions to longer work with tools.

Seven task suites

  • Agentic work
  • Reasoning
  • Coding
  • Browser use
  • Data analysis
  • Research
  • Design
Source release
20261014 ·
Website update label

Results depend on the tested model, effort and tools. They describe performance under that protocol, not every language or real-world task.

AISubHub has not imported the full LiveBench results table. Open the official site for its current scores and method.

Coding agents · SWE-bench

Official results · external site

Software-fixing results can measure a model together with its agent and tools. Compare the same framework, budget and dataset.

Verified and Pro are separate benchmarks. Check the exact model, agent or harness, dataset version and execution budget before comparing.

These links open official results. AISubHub has not imported a complete SWE-bench results table.

Arena (LMArena)

Text preferences · Arena, style controlled

Text

Open source leaderboard

This Arena configuration measures preferences for text responses with style controls. Model positions can differ across evaluation dimensions.

Configuration: text_style_control · latestSnapshot date: Source checked: 416 entries

Partial source snapshot. The displayed rows do not represent the complete leaderboard.

Metric: Arena score (Bradley–Terry)

Scroll horizontally to see every reported field.

Text preferences · Arena, style controlled · Arena (LMArena) · 2026-10-15
Source rankModelMetricConfidence intervalVotes
1Gemini 4 Argon (High)
Model details
Model variant
Gemini 4 Argon (High)
Organization
google
Model license
Proprietary
Variance
20.24282977841088
1523.90358612991081515.0853098239602 – 1532.7218624358614904
2Muse Wonder (Max)
Model details
Model variant
Muse Wonder (Max)
Organization
meta
Model license
Proprietary
Variance
29.08683323846113
1508.87950559771371498.3089865891718 – 1519.45002460625553247
3Claude Opus 5.5 (High)
Model details
Model variant
Claude Opus 5.5 (High)
Organization
anthropic
Model license
Proprietary
Variance
13.990153311675366
1508.16647964311781500.8355453341774 – 1515.4974139520588300
4Claude Fable 5 (High)
Model details
Model variant
Claude Fable 5 (High)
Organization
anthropic
Model license
Proprietary
Variance
4.785559590088843
1503.60134434013071499.3137424347174 – 1507.88894624554442004
5Claude Opus 4.6 (High)
Model details
Model variant
Claude Opus 4.6 (High)
Organization
anthropic
Model license
Proprietary
Variance
2.9065443353877143
1503.05323759441421499.711775283552 – 1506.394699905276681394
6Claude Fable 5.1 (Max)
Model details
Model variant
Claude Fable 5.1 (Max)
Organization
anthropic
Model license
Proprietary
Variance
9.518034279509463
1502.28622788998631496.239481927182 – 1508.332973852790714590
7Claude Opus 4.7 (High)
Model details
Model variant
Claude Opus 4.7 (High)
Organization
anthropic
Model license
Proprietary
Variance
3.6803094220144255
1501.05780362944071497.2977827395944 – 1504.817824519287165116
8Claude Opus 4.6
Model details
Model variant
Claude Opus 4.6
Organization
anthropic
Model license
Proprietary
Variance
2.7587430013698993
1497.2091057296481493.9537105713546 – 1500.464500887941586071
9Gemini 3.8 Flash (High)
Model details
Model variant
Gemini 3.8 Flash (High)
Organization
google
Model license
Proprietary
Variance
5.578180928760354
1496.38026159123731491.7511847575463 – 1501.009338424928337454
10Muse Spark 1.3 (Max)
Model details
Model variant
Muse Spark 1.3 (Max)
Organization
meta
Model license
Proprietary
Variance
8.15438045929107
1494.4127248492861488.8158760267218 – 1500.009573671850417561
11Claude Opus 4.7
Model details
Model variant
Claude Opus 4.7
Organization
anthropic
Model license
Proprietary
Variance
3.681928855943243
1493.58657455974281489.8257265063335 – 1497.347422613151866216
12Muse Spark 1.2 (xHigh)
Model details
Model variant
Muse Spark 1.2 (xHigh)
Organization
meta
Model license
Proprietary
Variance
13.357467043490843
1493.06086672704171485.8976160964726 – 1500.2241173576118248
13Muse Spark 1.1
Model details
Model variant
Muse Spark 1.1
Organization
meta
Model license
Proprietary
Variance
4.69289000022992
1490.17583779855521485.9299522977522 – 1494.421723299358542810
14Claude Opus 5 (Max)
Model details
Model variant
Claude Opus 5 (Max)
Organization
anthropic
Model license
Proprietary
Variance
6.072401484708754
1489.99184642576691485.162055514534 – 1494.82163733732495
15Claude Opus 5 (High)
Model details
Model variant
Claude Opus 5 (High)
Organization
anthropic
Model license
Proprietary
Variance
3.5060682544858994
1489.9051972829391486.2352631115743 – 1493.575131454303866824
16Muse Spark
Model details
Model variant
Muse Spark
Organization
meta
Model license
Proprietary
Variance
8.545086868927068
1489.04139327499871483.3120303674639 – 1494.770756182533714150
17Gemini 3.7 Flash (High)
Model details
Model variant
Gemini 3.7 Flash (High)
Organization
google
Model license
Proprietary
Variance
6.20492913991812
1487.58787538929531482.7056648473051 – 1492.470085931285427232
18Kimi K3 (Max)
Model details
Model variant
Kimi K3 (Max)
Organization
moonshot
Model license
Kimi K3 license
Variance
5.469742975879085
1487.0719832237271482.4881210528476 – 1491.655845394606632795
19Gemini 3.1 Pro Preview
Model details
Model variant
Gemini 3.1 Pro Preview
Organization
google
Model license
Proprietary
Variance
2.2813174134582543
1486.90943588795681483.9491002818586 – 1489.869771494055127649
20Gemini 3 Pro
Model details
Model variant
Gemini 3 Pro
Organization
google
Model license
Proprietary
Variance
3.740384869043396
1485.45906795126981481.6684829768922 – 1489.249652925647542072
21gpt-5.6-sol-xhigh
Model details
Model variant
gpt-5.6-sol-xhigh
Organization
openai
Model license
Proprietary
Variance
4.899512898441768
1484.73949509110051480.4011455154182 – 1489.07784466678340442
22gpt-6.1-sol-max
Model details
Model variant
gpt-6.1-sol-max
Organization
openai
Model license
Proprietary
Variance
17.229067714644195
1483.84694220640721475.7115409166886 – 1491.9823434961266320
23gemini-3.6-flash-high
Model details
Model variant
gemini-3.6-flash-high
Organization
google
Model license
Proprietary
Variance
5.09307645614022
1482.70200399233521478.278787574737 – 1487.125220409933336122
24qwen3.8-max
Model details
Model variant
qwen3.8-max
Organization
alibaba
Model license
Proprietary
Variance
6.447493817048
1482.35301838626791477.3762943638942 – 1487.329742408641327766
25claude-opus-4-8-high
Model details
Model variant
claude-opus-4-8-high
Organization
anthropic
Model license
Proprietary
Variance
3.894437668975512
1481.49530193650781477.627444398396 – 1485.363159474619864100
26gpt-5.5-high
Model details
Model variant
gpt-5.5-high
Organization
openai
Model license
Proprietary
Variance
3.6079892815190755
1481.44023122199541477.7173368841902 – 1485.163125559800469401
27mimo-v2.6-pro
Model details
Model variant
mimo-v2.6-pro
Organization
xiaomi
Model license
MIT
Variance
22.84196543522433
1479.1947552293771469.827446672319 – 1488.56206378643514075
28glm-5.3-max
Model details
Model variant
glm-5.3-max
Organization
zai
Model license
MIT
Variance
7.1160838945186855
1478.5388519475971473.3104541772093 – 1483.767249717985122543
29gemini-3.5-flash-high
Model details
Model variant
gemini-3.5-flash-high
Organization
google
Model license
Proprietary
Variance
3.9412818782484575
1477.47500005635041473.5839498078906 – 1481.366050304810248486
30gpt-6-astra-max
Model details
Model variant
gpt-6-astra-max
Organization
openai
Model license
Proprietary
Variance
10.331275012641141
1477.3192315869181471.0194563904267 – 1483.619006783409312163
31gpt-5.5
Model details
Model variant
gpt-5.5
Organization
openai
Model license
Proprietary
Variance
3.5400925066969027
1476.67219770177421472.9844992886817 – 1480.359896114866470985
32glm-5.2-max
Model details
Model variant
glm-5.2-max
Organization
zai
Model license
MIT
Variance
4.546187780220516
1475.88110790280581471.702113628 – 1480.060102177611749820
33gemini-3.5-flash-medium
Model details
Model variant
gemini-3.5-flash-medium
Organization
google
Model license
Proprietary
Variance
4.46881065933409
1475.66604173846941471.5227637939777 – 1479.80931968296147292
34gpt-5.2-chat-latest-20260210
Model details
Model variant
gpt-5.2-chat-latest-20260210
Organization
openai
Model license
Proprietary
Variance
4.252045058041056
1475.63730781685511471.595766527421 – 1479.678849106289135999
35gpt-5.4-high
Model details
Model variant
gpt-5.4-high
Organization
openai
Model license
Proprietary
Variance
3.688633291891322
1475.1216703994311471.3573998332465 – 1478.885940965615264776
36claude-sonnet-5.5-xhigh
Model details
Model variant
claude-sonnet-5.5-xhigh
Organization
anthropic
Model license
Proprietary
Variance
15.597695903481656
1474.938713507291467.1980477406435 – 1482.67937927393656831
37grok-4.20-beta1
Model details
Model variant
grok-4.20-beta1
Organization
xai
Model license
Proprietary
Variance
5.440388226468636
1474.73026375331371470.1587183537176 – 1479.3018091529127908
38deepseek-v4.1-flash-max
Model details
Model variant
deepseek-v4.1-flash-max
Organization
deepseek
Model license
MIT
Variance
10.082279081537232
1474.63199797916951468.4086018074258 – 1480.855394150912812793
39qwen3.7-max-preview
Model details
Model variant
qwen3.7-max-preview
Organization
alibaba
Model license
Proprietary
Variance
24.627242086396368
1474.3464535721021464.6199672413577 – 1484.07293990284643934
40claude-opus-4-8
Model details
Model variant
claude-opus-4-8
Organization
anthropic
Model license
Proprietary
Variance
3.8514375910149865
1474.31883472239091470.4723897525055 – 1478.165279692276565172
41glm-5.3-flash
Model details
Model variant
glm-5.3-flash
Organization
zai
Model license
MIT
Variance
6.1784609974282905
1473.83815370255021468.9663672235586 – 1478.70994018154232925
42claude-opus-4-5-20251101-high-32k
Model details
Model variant
claude-opus-4-5-20251101-high-32k
Organization
anthropic
Model license
Proprietary
Variance
3.82223919212547
1473.66378312599521469.8319461697308 – 1477.495620082259637509
43gpt-5.5-instant
Model details
Model variant
gpt-5.5-instant
Organization
openai
Model license
Proprietary
Variance
6.511901044019009
1473.10712930514521468.1056095656027 – 1478.108649044687827158
44gemini-3-flash
Model details
Model variant
gemini-3-flash
Organization
google
Model license
Proprietary
Variance
4.9081641252869055
1472.79537166182171468.45319359402 – 1477.137549729623331325
45claude-sonnet-4-6
Model details
Model variant
claude-sonnet-4-6
Organization
anthropic
Model license
Proprietary
Variance
3.213289759865599
1472.1026645496351468.5893014469252 – 1475.616027652344770931
46grok-4.20-beta-0309-reasoning
Model details
Model variant
grok-4.20-beta-0309-reasoning
Organization
xai
Model license
Proprietary
Variance
3.5144476601607106
1471.5496196427071467.875302568203 – 1475.223936717211266436
47grok-4.20-multi-agent-beta-0309
Model details
Model variant
grok-4.20-multi-agent-beta-0309
Organization
xai
Model license
Proprietary
Variance
3.562517061829047
1470.31326982986461466.6139100756589 – 1474.012629584070364946
48claude-opus-4-5-20251101
Model details
Model variant
claude-opus-4-5-20251101
Organization
anthropic
Model license
Proprietary
Variance
2.5522718913873965
1469.63084826890851466.4996428508657 – 1472.76205368695172899
49mimo-v2.5-pro
Model details
Model variant
mimo-v2.5-pro
Organization
xiaomi
Model license
MIT
Variance
3.2638339597299986
1467.25613257124471463.7152451466172 – 1470.797019995872575721
50ernie-5.1
Model details
Model variant
ernie-5.1
Organization
baidu
Model license
Proprietary
Variance
5.365094306312365
1467.00702907048961462.4672285410786 – 1471.546829599900539468
51gpt-5.6-terra-xhigh
Model details
Model variant
gpt-5.6-terra-xhigh
Organization
openai
Model license
Proprietary
Variance
4.716499091410444
1466.4293954209741462.172843173263 – 1470.68594766868543271
52grok-4.5
Model details
Model variant
grok-4.5
Organization
xai
Model license
Proprietary
Variance
4.899220315795222
1465.70914911371661461.370929075886 – 1470.047369151547439896
53grok-4.1-thinking
Model details
Model variant
grok-4.1-thinking
Organization
xai
Model license
Proprietary
Variance
2.6333094921446305
1465.18465006949081462.004123387286 – 1468.365176751695366509
54glm-5.1
Model details
Model variant
glm-5.1
Organization
zai
Model license
MIT
Variance
3.345647175756761
1465.16547885524191461.580487104311 – 1468.750470606172562889
55gpt-5.4
Model details
Model variant
gpt-5.4
Organization
openai
Model license
Proprietary
Variance
3.5412857778020648
1464.74131314972621461.0529932764323 – 1468.429633023020467870
56deepseek-v4-pro-high-20260813
Model details
Model variant
deepseek-v4-pro-high-20260813
Organization
deepseek
Model license
MIT
Variance
11.38115229587885
1464.57803980461811457.965912470948 – 1471.19016713828829800
57qwen3.5-max-preview
Model details
Model variant
qwen3.5-max-preview
Organization
alibaba
Model license
Proprietary
Variance
6.205349958853094
1464.35900783126481459.47663173607 – 1469.241383926459822600
58claude-sonnet-5-high
Model details
Model variant
claude-sonnet-5-high
Organization
anthropic
Model license
Proprietary
Variance
4.431799013208923
1461.07443456340981456.948350050117 – 1465.200519076702749595
59kimi-k2.6
Model details
Model variant
kimi-k2.6
Organization
moonshot
Model license
Modified MIT
Variance
5.102302957644872
1460.82901673514561456.4017956312816 – 1465.256237839009640013
60qwen3.6-max-preview
Model details
Model variant
qwen3.6-max-preview
Organization
alibaba
Model license
Proprietary
Variance
17.46386113993701
1460.57663193782151452.3859846240014 – 1468.76727925164165426
61gpt-6-sol-max
Model details
Model variant
gpt-6-sol-max
Organization
openai
Model license
Proprietary
Variance
10.486182527456437
1459.02434360541341452.6775146046048 – 1465.371172606222212466
62grok-4.1
Model details
Model variant
grok-4.1
Organization
xai
Model license
Proprietary
Variance
2.608859340583804
1459.02302284624261455.857296116748 – 1462.188749575737168648
63gemini-3-flash (thinking-minimal)
Model details
Model variant
gemini-3-flash (thinking-minimal)
Organization
google
Model license
Proprietary
Variance
2.376160877888042
1458.29068948608281455.2694440204261 – 1461.311934951739491039
64deepseek-v4-pro
Model details
Model variant
deepseek-v4-pro
Organization
deepseek
Model license
MIT
Variance
3.954923013483331
1457.79214462810841453.8943665565255 – 1461.689922699691157594
65glm-5
Model details
Model variant
glm-5
Organization
zai
Model license
MIT
Variance
4.686678868325896
1457.26666318248431453.0235883683322 – 1461.509737996636429272
66claude-sonnet-4-5-20250929-high-32k
Model details
Model variant
claude-sonnet-4-5-20250929-high-32k
Organization
anthropic
Model license
Proprietary
Variance
1.9837973709892494
1456.39755116245151453.6369939887531 – 1459.158108336149683940
67dola-seed-2.0-pro
Model details
Model variant
dola-seed-2.0-pro
Organization
bytedance
Model license
Proprietary
Variance
2.999738928683731
1456.17498001285161452.7803705261254 – 1459.56958949957879140
68gpt-5.1-high
Model details
Model variant
gpt-5.1-high
Organization
openai
Model license
Proprietary
Variance
3.582140195702419
1455.71543245660771452.0058982470682 – 1459.424966666147241651
69qwen3.7-plus
Model details
Model variant
qwen3.7-plus
Organization
alibaba
Model license
Proprietary
Variance
4.886680649025687
1455.6827150602561451.3500504663698 – 1460.015379654142242075
70claude-sonnet-4-5-20250929
Model details
Model variant
claude-sonnet-4-5-20250929
Organization
anthropic
Model license
Proprietary
Variance
2.132293386904047
1454.93178811271831452.0697753175984 – 1457.793800907838482688
71deepseek-v4-pro-high-preview
Model details
Model variant
deepseek-v4-pro-high-preview
Organization
deepseek
Model license
MIT
Variance
4.091516156406905
1454.86223563196631450.897719163462 – 1458.826752100470554902
72gemini-3.5-flash-lite
Model details
Model variant
gemini-3.5-flash-lite
Organization
google
Model license
Proprietary
Variance
5.206826414442539
1454.75740240871191450.2850641771397 – 1459.229740640284335851
73grok-4.6-high
Model details
Model variant
grok-4.6-high
Organization
xai
Model license
Proprietary
Variance
6.084596344103329
1454.48914698128871449.6545088049184 – 1459.323785157659428965
74hy3
Model details
Model variant
hy3
Organization
tencent
Model license
Apache 2.0
Variance
9.837412919506436
1453.19218803491641447.0448295263823 – 1459.339546543450812208
75gpt-5.6-luna-xhigh
Model details
Model variant
gpt-5.6-luna-xhigh
Organization
openai
Model license
Proprietary
Variance
4.816760873175102
1452.56624587262351448.2646893469653 – 1456.867802398281841109
76gemma-4-31b
Model details
Model variant
gemma-4-31b
Organization
google
Model license
Apache 2.0
Variance
14.39556973264088
1452.16308008970581444.7266838974383 – 1459.59947628197356147
77mimo-v2.6-flash
Model details
Model variant
mimo-v2.6-flash
Organization
xiaomi
Model license
MIT
Variance
10.960873706883909
1450.93170482162781444.4428108493223 – 1457.420598793933610917
78gpt-5.3-chat-latest
Model details
Model variant
gpt-5.3-chat-latest
Organization
openai
Model license
Proprietary
Variance
4.674878812274269
1450.04372522983891445.8059953600753 – 1454.281455099602534345
79kimi-k2.5-thinking
Model details
Model variant
kimi-k2.5-thinking
Organization
moonshot
Model license
Modified MIT
Variance
2.7992465853806894
1449.84115077867821446.5619450079605 – 1453.120356549395974759
80claude-opus-4-1-20250805-thinking-16k
Model details
Model variant
claude-opus-4-1-20250805-thinking-16k
Organization
anthropic
Model license
Proprietary
Variance
3.097865763793121
1449.7403174601051446.2906328710956 – 1453.190002049114449542
81ernie-5.0-preview-1203
Model details
Model variant
ernie-5.0-preview-1203
Organization
baidu
Model license
Proprietary
Variance
11.00418023396379
1448.54241266683361442.0407124873213 – 1455.04411284634569806
82claude-opus-4-1-20250805
Model details
Model variant
claude-opus-4-1-20250805
Organization
anthropic
Model license
Proprietary
Variance
2.2967059590471846
1448.081228444611445.1109252000028 – 1451.051531689216777238
83mimo-v2-pro
Model details
Model variant
mimo-v2-pro
Organization
xiaomi
Model license
Proprietary
Variance
5.659114742358539
1447.78904377743081443.1265062446753 – 1452.451581310186225447
84Step 5 Preview
Model details
Model variant
Step 5 Preview
Organization
stepfun
Model license
Proprietary
Variance
14.676189383323775
1447.27016095956061439.7616339961178 – 1454.77868792300327116
85gpt-5.4-mini-high
Model details
Model variant
gpt-5.4-mini-high
Organization
openai
Model license
Proprietary
Variance
3.6560031133465682
1446.99939181522151443.2518078724324 – 1450.746975758010663449
86ernie-5.0-0110
Model details
Model variant
ernie-5.0-0110
Organization
baidu
Model license
Proprietary
Variance
3.9470569680118035
1446.1917209891891442.2978210411227 – 1450.085620937255336487
87gemini-2.5-pro
Model details
Model variant
gemini-2.5-pro
Organization
google
Model license
Proprietary
Variance
1.5762979032908633
1445.4137423459761442.9529937841278 – 1447.8744909078243125366
88gpt-4.5-preview-2025-02-27
Model details
Model variant
gpt-4.5-preview-2025-02-27
Organization
openai
Model license
Proprietary
Variance
8.492623379194677
1444.62709450077451438.915346695519 – 1450.338842306029814547
89grok-4.7-xhigh
Model details
Model variant
grok-4.7-xhigh
Organization
xai
Model license
Proprietary
Variance
10.727943725731812
1443.97893363946951437.5593577926459 – 1450.398509486293311591
90qwen3.6-plus
Model details
Model variant
qwen3.6-plus
Organization
alibaba
Model license
Proprietary
Variance
4.448402234185706
1443.058239162631438.9244329261805 – 1447.192045399079248165
91gpt-6-luna-max
Model details
Model variant
gpt-6-luna-max
Organization
openai
Model license
Proprietary
Variance
5.567588338338605
1442.81299430723951438.1883147148455 – 1447.437673899633449617
92chatgpt-4o-latest-20250326
Model details
Model variant
chatgpt-4o-latest-20250326
Organization
openai
Model license
Proprietary
Variance
2.0522657582761488
1442.59677569646851439.7889839663826 – 1445.404567426554481914
93grok-4.3
Model details
Model variant
grok-4.3
Organization
xai
Model license
Proprietary
Variance
3.4235949056808814
1441.71795086812951438.0914375496773 – 1445.344464186581571347
94qwen3.5-397b-a17b
Model details
Model variant
qwen3.5-397b-a17b
Organization
alibaba
Model license
Apache 2.0
Variance
2.4853015947403896
1441.56559700645361438.475745273247 – 1444.655448739660493567
95glm-4.7
Model details
Model variant
glm-4.7
Organization
zai
Model license
MIT
Variance
9.551016794592911
1441.32662917773541435.2694154856003 – 1447.383842869870312253
96minimax-m3
Model details
Model variant
minimax-m3
Organization
minimax
Model license
MiniMax Community License
Variance
3.838097112758699
1441.31559557353511437.475817974704 – 1445.155373172366663973
97inkling
Model details
Model variant
inkling
Organization
thinky
Model license
Apache 2.0
Variance
4.842863786452582
1440.87173961417491436.5585433735794 – 1445.184935854770640648
98deepseek-v4-flash-high-preview
Model details
Model variant
deepseek-v4-flash-high-preview
Organization
deepseek
Model license
MIT
Variance
4.387881566144908
1438.6714933770641434.5659037304447 – 1442.777083023683451809
99gpt-5.1
Model details
Model variant
gpt-5.1
Organization
openai
Model license
Proprietary
Variance
3.356952045123321
1438.60831705449981435.0172736066443 – 1442.199360502355144434
100qwen3.8-27b
Model details
Model variant
qwen3.8-27b
Organization
alibaba
Model license
Apache 2.0
Variance
6.793474596352551
1437.7521045738141432.6435966790054 – 1442.860612468622323294
101gemma-4-26b-a4b
Model details
Model variant
gemma-4-26b-a4b
Organization
google
Model license
Apache 2.0
Variance
14.396913014011185
1437.5197315251641430.082988387981 – 1444.9564746623476094
102gpt-5.2-high
Model details
Model variant
gpt-5.2-high
Organization
openai
Model license
Proprietary
Variance
3.2855125975698973
1437.24566714453521433.6930397578767 – 1440.79829453119449655
103longcat-flash-chat-2602-exp
Model details
Model variant
longcat-flash-chat-2602-exp
Organization
meituan
Model license
Proprietary
Variance
5.331450865847573
1436.20950733073231431.683963279935 – 1440.735051381529729291
104deepseek-v4-flash
Model details
Model variant
deepseek-v4-flash
Organization
deepseek
Model license
MIT
Variance
4.2399929697769725
1435.64754808114231431.6117385720809 – 1439.683357590203751987
105gpt-5.2
Model details
Model variant
gpt-5.2
Organization
openai
Model license
Proprietary
Variance
2.6210480593479897
1435.40421888434481432.2311055571777 – 1438.57733221151283855
106gpt-5-high
Model details
Model variant
gpt-5-high
Organization
openai
Model license
Proprietary
Variance
5.282817509896719
1434.80350753190921430.298651716069 – 1439.308363347749531722
107qwen3-max-preview
Model details
Model variant
qwen3-max-preview
Organization
alibaba
Model license
Proprietary
Variance
5.303086246869747
1434.1620648368111429.6485753397656 – 1438.675554333856327370
108mimo-v2.5
Model details
Model variant
mimo-v2.5
Organization
xiaomi
Model license
MIT
Variance
4.641398322360331
1433.7801609024171429.557633161148 – 1438.00268864368647362
109glm-5v-turbo
Model details
Model variant
glm-5v-turbo
Organization
zai
Model license
Proprietary
Variance
10.769141571585735
1433.7365499129491427.304659531306 – 1440.16844029459210482
110gemini-3.1-flash-lite-preview
Model details
Model variant
gemini-3.1-flash-lite-preview
Organization
google
Model license
Proprietary
Variance
3.4143510056041553
1432.92709435583011429.3054802422857 – 1436.548708469374364211
111mistral-large-4
Model details
Model variant
mistral-large-4
Organization
mistral
Model license
Proprietary
Variance
13.693025927552881
1431.7700909017661424.517422756084 – 1439.02275904744837451
112o3-2025-04-16
Model details
Model variant
o3-2025-04-16
Organization
openai
Model license
Proprietary
Variance
3.4311003591731453
1431.69116285789321428.060676562721 – 1435.321649153065258908
113mimo-v2-omni
Model details
Model variant
mimo-v2-omni
Organization
xiaomi
Model license
Proprietary
Variance
8.003916643190918
1430.86117848921621425.3162063351756 – 1436.40615064325720619
114kimi-k2.5-instant
Model details
Model variant
kimi-k2.5-instant
Organization
moonshot
Model license
Modified MIT
Variance
11.01413505011314
1430.52924675231771424.0246063901936 – 1437.03388711444188376
115grok-4-1-fast-reasoning
Model details
Model variant
grok-4-1-fast-reasoning
Organization
xai
Model license
Proprietary
Variance
2.6591212586378394
1430.37482016673431427.1787436948255 – 1433.570896638643357541
116kimi-k2-thinking-turbo
Model details
Model variant
kimi-k2-thinking-turbo
Organization
moonshot
Model license
Modified MIT
Variance
2.481661378233848
1430.09796857661061427.01038052258 – 1433.18555663064163368
117mistral-medium-3.5
Model details
Model variant
mistral-medium-3.5
Organization
mistral
Model license
Modified MIT
Variance
10.659428579463944
1426.49270302030441420.0936596589775 – 1432.891746381631311778
118gpt-5-chat
Model details
Model variant
gpt-5-chat
Organization
openai
Model license
Proprietary
Variance
4.803119782412296
1426.35307502309021422.0576138307385 – 1430.648536215441731188
119claude-opus-4-20250514-thinking-16k
Model details
Model variant
claude-opus-4-20250514-thinking-16k
Organization
anthropic
Model license
Proprietary
Variance
5.036195733985207
1426.25070437299251421.852257087295 – 1430.6491516586935904
120amazon-nova-experimental-chat-26-02-10
Model details
Model variant
amazon-nova-experimental-chat-26-02-10
Organization
amazon
Model license
Proprietary
Variance
24.335411026982094
1426.1107496225171416.4420641200911 – 1435.77943512494273526
121nvidia-nemotron-3-ultra-550b-a55b-nvfp4
Model details
Model variant
nvidia-nemotron-3-ultra-550b-a55b-nvfp4
Organization
nvidia
Model license
OpenMDW-1.1
Variance
12.340147988966878
1426.0208389704551419.1357703185906 – 1432.905907622319811567
122deepseek-v3.2-exp-thinking
Model details
Model variant
deepseek-v3.2-exp-thinking
Organization
deepseek
Model license
MIT
Variance
11.211052950886724
1425.08930876772961418.526778901325 – 1431.65183863413438998
123deepseek-v3.2
Model details
Model variant
deepseek-v3.2
Organization
deepseek
Model license
MIT
Variance
3.172636133838645
1424.63584144321841421.1447741191487 – 1428.126908767288148112
124muse-glimmer
Model details
Model variant
muse-glimmer
Organization
meta
Model license
Apache-2.0
Variance
24.447105562343737
1424.54276137118041414.851912631111 – 1434.23361011124983897
125glm-4.6
Model details
Model variant
glm-4.6
Organization
zai
Model license
MIT
Variance
3.960199337833776
1424.12284064502841420.2224633968601 – 1428.023217893196735824
126qwen3-max-2025-09-23
Model details
Model variant
qwen3-max-2025-09-23
Organization
alibaba
Model license
Proprietary
Variance
10.941978479192366
1423.43916687489131416.9558683513974 – 1429.92246539838549027
127deepseek-v3.2-thinking
Model details
Model variant
deepseek-v3.2-thinking
Organization
deepseek
Model license
MIT
Variance
3.3246473815701725
1422.43486393753761418.861140947485 – 1426.008586927590242071
128qwen3-235b-a22b-instruct-2507
Model details
Model variant
qwen3-235b-a22b-instruct-2507
Organization
alibaba
Model license
Apache 2.0
Variance
1.6936339585150162
1422.1310043359561419.580313231772 – 1424.681695440140498134
129deepseek-v3.2-exp
Model details
Model variant
deepseek-v3.2-exp
Organization
deepseek
Model license
MIT
Variance
10.584760957116448
1421.69815896257071415.321567134356 – 1428.074750790785412004
130deepseek-r1-0528
Model details
Model variant
deepseek-r1-0528
Organization
deepseek
Model license
MIT
Variance
8.393254345955512
1421.42902223289341415.7507882696264 – 1427.107256196160518167
131grok-4-fast-chat
Model details
Model variant
grok-4-fast-chat
Organization
xai
Model license
Proprietary
Variance
15.863950291787575
1418.64093857130111410.8344853574888 – 1426.44739178511356340
132kimi-k2-0905-preview
Model details
Model variant
kimi-k2-0905-preview
Organization
moonshot
Model license
Modified MIT
Variance
11.085403966020893
1418.61240496460441412.0867538211378 – 1425.138056108071211589
133ernie-5.0-preview-1022
Model details
Model variant
ernie-5.0-preview-1022
Organization
baidu
Model license
Proprietary
Variance
19.960478469721863
1418.28969568623031409.533134941121 – 1427.04625643133954753
134kimi-k2-0711-preview
Model details
Model variant
kimi-k2-0711-preview
Organization
moonshot
Model license
Modified MIT
Variance
6.2356336066358615
1417.76654072040361412.8722655216814 – 1422.660815919125827146
135deepseek-v3.1
Model details
Model variant
deepseek-v3.1
Organization
deepseek
Model license
MIT
Variance
9.56737443751662
1417.02861314000321410.9662146935234 – 1423.091011586483314610
136qwen3.5-122b-a10b
Model details
Model variant
qwen3.5-122b-a10b
Organization
alibaba
Model license
Apache 2.0
Variance
4.782215571904489
1416.31430071759771412.0281971034565 – 1420.600404331738729732
137deepseek-v3.1-terminus-thinking
Model details
Model variant
deepseek-v3.1-terminus-thinking
Organization
deepseek
Model license
MIT
Variance
26.59174511317227
1416.08177075767731405.9747883285522 – 1426.18875318680263375
138nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4
Model details
Model variant
nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4
Organization
nvidia
Model license
OpenMDW-1.1
Variance
36.3384257668498
1415.87802425004091404.063094449479 – 1427.69295405060282523
139deepseek-v3.1-thinking
Model details
Model variant
deepseek-v3.1-thinking
Organization
deepseek
Model license
MIT
Variance
11.546831814639715
1415.74603381173821409.085952811824 – 1422.406114811652511459
140minimax-m2.7
Model details
Model variant
minimax-m2.7
Organization
minimax
Model license
Modified MIT
Variance
2.9221413878946043
1415.00353415699671411.653118390283 – 1418.353949923710284977
141deepseek-v3.1-terminus
Model details
Model variant
deepseek-v3.1-terminus
Organization
deepseek
Model license
MIT
Variance
24.580350918700017
1414.68910980491771404.9718876785898 – 1424.40633193124563608
142gpt-4.1-2025-04-14
Model details
Model variant
gpt-4.1-2025-04-14
Organization
openai
Model license
Proprietary
Variance
3.5899291141551335
1414.58632213060881410.8727571505342 – 1418.299887110683650312
143claude-opus-4-20250514
Model details
Model variant
claude-opus-4-20250514
Organization
anthropic
Model license
Proprietary
Variance
4.863005434080417
1414.27185761790841409.9497013134892 – 1418.594013922327843043
144claude-haiku-4-5-20251001
Model details
Model variant
claude-haiku-4-5-20251001
Organization
anthropic
Model license
Proprietary
Variance
1.504296501292362
1414.2644347786551411.8605435448783 – 1416.6683260124319149199
145mistral-large-3
Model details
Model variant
mistral-large-3
Organization
mistral
Model license
Apache 2.0
Variance
2.130676478268279
1414.24710038652031411.3861729230061 – 1417.108027850034284205
146qwen3-vl-235b-a22b-instruct
Model details
Model variant
qwen3-vl-235b-a22b-instruct
Organization
alibaba
Model license
Apache 2.0
Variance
11.078557512859508
1413.31517839441361406.7915427149521 – 1419.838814073874811320
147amazon-nova-experimental-chat-26-01-10
Model details
Model variant
amazon-nova-experimental-chat-26-01-10
Organization
amazon
Model license
Proprietary
Variance
24.381264455924015
1412.6243657304271402.9465755175795 – 1422.30215594327433539
148grok-3-preview-02-24
Model details
Model variant
grok-3-preview-02-24
Organization
xai
Model license
Proprietary
Variance
4.916839412632139
1411.2165991281571406.870585307241 – 1415.56261294907332499
149grok-4-0709
Model details
Model variant
grok-4-0709
Organization
xai
Model license
Proprietary
Variance
4.04719547052785
1410.85082366005351406.9078381491324 – 1414.793809170974339693
150glm-4.5
Model details
Model variant
glm-4.5
Organization
zai
Model license
MIT
Variance
6.307421134549811
1410.79607678518441405.8737096155037 – 1415.718443954864823796
151gemini-2.5-flash
Model details
Model variant
gemini-2.5-flash
Organization
google
Model license
Proprietary
Variance
1.5463182544867693
1409.23697344099831406.7997377325987 – 1411.6742091493982125521
152hunyuan-hy3-preview
Model details
Model variant
hunyuan-hy3-preview
Organization
tencent
Model license
tencent-hunyuan-community
Variance
14.280815215671
1409.1301818682111401.7234846571093 – 1416.53687907931276879
153qwen3.5-27b
Model details
Model variant
qwen3.5-27b
Organization
alibaba
Model license
Apache 2.0
Variance
4.7963913671422445
1408.67988598669291404.387434481456 – 1412.972337491929528671
154mistral-medium-2508
Model details
Model variant
mistral-medium-2508
Organization
mistral
Model license
Proprietary
Variance
1.7568915987452463
1407.73044526489481405.1325563663845 – 1410.32833416340595321
155grok-4-fast-reasoning
Model details
Model variant
grok-4-fast-reasoning
Organization
xai
Model license
Proprietary
Variance
6.673657206341331
1405.34453762938621400.281279849894 – 1410.407795408878418269
156Inkling Small
Model details
Model variant
Inkling Small
Organization
thinky
Model license
Apache 2.0
Variance
5.668108423281059
1403.98041305107861399.3141720479516 – 1408.646654054205632304
157gemini-2.5-flash-preview-09-2025
Model details
Model variant
gemini-2.5-flash-preview-09-2025
Organization
google
Model license
Proprietary
Variance
4.268778163823948
1403.02106630706951398.9715804716816 – 1407.070552142457732995
158o1-2024-12-17
Model details
Model variant
o1-2024-12-17
Organization
openai
Model license
Proprietary
Variance
5.215104269963381
1402.28363093635971397.8077390365602 – 1406.759522836159227807
159qwen3-235b-a22b-no-thinking
Model details
Model variant
qwen3-235b-a22b-no-thinking
Organization
alibaba
Model license
Apache 2.0
Variance
5.345404055218789
1402.00834711321681397.4768849255674 – 1406.53980930086637484
160claude-sonnet-4-20250514-thinking-32k
Model details
Model variant
claude-sonnet-4-20250514-thinking-32k
Organization
anthropic
Model license
Proprietary
Variance
5.154678411141355
1401.9163897519091397.4665038151325 – 1406.366275688685434132
161gpt-5.4-nano-high
Model details
Model variant
gpt-5.4-nano-high
Organization
openai
Model license
Proprietary
Variance
3.7212042394726432
1401.1894867815931397.408633326442 – 1404.970340236743862396
162longcat-flash-chat
Model details
Model variant
longcat-flash-chat
Organization
meituan
Model license
MIT
Variance
10.719705180353532
1400.62451222971691394.2074018192354 – 1407.041622640198311168
163qwen3-235b-a22b-thinking-2507
Model details
Model variant
qwen3-235b-a22b-thinking-2507
Organization
alibaba
Model license
Apache 2.0
Variance
11.248162635660568
1399.7562186310161393.182836429032 – 1406.3296008338823
164qwen3-next-80b-a3b-instruct
Model details
Model variant
qwen3-next-80b-a3b-instruct
Organization
alibaba
Model license
Apache 2.0
Variance
5.932235903771741
1398.53120037493141393.7574764680655 – 1403.304924281797222760
165deepseek-r1
Model details
Model variant
deepseek-r1
Organization
deepseek
Model license
MIT
Variance
6.239926486061999
1398.08158723070851393.1856276066546 – 1402.977546854762518524
166qwen3.5-flash
Model details
Model variant
qwen3.5-flash
Organization
alibaba
Model license
Proprietary
Variance
3.500276384713683
1395.90100747238851392.2341058384577 – 1399.567909106319661802
167deepseek-v3-0324
Model details
Model variant
deepseek-v3-0324
Organization
deepseek
Model license
MIT
Variance
3.944876222051854
1395.1944555549511391.3016314438785 – 1399.087279666023544973
168qwen3-vl-235b-a22b-thinking
Model details
Model variant
qwen3-vl-235b-a22b-thinking
Organization
alibaba
Model license
Apache 2.0
Variance
12.142014882026254
1394.90292446071841388.0733527194186 – 1401.73249620201827859
169qwen3.5-35b-a3b
Model details
Model variant
qwen3.5-35b-a3b
Organization
alibaba
Model license
Apache 2.0
Variance
4.66220029631647
1394.01263204936661389.7806525536546 – 1398.244611545078730457
170hunyuan-vision-1.5-thinking
Model details
Model variant
hunyuan-vision-1.5-thinking
Organization
tencent
Model license
Proprietary
Variance
40.12591165785754
1393.7758370412241381.360441869242 – 1406.1912322132062170
171step-3.5-flash
Model details
Model variant
step-3.5-flash
Organization
stepfun
Model license
Apache 2.0
Variance
3.2861776159810683
1392.81569716716761389.2627102562321 – 1396.36868407810360332
172amazon-nova-experimental-chat-12-10
Model details
Model variant
amazon-nova-experimental-chat-12-10
Organization
amazon
Model license
Proprietary
Variance
23.346161785691752
1392.70829608266791383.2381683580277 – 1402.1784238073083733
173mimo-v2-flash (non-thinking)
Model details
Model variant
mimo-v2-flash (non-thinking)
Organization
xiaomi
Model license
MIT
Variance
3.1581282136355573
1391.5329065900891388.049830437727 – 1395.015982742451148088
174o4-mini-2025-04-16
Model details
Model variant
o4-mini-2025-04-16
Organization
openai
Model license
Proprietary
Variance
4.14594146662398
1391.05477554124381387.0639782002297 – 1395.045572882257644855
175claude-sonnet-4-20250514
Model details
Model variant
claude-sonnet-4-20250514
Organization
anthropic
Model license
Proprietary
Variance
5.026160277108696
1390.88711117498471386.493048393148 – 1395.281173956821239163
176minimax-m2.5
Model details
Model variant
minimax-m2.5
Organization
minimax
Model license
Modified MIT
Variance
3.936274942179198
1390.63932481592631386.7507469142622 – 1394.527902717590742815
177gpt-5-mini-high
Model details
Model variant
gpt-5-mini-high
Organization
openai
Model license
Proprietary
Variance
5.6242102683993185
1389.95547839503981385.3073419786917 – 1394.603614811387826804
178o1-preview
Model details
Model variant
o1-preview
Organization
openai
Model license
Proprietary
Variance
6.535160954746777
1388.58458036156821383.5741361004004 – 1393.595024622735831122
179claude-3-7-sonnet-20250219-thinking-32k
Model details
Model variant
claude-3-7-sonnet-20250219-thinking-32k
Organization
anthropic
Model license
Proprietary
Variance
4.5998975308305425
1388.35460573239081384.1509981217666 – 1392.55821334301538159
180qwen3-coder-480b-a35b-instruct
Model details
Model variant
qwen3-coder-480b-a35b-instruct
Organization
alibaba
Model license
Apache 2.0
Variance
6.449267837399688
1387.55206178000031382.5746531348318 – 1392.529470425168725195
181mistral-medium-2505
Model details
Model variant
mistral-medium-2505
Organization
mistral
Model license
Proprietary
Variance
5.800080402553577
1387.26155902536741382.5413079702723 – 1391.981810080462332782
182hunyuan-t1-20250711
Model details
Model variant
hunyuan-t1-20250711
Organization
tencent
Model license
Proprietary
Variance
19.73036879141866
1387.06058328046861378.3546428241282 – 1395.7665237368094595
183solar-pro4
Model details
Model variant
solar-pro4
Organization
upstage
Model license
Proprietary
Variance
7.350820512336554
1386.4258163784971381.111884284797 – 1391.73974847219721281
184mimo-v2-flash (thinking)
Model details
Model variant
mimo-v2-flash (thinking)
Organization
xiaomi
Model license
MIT
Variance
9.914041673185674
1386.1714455540821380.000190994903 – 1392.342700113261111142
185minimax-m2.1-preview
Model details
Model variant
minimax-m2.1-preview
Organization
minimax
Model license
MIT
Variance
6.975497626089416
1384.4378549186561379.2613612323398 – 1389.614348604972317239
186hunyuan-turbos-20250416
Model details
Model variant
hunyuan-turbos-20250416
Organization
tencent
Model license
Proprietary
Variance
10.977516557850603
1383.06990557968561376.5760871490186 – 1389.563724010352610626
187gpt-4.1-mini-2025-04-14
Model details
Model variant
gpt-4.1-mini-2025-04-14
Organization
openai
Model license
Proprietary
Variance
4.888337801513956
1382.8483140097921378.5149148398377 – 1387.181713179745938709
188qwen3-30b-a3b-instruct-2507
Model details
Model variant
qwen3-30b-a3b-instruct-2507
Organization
alibaba
Model license
Apache 2.0
Variance
6.2604174385862335
1382.3375902054511377.433598383406 – 1387.24158202749623322
189gemini-2.5-flash-lite-preview-09-2025-no-thinking
Model details
Model variant
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Organization
google
Model license
Proprietary
Variance
3.048334149323278
1379.34000798418631375.918012936507 – 1382.762003031865647437
190trinity-large-preview
Model details
Model variant
trinity-large-preview
Organization
Not reported
Model license
Apache 2.0
Variance
4.7178640581301945
1378.70599515990441374.4488270282775 – 1382.963163291531431266
191glm-4.6v
Model details
Model variant
glm-4.6v
Organization
zai
Model license
MIT
Variance
32.48453568097595
1378.25094511771661367.0800899074904 – 1389.42180032794272837
192qwen3-235b-a22b
Model details
Model variant
qwen3-235b-a22b
Organization
alibaba
Model license
Apache 2.0
Variance
5.772922841965766
1374.83373217804111370.1245448413072 – 1379.542919514775125948
193gemini-2.5-flash-lite-preview-06-17-thinking
Model details
Model variant
gemini-2.5-flash-lite-preview-06-17-thinking
Organization
google
Model license
Proprietary
Variance
5.323593367693547
1374.81365138631961370.2914434410661 – 1379.335859331573432381
194claude-3-5-sonnet-20241022
Model details
Model variant
claude-3-5-sonnet-20241022
Organization
anthropic
Model license
Proprietary
Variance
2.6753340160031254
1374.25605716926571371.0502522073134 – 1377.46186213121887769
195qwen2.5-max
Model details
Model variant
qwen2.5-max
Organization
alibaba
Model license
Proprietary
Variance
4.407992815156855
1373.76917943999481369.654191848113 – 1377.884167031876432487
196glm-4.5-air
Model details
Model variant
glm-4.5-air
Organization
zai
Model license
MIT
Variance
4.709399801025887
1372.9828530476271368.7295054947192 – 1377.236200600534630660
197claude-3-7-sonnet-20250219
Model details
Model variant
claude-3-7-sonnet-20250219
Organization
anthropic
Model license
Proprietary
Variance
4.092153015613351
1372.5682468093871368.603421807264 – 1376.533071811509742572
198qwen3-next-80b-a3b-thinking
Model details
Model variant
qwen3-next-80b-a3b-thinking
Organization
alibaba
Model license
Apache 2.0
Variance
8.945493397122354
1369.193400215161363.3313404648811 – 1375.055459965438613474
199trinity-large-thinking
Model details
Model variant
trinity-large-thinking
Organization
Not reported
Model license
Apache 2.0
Variance
5.493567766962007
1367.26435007739381362.6705156925389 – 1371.85818446224930337
200gemma-3-27b-it
Model details
Model variant
gemma-3-27b-it
Organization
google
Model license
Gemma
Variance
3.5705970944708425
1365.45286598163331361.7493134028653 – 1369.156418560401346666
201glm-4.7-flash
Model details
Model variant
glm-4.7-flash
Organization
zai
Model license
MIT
Variance
8.500349030979798
1364.51602039654021358.8016752228536 – 1370.23036557022712021
202minimax-m1
Model details
Model variant
minimax-m1
Organization
minimax
Model license
Apache 2.0
Variance
4.796355665881976
1363.80323732714561359.5108017970663 – 1368.09567285722534303
203amazon-nova-experimental-chat-11-10
Model details
Model variant
amazon-nova-experimental-chat-11-10
Organization
amazon
Model license
Proprietary
Variance
4.76424237639796
1363.73604407098151359.458002357681 – 1368.014085784281926039
204grok-3-mini-high
Model details
Model variant
grok-3-mini-high
Organization
xai
Model license
Proprietary
Variance
7.796014658517288
1363.7124706811611358.239987764219 – 1369.18495359810315596
205o3-mini-high
Model details
Model variant
o3-mini-high
Organization
openai
Model license
Proprietary
Variance
7.222371876210154
1363.58185725131921358.314557739216 – 1368.849156763422118589
206nvidia-nemotron-3-super-120b-a12b
Model details
Model variant
nvidia-nemotron-3-super-120b-a12b
Organization
nvidia
Model license
NVIDIA Open Model
Variance
13.20610725527328
1360.0805689651121352.9580190563502 – 1367.20311887387387878
207gemini-2.0-flash-001
Model details
Model variant
gemini-2.0-flash-001
Organization
google
Model license
Proprietary
Variance
3.7682163217146
1359.90296251156951356.098301182708 – 1363.70762384043143446
208deepseek-v3
Model details
Model variant
deepseek-v3
Organization
deepseek
Model license
DeepSeek
Variance
5.8946819496932195
1358.40930561274221353.6507156986147 – 1363.167895526869421770
209grok-3-mini-beta
Model details
Model variant
grok-3-mini-beta
Organization
xai
Model license
Proprietary
Variance
6.86485014485065
1357.90324445491251352.7679704464801 – 1363.038518463344620931
210mistral-small-2506
Model details
Model variant
mistral-small-2506
Organization
mistral
Model license
Apache 2.0
Variance
7.101793370261857
1356.113046194121350.8899008979465 – 1361.336191490293517462
211intellect-3
Model details
Model variant
intellect-3
Organization
Not reported
Model license
MIT
Variance
17.732191909377747
1355.7998421337491347.5465103810252 – 1364.0531738864735431
212command-a-03-2025
Model details
Model variant
command-a-03-2025
Organization
cohere
Model license
CC-BY-NC-4.0
Variance
3.1360589705346364
1353.70646422331041350.2355794089472 – 1357.177349037673655766
213gemini-2.0-flash-lite-preview-02-05
Model details
Model variant
gemini-2.0-flash-lite-preview-02-05
Organization
google
Model license
Proprietary
Variance
4.86876627748806
1353.57253059328971349.2478149769104 – 1357.897246209668824955
214glm-4.5v
Model details
Model variant
glm-4.5v
Organization
zai
Model license
MIT
Variance
18.53036592313969
1352.17306699938441343.73602737484 – 1360.61010662392914821
215gpt-oss-120b
Model details
Model variant
gpt-oss-120b
Organization
openai
Model license
Apache 2.0
Variance
4.959079847095804
1351.7586077129531347.3939655717056 – 1356.123249854200630206
216nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4
Model details
Model variant
nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4
Organization
nvidia
Model license
OpenMDW-1.1
Variance
8.041851438423315
1351.34647419676681345.7883772973917 – 1356.904571096141819938
217gemini-1.5-pro-002
Model details
Model variant
gemini-1.5-pro-002
Organization
google
Model license
Proprietary
Variance
3.014449720214967
1351.33404442104691347.9311214910852 – 1354.736967351008455606
218step-3
Model details
Model variant
step-3
Organization
stepfun
Model license
Apache 2.0
Variance
14.688921399145777
1348.93467356949331341.4228903807139 – 1356.4464567582736293
219hunyuan-turbos-20250226
Model details
Model variant
hunyuan-turbos-20250226
Organization
tencent
Model license
Proprietary
Variance
35.67042035852818
1348.8356630904711337.129833306806 – 1360.54149287413572220
220o3-mini
Model details
Model variant
o3-mini
Organization
openai
Model license
Proprietary
Variance
3.2896382749416677
1348.09563354283161344.540776306856 – 1351.650490778807156741
221amazon-nova-experimental-chat-10-20
Model details
Model variant
amazon-nova-experimental-chat-10-20
Organization
amazon
Model license
Proprietary
Variance
9.817345651979693
1348.0392623510341341.8981770193845 – 1354.180347682683511626
222llama-3.1-nemotron-ultra-253b-v1
Model details
Model variant
llama-3.1-nemotron-ultra-253b-v1
Organization
nvidia
Model license
Nvidia Open Model
Variance
35.500450840302
1347.58959120974211335.9116838621437 – 1359.26749855734082549
223qwen3-32b
Model details
Model variant
qwen3-32b
Organization
alibaba
Model license
Apache 2.0
Variance
23.282816507667818
1346.80548871985391337.3482173985908 – 1356.26276004111673926
224amazon-nova-experimental-chat-10-09
Model details
Model variant
amazon-nova-experimental-chat-10-09
Organization
amazon
Model license
Proprietary
Variance
31.11402678593228
1346.1442267317041335.2115576777112 – 1357.0768957856972781
225gpt-4o-2024-05-13
Model details
Model variant
gpt-4o-2024-05-13
Organization
openai
Model license
Proprietary
Variance
3.127369986612137
1346.13271185705251342.6666387157807 – 1349.5987849983242112881
226qwen-plus-0125
Model details
Model variant
qwen-plus-0125
Organization
alibaba
Model license
Proprietary
Variance
18.07085831345818
1345.86755355962031337.5357795548991 – 1354.19932756434155819
227minimax-m2
Model details
Model variant
minimax-m2
Organization
minimax
Model license
Apache 2.0
Variance
15.59808274653504
1343.33498933740271335.5942275820846 – 1351.07575109272066856
228claude-3-5-sonnet-20240620
Model details
Model variant
claude-3-5-sonnet-20240620
Organization
anthropic
Model license
Proprietary
Variance
3.087936993992099
1343.31274183798561339.8685898664085 – 1346.756893809562882419
229ling-flash-2.0
Model details
Model variant
ling-flash-2.0
Organization
ant-group
Model license
MIT
Variance
13.794661317753524
1343.27123475948521335.991700200355 – 1350.55076931861556947
230mercury-2
Model details
Model variant
mercury-2
Organization
inception-ai
Model license
Proprietary
Variance
28.833543024578425
1343.0690066242831332.5446126662619 – 1353.59340058230423197
231nvidia-llama-3.3-nemotron-super-49b-v1.5
Model details
Model variant
nvidia-llama-3.3-nemotron-super-49b-v1.5
Organization
nvidia
Model license
Nvidia Open
Variance
26.001018848118143
1342.95979183630671332.9657014224101 – 1352.95388225020323328
232glm-4-plus-0111
Model details
Model variant
glm-4-plus-0111
Organization
zai
Model license
Proprietary
Variance
18.44036439470308
1342.73204414106841334.315518702335 – 1351.14856957980175760
233gemma-3-12b-it
Model details
Model variant
gemma-3-12b-it
Organization
google
Model license
Gemma
Variance
23.5507108222297
1341.76997410135441332.2584502580542 – 1351.28149794465483829
234hunyuan-turbo-0110
Model details
Model variant
hunyuan-turbo-0110
Organization
tencent
Model license
Proprietary
Variance
34.53005941808906
1340.6604579094181329.1432620123817 – 1352.17765380645412290
235granite-4.2-30b
Model details
Model variant
granite-4.2-30b
Organization
ibm
Model license
Apache 2.0
Variance
28.537365807270746
1340.0003747235931329.5301734074906 – 1350.47057603969553401
236gpt-5-nano-high
Model details
Model variant
gpt-5-nano-high
Organization
openai
Model license
Proprietary
Variance
12.461908756156038
1337.70949374505081330.790540839154 – 1344.6284466509488132
237o1-mini
Model details
Model variant
o1-mini
Organization
openai
Model license
Proprietary
Variance
3.4955161685694143
1336.78979868156581333.1253913053822 – 1340.454206057749651981
238gemini-advanced-0514
Model details
Model variant
gemini-advanced-0514
Organization
google
Model license
Proprietary
Variance
6.9138862269862695
1336.00121630295761330.8476341282046 – 1341.154798477710550148
239grok-2-2024-08-13
Model details
Model variant
grok-2-2024-08-13
Organization
xai
Model license
Proprietary
Variance
3.5507289310132517
1335.65173007485031331.9584958591615 – 1339.34496429053963498
240gpt-4o-2024-08-06
Model details
Model variant
gpt-4o-2024-08-06
Organization
openai
Model license
Proprietary
Variance
4.622209104086504
1335.60683509195061331.3930451192557 – 1339.820625064645845499
241qwq-32b
Model details
Model variant
qwq-32b
Organization
alibaba
Model license
Apache 2.0
Variance
5.181503732138864
1335.5757841319211331.1143344553827 – 1340.037233808459425178
242llama-3.1-405b-instruct-bf16
Model details
Model variant
llama-3.1-405b-instruct-bf16
Organization
meta
Model license
Llama 3.1 Community
Variance
3.6246547616112847
1335.49950926106541331.7680267130743 – 1339.230991809056641375
243nova-2-lite
Model details
Model variant
nova-2-lite
Organization
amazon
Model license
Proprietary
Variance
9.628260021951663
1334.78382513875041328.7021671091286 – 1340.86548316837212413
244llama-3.1-405b-instruct-fp8
Model details
Model variant
llama-3.1-405b-instruct-fp8
Organization
meta
Model license
Llama 3.1 Community
Variance
3.3836320846996637
1333.64580260705181330.04051713739 – 1337.251088076713459656
245step-2-16k-exp-202412
Model details
Model variant
step-2-16k-exp-202412
Organization
stepfun
Model license
Proprietary
Variance
19.191602830176585
1333.48109104783021324.8948373842559 – 1342.06734471140434833
246olmo-3.1-32b-instruct
Model details
Model variant
olmo-3.1-32b-instruct
Organization
allenai
Model license
Apache 2.0
Variance
9.817062648957286
1329.21905441507281323.078057598094 – 1335.360051232051511817
247yi-lightning
Model details
Model variant
yi-lightning
Organization
Not reported
Model license
Proprietary
Variance
6.364222582746507
1328.26719946984941323.3227178006193 – 1333.211681139079527332
248llama-3.3-nemotron-49b-super-v1
Model details
Model variant
llama-3.3-nemotron-49b-super-v1
Organization
nvidia
Model license
Nvidia
Variance
38.313652421037624
1327.72138075494651315.5895911900964 – 1339.85317031979642218
249llama-4-maverick-17b-128e-instruct
Model details
Model variant
llama-4-maverick-17b-128e-instruct
Organization
meta
Model license
Llama 4
Variance
4.766189195433558
1326.98230644479991322.7033907496857 – 1331.261222139914339450
250qwen3-30b-a3b
Model details
Model variant
qwen3-30b-a3b
Organization
alibaba
Model license
Apache 2.0
Variance
5.869304508022235
1326.7204384502281321.9721027866842 – 1331.468774113771826157
251hunyuan-large-2025-02-10
Model details
Model variant
hunyuan-large-2025-02-10
Organization
tencent
Model license
Proprietary
Variance
24.628868380126015
1326.32416600045941316.59735852408 – 1336.05097347683893738
252claude-3-5-haiku-20241022
Model details
Model variant
claude-3-5-haiku-20241022
Organization
anthropic
Model license
Proprietary
Variance
2.7705174227808826
1324.77891603257671321.5165811951285 – 1328.04125087002569061
253gpt-4-turbo-2024-04-09
Model details
Model variant
gpt-4-turbo-2024-04-09
Organization
openai
Model license
Proprietary
Variance
4.0139140248779785
1324.52813278231361320.6013929849275 – 1328.454872579699798114
254gemini-1.5-pro-001
Model details
Model variant
gemini-1.5-pro-001
Organization
google
Model license
Proprietary
Variance
4.136207337003033
1324.079918202541320.0938085503917 – 1328.066027854688479138
255deepseek-v2.5-1210
Model details
Model variant
deepseek-v2.5-1210
Organization
deepseek
Model license
DeepSeek
Variance
17.815933760777586
1323.36519840005081315.09240105609 – 1331.63799574401136795
256ring-flash-2.0
Model details
Model variant
ring-flash-2.0
Organization
ant-group
Model license
MIT
Variance
13.77787999646773
1322.56569638379911315.2905909795527 – 1329.84080178804566990
257claude-3-opus-20240229
Model details
Model variant
claude-3-opus-20240229
Organization
anthropic
Model license
Proprietary
Variance
2.459201916583482
1322.28068931885561319.207104621092 – 1325.3542740166195194909
258gpt-4.1-nano-2025-04-14
Model details
Model variant
gpt-4.1-nano-2025-04-14
Organization
openai
Model license
Proprietary
Variance
15.555605639255113
1322.27435278411921314.544138136766 – 1330.00456743147246103
259molmo-2-8b
Model details
Model variant
molmo-2-8b
Organization
allenai
Model license
Apache 2.0
Variance
115.96514497570806
1322.18536374009161301.0790772580974 – 1343.2916502220858822
260llama-4-scout-17b-16e-instruct
Model details
Model variant
llama-4-scout-17b-16e-instruct
Organization
meta
Model license
Llama
Variance
5.842274759986712
1321.5006153839751316.763226028046 – 1326.238004739903829826
261step-1o-turbo-202506
Model details
Model variant
step-1o-turbo-202506
Organization
stepfun
Model license
Proprietary
Variance
12.300890216038452
1319.72705162955121312.8529434530099 – 1326.60115980609238901
262glm-4-plus
Model details
Model variant
glm-4-plus
Organization
zai
Model license
Proprietary
Variance
6.335534870210011
1319.35307800942341314.4197529328667 – 1324.2864030859826126
263qwen-max-0919
Model details
Model variant
qwen-max-0919
Organization
alibaba
Model license
Qwen
Variance
8.466880260449031
1318.11161075137921312.4085263350073 – 1323.814695167750916478
264llama-3.3-70b-instruct
Model details
Model variant
llama-3.3-70b-instruct
Organization
meta
Model license
Llama-3.3
Variance
3.1960444918260653
1318.06544739174961314.561524832038 – 1321.56936995146154497
265gpt-4o-mini-2024-07-18
Model details
Model variant
gpt-4o-mini-2024-07-18
Organization
openai
Model license
Proprietary
Variance
3.279993858795232
1317.57965894927321314.0300165249307 – 1321.129301373615668705
266gemma-3n-e4b-it
Model details
Model variant
gemma-3n-e4b-it
Organization
google
Model license
Gemma
Variance
6.991320812538375
1317.5448994986741312.3625379709893 – 1322.72726102635922137
267gpt-oss-20b
Model details
Model variant
gpt-oss-20b
Organization
openai
Model license
Apache 2.0
Variance
10.711706912631136
1317.42397298200941311.0092570097922 – 1323.838688954226410419
268qwen2.5-plus-1127
Model details
Model variant
qwen2.5-plus-1127
Organization
alibaba
Model license
Proprietary
Variance
10.524450746902334
1314.58670580956961308.2283063132618 – 1320.945105305877610187
269mistral-large-2407
Model details
Model variant
mistral-large-2407
Organization
mistral
Model license
Mistral Research
Variance
4.02869555260196
1314.44644467491621310.512481270608 – 1318.38040807922445459
270athene-v2-chat
Model details
Model variant
athene-v2-chat
Organization
Not reported
Model license
NexusFlow
Variance
5.42947534920657
1314.11692211124861309.549964045758 – 1318.683880176739424739
271nvidia-nemotron-3-nano-30b-a3b-bf16
Model details
Model variant
nvidia-nemotron-3-nano-30b-a3b-bf16
Organization
nvidia
Model license
NVIDIA Open Model
Variance
7.8112632209763
1313.5812237626081308.103391527044 – 1319.05905599817215770
272gpt-4-0125-preview
Model details
Model variant
gpt-4-0125-preview
Organization
openai
Model license
Proprietary
Variance
4.344087554944109
1313.28488919671351309.1998392024286 – 1317.369939190998693439
273gpt-4-1106-preview
Model details
Model variant
gpt-4-1106-preview
Organization
openai
Model license
Proprietary
Variance
3.9384710442198276
1312.95026647510141309.0606039790914 – 1316.8399289711115100105
274hunyuan-standard-2025-02-10
Model details
Model variant
hunyuan-standard-2025-02-10
Organization
tencent
Model license
Proprietary
Variance
24.314269175220808
1311.26747827264561301.6029936101359 – 1320.9319629351553904
275gemini-1.5-flash-002
Model details
Model variant
gemini-1.5-flash-002
Organization
google
Model license
Proprietary
Variance
4.660897578977487
1309.30343915161851305.0720509494897 – 1313.534827353747534902
276grok-2-mini-2024-08-13
Model details
Model variant
grok-2-mini-2024-08-13
Organization
xai
Model license
Proprietary
Variance
3.6291867145298258
1308.38425769958581304.6504431197657 – 1312.118072279405652567
277deepseek-v2.5
Model details
Model variant
deepseek-v2.5
Organization
deepseek
Model license
DeepSeek
Variance
5.782663210099713
1307.17589394122271302.462735489023 – 1311.889052393422424572
278athene-70b-0725
Model details
Model variant
athene-70b-0725
Organization
Not reported
Model license
CC-BY-NC-4.0
Variance
8.382857248328653
1306.65578942428241300.9810734913733 – 1312.330505357191419621
279olmo-3-32b-think
Model details
Model variant
olmo-3-32b-think
Organization
allenai
Model license
Apache 2.0
Variance
17.694138043926497
1306.07805886065351297.8335878246548 – 1314.3225298966525831
280mistral-large-2411
Model details
Model variant
mistral-large-2411
Organization
mistral
Model license
MRL
Variance
5.169548223842913
1305.57458264435171301.118282988417 – 1310.030882300286528073
281mercury
Model details
Model variant
mercury
Organization
inception-ai
Model license
Proprietary
Variance
49.417555115801584
1305.37245231754741291.5943717909743 – 1319.15053284412061965
282magistral-medium-2506
Model details
Model variant
magistral-medium-2506
Organization
mistral
Model license
Proprietary
Variance
10.827873801570432
1304.92494268446831298.4755371828421 – 1311.374348186094511510
283granite-4.1-8b
Model details
Model variant
granite-4.1-8b
Organization
ibm
Model license
Apache 2.0
Variance
26.0454234107106
1304.16778216494961294.1651614333718 – 1314.17040289652734180
284gemma-3-4b-it
Model details
Model variant
gemma-3-4b-it
Organization
google
Model license
Gemma
Variance
22.597442273564212
1303.2621184411581293.945083293274 – 1312.57915358904234171
285qwen2.5-72b-instruct
Model details
Model variant
qwen2.5-72b-instruct
Organization
alibaba
Model license
Qwen
Variance
4.350827159791106
1302.85383231531661298.7656146877564 – 1306.94204994287739406
286mistral-small-3.1-24b-instruct-2503
Model details
Model variant
mistral-small-3.1-24b-instruct-2503
Organization
mistral
Model license
Apache 2.0
Variance
5.374740324468048
1302.71437007384271298.1704902747756 – 1307.258249872909632727
287llama-3.1-nemotron-70b-instruct
Model details
Model variant
llama-3.1-nemotron-70b-instruct
Organization
nvidia
Model license
Llama 3.1
Variance
15.683994805306654
1298.7204852735771290.9584352744746 – 1306.48253527267967140
288hunyuan-large-vision
Model details
Model variant
hunyuan-large-vision
Organization
tencent
Model license
Proprietary
Variance
21.790830196720922
1293.77422822648531284.624989084926 – 1302.92346736804485279
289llama-3.1-70b-instruct
Model details
Model variant
llama-3.1-70b-instruct
Organization
meta
Model license
Llama 3.1 Community
Variance
3.656022167207621
1293.37622606944271289.6286323610916 – 1297.123819777793955240
290granite-4.2-8b
Model details
Model variant
granite-4.2-8b
Organization
ibm
Model license
Apache 2.0
Variance
32.49432316741007
1290.17619264418071279.0036546892693 – 1301.34873059909183254
291amazon-nova-pro-v1.0
Model details
Model variant
amazon-nova-pro-v1.0
Organization
amazon
Model license
Proprietary
Variance
5.477486332944168
1290.09713989475971285.5100342507922 – 1294.684245538727524745
292granite-4.2-3b
Model details
Model variant
granite-4.2-3b
Organization
ibm
Model license
Apache 2.0
Variance
35.02726881260006
1289.6494481147491278.0496286874911 – 1301.24926754200673251
293gemma-2-27b-it
Model details
Model variant
gemma-2-27b-it
Organization
google
Model license
Gemma license
Variance
3.0034007648789367
1289.51415606611431286.1174752803583 – 1292.910836851870375754
294jamba-1.5-large
Model details
Model variant
jamba-1.5-large
Organization
Not reported
Model license
Jamba Open
Variance
13.889046447815076
1289.47869531674361282.1742993808712 – 1296.7830912526168662
295reka-core-20240904
Model details
Model variant
reka-core-20240904
Organization
Not reported
Model license
Proprietary
Variance
13.422613476445573
1288.0642440405491280.883546516223 – 1295.24494156487487312
296gpt-4-0314
Model details
Model variant
gpt-4-0314
Organization
openai
Model license
Proprietary
Variance
5.884008871690951
1287.95156999417331283.1972900506698 – 1292.70584993767754173
297ibm-granite-h-small
Model details
Model variant
ibm-granite-h-small
Organization
ibm
Model license
Apache 2.0
Variance
18.36747967168066
1287.47421077861711279.07433477961 – 1295.87408677762445630
298llama-3.1-nemotron-51b-instruct
Model details
Model variant
llama-3.1-nemotron-51b-instruct
Organization
nvidia
Model license
Llama 3.1
Variance
25.84765496239177
1286.70613433682071276.7415619852575 – 1296.6707066883843749
299olmo-3.1-32b-think
Model details
Model variant
olmo-3.1-32b-think
Organization
allenai
Model license
Apache 2.0
Variance
13.727264394926719
1286.65782559342191279.3960957104057 – 1293.9195554764388301
300gemini-1.5-flash-001
Model details
Model variant
gemini-1.5-flash-001
Organization
google
Model license
Proprietary
Variance
5.274677051575625
1286.55738068083041282.0559970395389 – 1291.05876432212262833
301llama-3.1-tulu-3-70b
Model details
Model variant
llama-3.1-tulu-3-70b
Organization
allenai
Model license
Llama 3.1
Variance
28.46681426221456
1286.13427710678141275.6770262852392 – 1296.59152792832362846
302claude-3-sonnet-20240229
Model details
Model variant
claude-3-sonnet-20240229
Organization
anthropic
Model license
Proprietary
Variance
4.126038922322187
1281.4494128680661277.46820593892 – 1285.4306197972123109284
303gemma-2-9b-it-simpo
Model details
Model variant
gemma-2-9b-it-simpo
Organization
Not reported
Model license
MIT
Variance
12.237155550395489
1280.40965415833031273.5533775354634 – 1287.265930781197310072
304nemotron-4-340b-instruct
Model details
Model variant
nemotron-4-340b-instruct
Organization
nvidia
Model license
NVIDIA Open Model
Variance
7.358852577758633
1277.25036797910231271.9335334749053 – 1282.56720248329919659
305llama-3-70b-instruct
Model details
Model variant
llama-3-70b-instruct
Organization
meta
Model license
Llama 3 Community
Variance
3.344422882067935
1276.63809764172881273.0537618900935 – 1280.222433393364156876
306command-r-plus-08-2024
Model details
Model variant
command-r-plus-08-2024
Organization
cohere
Model license
CC-BY-NC-4.0
Variance
11.263167097779387
1276.38191069461821269.804145679302 – 1282.95967570993439866
307gpt-4-0613
Model details
Model variant
gpt-4-0613
Organization
openai
Model license
Proprietary
Variance
4.269213330288
1276.34464633115361272.294954095309 – 1280.394338566998288723
308mistral-small-24b-instruct-2501
Model details
Model variant
mistral-small-24b-instruct-2501
Organization
mistral
Model license
Apache 2.0
Variance
9.128242241375535
1274.40083857071021268.4792030976703 – 1280.322474043750214681
309glm-4-0520
Model details
Model variant
glm-4-0520
Organization
zai
Model license
Proprietary
Variance
12.682469937866994
1273.47931546746211266.499402429966 – 1280.4592285049589788
310reka-flash-20240904
Model details
Model variant
reka-flash-20240904
Organization
Not reported
Model license
Proprietary
Variance
12.747611226687226
1272.4910652558831265.4932496260212 – 1279.48888088574477536
311qwen2.5-coder-32b-instruct
Model details
Model variant
qwen2.5-coder-32b-instruct
Organization
alibaba
Model license
Apache 2.0
Variance
17.19816502663825
1270.6307871130441262.5026850749707 – 1278.75888915111755432
312c4ai-aya-expanse-32b
Model details
Model variant
c4ai-aya-expanse-32b
Organization
cohere
Model license
CC-BY-NC-4.0
Variance
6.250764756678548
1267.2969025465971262.3966928153072 – 1272.197112277886827124
313gemma-2-9b-it
Model details
Model variant
gemma-2-9b-it
Organization
google
Model license
Gemma license
Variance
3.8221935889095735
1267.04161003453711263.2097959372045 – 1270.873424131869854611
314deepseek-coder-v2
Model details
Model variant
deepseek-coder-v2
Organization
deepseek
Model license
DeepSeek License
Variance
10.240256473096139
1265.44995839767171259.1779951041929 – 1271.721921691150315147
315qwen2-72b-instruct
Model details
Model variant
qwen2-72b-instruct
Organization
alibaba
Model license
Qianwen LICENSE
Variance
6.369663137657024
1261.91496779126561256.9683731398916 – 1266.861562442639837325
316command-r-plus
Model details
Model variant
command-r-plus
Organization
cohere
Model license
CC-BY-NC-4.0
Variance
4.848693049079693
1261.8794493781411257.563658062261 – 1266.195240694021377554
317claude-3-haiku-20240307
Model details
Model variant
claude-3-haiku-20240307
Organization
anthropic
Model license
Proprietary
Variance
3.6792074052391195
1261.76888396163121258.0094260565577 – 1265.5283418667045117701
318amazon-nova-lite-v1.0
Model details
Model variant
amazon-nova-lite-v1.0
Organization
amazon
Model license
Proprietary
Variance
7.020047219176645
1260.4434793576421255.2504819272754 – 1265.636476788008619372
319gemini-1.5-flash-8b-001
Model details
Model variant
gemini-1.5-flash-8b-001
Organization
google
Model license
Proprietary
Variance
4.832776128037473
1258.831038277521254.5223365605884 – 1263.139739994451735558
320phi-4
Model details
Model variant
phi-4
Organization
microsoft
Model license
MIT
Variance
5.534529755665279
1256.31069772864611251.6997685220442 – 1260.92162693524824126
321olmo-2-0325-32b-instruct
Model details
Model variant
olmo-2-0325-32b-instruct
Organization
allenai
Model license
Apache-2.0
Variance
30.22250442868419
1251.70734594063041240.9324442602885 – 1262.48224762097243334
322command-r-08-2024
Model details
Model variant
command-r-08-2024
Organization
cohere
Model license
CC-BY-NC-4.0
Variance
11.34775808356821
1250.5265234124321243.924103751033 – 1257.12894307383110140
323mistral-large-2402
Model details
Model variant
mistral-large-2402
Organization
mistral
Model license
Proprietary
Variance
5.771934121842871
1242.66278698608271237.9540029344598 – 1247.371571037705762436
324amazon-nova-micro-v1.0
Model details
Model variant
amazon-nova-micro-v1.0
Organization
amazon
Model license
Proprietary
Variance
6.983641092001364
1240.7227996030621235.5432851785786 – 1245.902314027545319364
325jamba-1.5-mini
Model details
Model variant
jamba-1.5-mini
Organization
Not reported
Model license
Jamba Open
Variance
13.587235675494073
1239.81188341298551232.5872861000223 – 1247.03648072594898858
326ministral-8b-2410
Model details
Model variant
ministral-8b-2410
Organization
mistral
Model license
MRL
Variance
21.49508249452475
1237.6288321481781228.541892385522 – 1246.7157719108344781
327gemini-pro-dev-api
Model details
Model variant
gemini-pro-dev-api
Organization
google
Model license
Proprietary
Variance
13.901910423635858
1236.93210783387621229.6243300306467 – 1244.239885637105818354
328qwen1.5-110b-chat
Model details
Model variant
qwen1.5-110b-chat
Organization
alibaba
Model license
Qianwen LICENSE
Variance
8.000304441585984
1234.2702277133461228.726506935261 – 1239.813948491430726195
329reka-flash-21b-20240226-online
Model details
Model variant
reka-flash-21b-20240226-online
Organization
Not reported
Model license
Proprietary
Variance
14.21655329733944
1233.66643124312371226.2764174363754 – 1241.05644504987215450
330qwen1.5-72b-chat
Model details
Model variant
qwen1.5-72b-chat
Organization
alibaba
Model license
Qianwen LICENSE
Variance
7.213503745890621
1233.64286864657631228.3788039060205 – 1238.906933387131939302
331hunyuan-standard-256k
Model details
Model variant
hunyuan-standard-256k
Organization
tencent
Model license
Proprietary
Variance
35.782729523500386
1233.18235880223961221.4581154596372 – 1244.90660214484232728
332mixtral-8x22b-instruct-v0.1
Model details
Model variant
mixtral-8x22b-instruct-v0.1
Organization
mistral
Model license
Apache 2.0
Variance
5.395342720438663
1229.71024536953061225.1576651248674 – 1234.262825614193651416
333command-r
Model details
Model variant
command-r
Organization
cohere
Model license
CC-BY-NC-4.0
Variance
5.932904452369178
1226.99197750329061222.2179846104505 – 1231.765970396130854036
334reka-flash-21b-20240226
Model details
Model variant
reka-flash-21b-20240226
Organization
Not reported
Model license
Proprietary
Variance
9.171067010383956
1226.9211544873241220.9856447145903 – 1232.856664260057424806
335gpt-3.5-turbo-0125
Model details
Model variant
gpt-3.5-turbo-0125
Organization
openai
Model license
Proprietary
Variance
5.725176257250318
1225.70694210762921221.0172695355361 – 1230.396614679722566207
336gemini-pro
Model details
Model variant
gemini-pro
Organization
google
Model license
Proprietary
Variance
35.752139139259334
1223.72302199425621212.003791206564 – 1235.44225278194846390
337llama-3-8b-instruct
Model details
Model variant
llama-3-8b-instruct
Organization
meta
Model license
Llama 3 Community
Variance
3.6306334970118743
1223.71862196141961219.9840632094645 – 1227.4531807133744104642
338c4ai-aya-expanse-8b
Model details
Model variant
c4ai-aya-expanse-8b
Organization
cohere
Model license
CC-BY-NC-4.0
Variance
12.683914941987634
1223.10055451933541216.1202438575647 – 1230.08086518110649818
339mistral-medium
Model details
Model variant
mistral-medium
Organization
mistral
Model license
Proprietary
Variance
7.818000414215666
1222.82879227711211217.3485982430127 – 1228.308986311211634550
340llama-3.1-tulu-3-8b
Model details
Model variant
llama-3.1-tulu-3-8b
Organization
allenai
Model license
Llama 3.1
Variance
29.638374463418046
1220.51844720094251209.8481803339173 – 1231.18871406796762896
341zephyr-orpo-141b-A35b-v0.1
Model details
Model variant
zephyr-orpo-141b-A35b-v0.1
Organization
Not reported
Model license
Apache 2.0
Variance
30.19961425037058
1213.13950796744141202.368687453495 – 1223.91032848138784652
342yi-1.5-34b-chat
Model details
Model variant
yi-1.5-34b-chat
Organization
Not reported
Model license
Apache-2.0
Variance
6.592471750926602
1212.9148497216441207.882483602434 – 1217.947215840854124146
343llama-3.1-8b-instruct
Model details
Model variant
llama-3.1-8b-instruct
Organization
meta
Model license
Llama 3.1 Community
Variance
4.508799270603172
1211.22998562269071207.0682111539336 – 1215.391760091447649605
344granite-3.1-8b-instruct
Model details
Model variant
granite-3.1-8b-instruct
Organization
ibm
Model license
Apache 2.0
Variance
32.01766821733427
1208.6221460260091197.5318550473405 – 1219.71243700467773090
345gpt-3.5-turbo-1106
Model details
Model variant
gpt-3.5-turbo-1106
Organization
openai
Model license
Proprietary
Variance
19.789668612218993
1204.3643400596461195.6453265231833 – 1213.08335359610916619
346qwen1.5-32b-chat
Model details
Model variant
qwen1.5-32b-chat
Organization
alibaba
Model license
Qianwen LICENSE
Variance
9.71021224495237
1204.11036774716721198.0028821369358 – 1210.217853357398621741
347gemma-2-2b-it
Model details
Model variant
gemma-2-2b-it
Organization
google
Model license
Gemma license
Variance
4.387708444908676
1200.1075779850561196.0020693310244 – 1204.213086639087646616
348phi-3-medium-4k-instruct
Model details
Model variant
phi-3-medium-4k-instruct
Organization
microsoft
Model license
MIT
Variance
6.924057333702734
1198.01658632520161192.859214793157 – 1203.17395785724625055
349mixtral-8x7b-instruct-v0.1
Model details
Model variant
mixtral-8x7b-instruct-v0.1
Organization
mistral
Model license
Apache 2.0
Variance
4.717716018798278
1197.28368608254351193.026584743141 – 1201.54078742194673503
350dbrx-instruct-preview
Model details
Model variant
dbrx-instruct-preview
Organization
Not reported
Model license
DBRX LICENSE
Variance
9.697304205791953
1195.6446940403721189.5412692003094 – 1201.748118880434732191
351qwen1.5-14b-chat
Model details
Model variant
qwen1.5-14b-chat
Organization
alibaba
Model license
Qianwen LICENSE
Variance
13.139084036912465
1191.19104938677671184.0865965387777 – 1198.295502234775517839
352internlm2_5-20b-chat
Model details
Model variant
internlm2_5-20b-chat
Organization
Not reported
Model license
Other
Variance
13.4295444722087
1190.81179476462281183.6292435416472 – 1197.99434598759859901
353deepseek-llm-67b-chat
Model details
Model variant
deepseek-llm-67b-chat
Organization
deepseek
Model license
DeepSeek License
Variance
34.177480111276616
1185.06493454089381173.6066893679817 – 1196.52317971380584932
354wizardlm-70b
Model details
Model variant
wizardlm-70b
Organization
microsoft
Model license
Llama 2 Community
Variance
23.079206659944315
1184.8613743539481175.4455460845672 – 1194.27720262332838214
355yi-34b-chat
Model details
Model variant
yi-34b-chat
Organization
Not reported
Model license
Yi License
Variance
12.09196652346064
1183.82974390556461177.0142621572884 – 1190.645225653840715483
356granite-3.0-8b-instruct
Model details
Model variant
granite-3.0-8b-instruct
Organization
ibm
Model license
Apache 2.0
Variance
19.5707628484502
1183.2600941202191174.5894378836997 – 1191.93075035673846638
357openchat-3.5
Model details
Model variant
openchat-3.5
Organization
Not reported
Model license
Apache-2.0
Variance
24.17975445618906
1183.17231372240281173.534599727998 – 1192.81002771680767968
358openchat-3.5-0106
Model details
Model variant
openchat-3.5-0106
Organization
Not reported
Model license
Apache-2.0
Variance
16.5695467030232
1182.86741178369581174.8892396034762 – 1190.845583963915512637
359gemma-1.1-7b-it
Model details
Model variant
gemma-1.1-7b-it
Organization
google
Model license
Gemma license
Variance
9.566338554791846
1182.63903778666281176.576967544324 – 1188.701108029001723893
360snowflake-arctic-instruct
Model details
Model variant
snowflake-arctic-instruct
Organization
Not reported
Model license
Apache 2.0
Variance
9.06510402260787
1180.17504857191531174.2739280166177 – 1186.07616912721332832
361granite-3.1-2b-instruct
Model details
Model variant
granite-3.1-2b-instruct
Organization
ibm
Model license
Apache 2.0
Variance
32.52390748567455
1178.96623142100251167.788608628374 – 1190.1438542136313188
362tulu-2-dpo-70b
Model details
Model variant
tulu-2-dpo-70b
Organization
Not reported
Model license
AI2 ImpACT Low-risk
Variance
24.92946626476706
1177.77927279383131167.9932869938218 – 1187.56525859384086535
363openhermes-2.5-mistral-7b
Model details
Model variant
openhermes-2.5-mistral-7b
Organization
Not reported
Model license
Apache-2.0
Variance
28.06207321783309
1176.08307165331761165.7004275445363 – 1186.46571576209895006
364vicuna-33b
Model details
Model variant
vicuna-33b
Organization
Not reported
Model license
Non-commercial
Variance
9.94967194031669
1173.04705261884371166.8647185096142 – 1179.229386728073222479
365phi-3-small-8k-instruct
Model details
Model variant
phi-3-small-8k-instruct
Organization
microsoft
Model license
MIT
Variance
9.085612025774486
1171.18218455286681165.27439271007 – 1177.089976395663617766
366starling-lm-7b-beta
Model details
Model variant
starling-lm-7b-beta
Organization
Not reported
Model license
Apache-2.0
Variance
14.21836839987152
1171.06760149718251163.6771159444218 – 1178.458087049943316056
367llama-2-70b-chat
Model details
Model variant
llama-2-70b-chat
Organization
meta
Model license
Llama 2 Community
Variance
7.821060345026512
1170.74445670186651165.2631903108231 – 1176.225723092910138492
368starling-lm-7b-alpha
Model details
Model variant
starling-lm-7b-alpha
Organization
Not reported
Model license
CC-BY-NC-4.0
Variance
16.85858728171387
1167.52259817712341159.4751408881543 – 1175.570055466092510224
369llama-3.2-3b-instruct
Model details
Model variant
llama-3.2-3b-instruct
Organization
meta
Model license
Llama 3.2
Variance
15.44019230047495
1166.86510831521171159.1636238540268 – 1174.56659277639667936
370nous-hermes-2-mixtral-8x7b-dpo
Model details
Model variant
nous-hermes-2-mixtral-8x7b-dpo
Organization
Not reported
Model license
Apache-2.0
Variance
36.78185210548088
1164.50162565675851152.6148275087262 – 1176.3884238047913777
371granite-3.0-2b-instruct
Model details
Model variant
granite-3.0-2b-instruct
Organization
ibm
Model license
Apache 2.0
Variance
18.275147019882436
1156.77263032108321148.3938938579277 – 1165.15136678423856837
372llama2-70b-steerlm-chat
Model details
Model variant
llama2-70b-steerlm-chat
Organization
nvidia
Model license
Llama 2 Community
Variance
41.123832610740564
1154.82016064057171142.2513297672056 – 1167.38899151393753585
373qwq-32b-preview
Model details
Model variant
qwq-32b-preview
Organization
alibaba
Model license
Apache 2.0
Variance
34.273721634199
1154.27083061445891142.7964639526465 – 1165.7451972762713231
374solar-10.7b-instruct-v1.0
Model details
Model variant
solar-10.7b-instruct-v1.0
Organization
Not reported
Model license
CC-BY-NC-4.0
Variance
44.88241578891134
1152.54760414669571139.4169548091202 – 1165.67825348427144155
375dolphin-2.2.1-mistral-7b
Model details
Model variant
dolphin-2.2.1-mistral-7b
Organization
Not reported
Model license
Apache-2.0
Variance
60.73165022513074
1152.39425012031321137.120150033806 – 1167.66835020682041679
376mpt-30b-chat
Model details
Model variant
mpt-30b-chat
Organization
Not reported
Model license
CC-BY-NC-SA-4.0
Variance
38.75804629876402
1150.87996748244361138.6780234231037 – 1163.08191154178352572
377wizardlm-13b
Model details
Model variant
wizardlm-13b
Organization
microsoft
Model license
Llama 2 Community
Variance
21.991326907358104
1149.644597604921140.453363915853 – 1158.8358312939877044
378mistral-7b-instruct-v0.2
Model details
Model variant
mistral-7b-instruct-v0.2
Organization
mistral
Model license
Apache-2.0
Variance
11.470292908623792
1149.50469772544351142.8667268103386 – 1156.142668640548419402
379falcon-180b-chat
Model details
Model variant
falcon-180b-chat
Organization
Not reported
Model license
Falcon-180B TII License
Variance
75.24790226548367
1148.2543606528341131.2525455174882 – 1165.256175788181295
380qwen1.5-7b-chat
Model details
Model variant
qwen1.5-7b-chat
Organization
alibaba
Model license
Qianwen LICENSE
Variance
25.36785051447037
1143.95133111815651134.0796770966228 – 1153.82298513969024737
381phi-3-mini-4k-instruct-june-2024
Model details
Model variant
phi-3-mini-4k-instruct-june-2024
Organization
microsoft
Model license
MIT
Variance
10.77996790742424
1143.22471150554321136.7895889111574 – 1149.65983409992912297
382vicuna-13b
Model details
Model variant
vicuna-13b
Organization
Not reported
Model license
Llama 2 Community
Variance
11.60607359006862
1141.69397048846441135.0168263559633 – 1148.371114620965519367
383llama-2-13b-chat
Model details
Model variant
llama-2-13b-chat
Organization
meta
Model license
Llama 2 Community
Variance
11.715518583169066
1141.5244982364741134.8159453224455 – 1148.233051150502719174
384qwen-14b-chat
Model details
Model variant
qwen-14b-chat
Organization
alibaba
Model license
Qianwen LICENSE
Variance
31.019427774255504
1139.48586699466321128.5698304228895 – 1150.40190356643674964
385palm-2
Model details
Model variant
palm-2
Organization
google
Model license
Proprietary
Variance
22.675895131326467
1139.30684339157551129.973649009727 – 1148.64003777342428554
386gemma-7b-it
Model details
Model variant
gemma-7b-it
Organization
google
Model license
Gemma license
Variance
23.32477766875883
1137.7933036568761128.3275140481649 – 1147.25909326558718925
387codellama-34b-instruct
Model details
Model variant
codellama-34b-instruct
Organization
meta
Model license
Llama 2 Community
Variance
20.473672019869785
1136.97997939609921128.111565334232 – 1145.84839345796677366
388zephyr-7b-beta
Model details
Model variant
zephyr-7b-beta
Organization
Not reported
Model license
MIT
Variance
20.189138471083005
1130.92344200225561122.1168680905714 – 1139.730015913939711118
389phi-3-mini-128k-instruct
Model details
Model variant
phi-3-mini-128k-instruct
Organization
microsoft
Model license
MIT
Variance
14.299495699442282
1129.95482370357061122.5432837902933 – 1137.366363616847620685
390phi-3-mini-4k-instruct
Model details
Model variant
phi-3-mini-4k-instruct
Organization
microsoft
Model license
MIT
Variance
10.62431211704425
1128.20447198706351121.8159778377487 – 1134.59296613637820118
391guanaco-33b
Model details
Model variant
guanaco-33b
Organization
Not reported
Model license
Non-commercial
Variance
37.784147122399375
1127.61541703906691115.5677514873616 – 1139.6630825907722921
392zephyr-7b-alpha
Model details
Model variant
zephyr-7b-alpha
Organization
Not reported
Model license
MIT
Variance
62.896790366953375
1127.05548935335381111.5115056249629 – 1142.59947308174471785
393stripedhyena-nous-7b
Model details
Model variant
stripedhyena-nous-7b
Organization
Not reported
Model license
Apache 2.0
Variance
31.222577440975346
1121.7376039180811110.7858805141852 – 1132.68932732197695182
394codellama-70b-instruct
Model details
Model variant
codellama-70b-instruct
Organization
meta
Model license
Llama 2 Community
Variance
85.08862070168838
1119.26654767169751101.1871551892275 – 1137.34594015416771143
395gemma-1.1-2b-it
Model details
Model variant
gemma-1.1-2b-it
Organization
google
Model license
Gemma license
Variance
15.498332341524742
1116.74639209749531109.0304212914723 – 1124.462362903518410854
396vicuna-7b
Model details
Model variant
vicuna-7b
Organization
Not reported
Model license
Llama 2 Community
Variance
21.55598947299021
1115.43512750192441106.3353227842501 – 1124.53493221959896923
397smollm2-1.7b-instruct
Model details
Model variant
smollm2-1.7b-instruct
Organization
Not reported
Model license
Apache 2.0
Variance
53.50250781476447
1114.81156803464321100.475331409424 – 1129.14780465986272199
398llama-3.2-1b-instruct
Model details
Model variant
llama-3.2-1b-instruct
Organization
meta
Model license
Llama 3.2
Variance
16.157448068105566
1111.19327345004651103.3149378770254 – 1119.07160902306788045
399mistral-7b-instruct
Model details
Model variant
mistral-7b-instruct
Organization
mistral
Model license
Apache 2.0
Variance
22.318893576895416
1110.48790691888641101.2284733185468 – 1119.74734051922598977
400llama-2-7b-chat
Model details
Model variant
llama-2-7b-chat
Organization
meta
Model license
Llama 2 Community
Variance
12.887399407021004
1108.02828379396281100.9922043367717 – 1115.064363251154214148
401gemma-2b-it
Model details
Model variant
gemma-2b-it
Organization
google
Model license
Gemma license
Variance
34.15005941026576
1093.73070716178181082.2770594044603 – 1105.1843549191034780
402qwen1.5-4b-chat
Model details
Model variant
qwen1.5-4b-chat
Organization
alibaba
Model license
Qianwen LICENSE
Variance
22.58238636499155
1091.26699228342751081.9530614648033 – 1100.58092310205197597
403olmo-7b-instruct
Model details
Model variant
olmo-7b-instruct
Organization
allenai
Model license
Apache-2.0
Variance
32.242050332317355
1073.71887183250061062.589787923825 – 1084.84795574117636328
404koala-13b
Model details
Model variant
koala-13b
Organization
Not reported
Model license
Non-commercial
Variance
25.07340421265077
1071.04968307383661061.2354867349857 – 1080.86387941268786965
405alpaca-13b
Model details
Model variant
alpaca-13b
Organization
Not reported
Model license
Non-commercial
Variance
33.74596913041982
1070.36792988332151058.9822480513483 – 1081.75361171529455745
406gpt4all-13b-snoozy
Model details
Model variant
gpt4all-13b-snoozy
Organization
Not reported
Model license
Non-commercial
Variance
59.627564913884484
1067.8371080859241052.7024843643064 – 1082.97173180754181743
407mpt-7b-chat
Model details
Model variant
mpt-7b-chat
Organization
Not reported
Model license
CC-BY-NC-SA-4.0
Variance
36.895378037812925
1063.57544072210341051.6703126082946 – 1075.48056883591223924
408chatglm3-6b
Model details
Model variant
chatglm3-6b
Organization
Not reported
Model license
Apache-2.0
Variance
35.202232971468234
1056.69262339862331045.0638690218045 – 1068.32137777544184658
409RWKV-4-Raven-14B
Model details
Model variant
RWKV-4-Raven-14B
Organization
Not reported
Model license
Apache 2.0
Variance
33.34358529664022
1042.46045343699351031.142856083697 – 1053.778050790294845
410chatglm2-6b
Model details
Model variant
chatglm2-6b
Organization
Not reported
Model license
Apache-2.0
Variance
47.68293057097084
1024.89389869652881011.3597931022016 – 1038.4280042908562658
411oasst-pythia-12b
Model details
Model variant
oasst-pythia-12b
Organization
Not reported
Model license
Apache 2.0
Variance
30.337506933715467
1023.65482119948341012.8594386861869 – 1034.450203712786310
412chatglm-6b
Model details
Model variant
chatglm-6b
Organization
Not reported
Model license
Non-commercial
Variance
40.6157703177141
995.9417400733207983.4507909842296 – 1008.43268916241214914
413fastchat-t5-3b
Model details
Model variant
fastchat-t5-3b
Organization
Not reported
Model license
Apache 2.0
Variance
39.33889117454815
992.6838579422479980.3908220886115 – 1004.97689379588454203
414dolly-v2-12b
Model details
Model variant
dolly-v2-12b
Organization
Not reported
Model license
MIT
Variance
46.946476196221894
982.6233095251253969.1941265609801 – 996.05249248927023412
415llama-13b
Model details
Model variant
llama-13b
Organization
meta
Model license
Non-commercial
Variance
63.885658937051254
975.3067896859363959.6410905939842 – 990.97248877788842391
416stablelm-tuned-alpha-7b
Model details
Model variant
stablelm-tuned-alpha-7b
Organization
Not reported
Model license
CC-BY-NC-SA-4.0
Variance
41.48189490523768
953.3231557218382940.699725479514 – 965.94658596416283287
Methodology · Arena (LMArena)
Source category
overall
Configuration
text_style_control · latest
Metric
Arena score (Bradley–Terry) · higher · styleControlled=true
Source checked
Source
8b599a3c759427b568b742e7ceeca9a516933e25
Data license
CC-BY-4.0
Attribution
Arena (LMArena), Arena Leaderboard Dataset. Selected and normalized by AISubHub; original ranks and scores retained.

Observed a contiguous prefix of the source up to the next category boundary. The complete source data was not retrieved.

Source rows read
3900
Reported source rows
11033
Category rows included
416
Next source category
chinese · row_idx 416