Rankings globais de modelos de IA
Compare separadamente o desempenho em tarefas, as preferências de texto e os agentes de programação. Cada fonte mede resultados diferentes.
Desempenho em tarefas variadas
Para modelos como Claude Opus 5.5 ou GPT-6 Astra, comece por avaliações que combinam vários tipos de tarefas. Confira a versão exata e as configurações do teste.
LiveBench 2.0
O LiveBench 2.0 reúne sete grupos de tarefas, de perguntas curtas de raciocínio a trabalhos mais longos com ferramentas.
Sete grupos de tarefas
- Trabalho com agentes
- Raciocínio
- Programação
- Uso do navegador
- Análise de dados
- Pesquisa
- Design
Os resultados dependem do modelo, esforço de raciocínio e ferramentas testados. Descrevem esse protocolo, não todos os idiomas ou trabalhos reais.
O AISubHub ainda não incorporou a tabela completa do LiveBench. Consulte as notas atuais e o método no site oficial.
Agentes de programação · SWE-bench
Resultados oficiais · site externoOs resultados de correção de software podem avaliar o modelo junto com seu agente e ferramentas. Compare o mesmo ambiente, orçamento e conjunto de dados.
Verified e Pro são avaliações distintas. Confira o modelo exato, agente ou ambiente de execução, versão dos dados e orçamento antes de comparar.
Estes links abrem resultados oficiais. O AISubHub ainda não incorporou uma tabela completa do SWE-bench.
Preferências de texto · Arena com controle de estilo
Text
Esta configuração do Arena mede preferências sobre respostas de texto com controles de estilo. As posições dos modelos podem variar entre dimensões de avaliação.
Retrato parcial: as linhas exibidas não representam todo o ranking.
Métrica: Arena score (Bradley–Terry)
Role horizontalmente para ver todos os campos.
| Posição na fonte | Modelo | Métrica | Intervalo de confiança | Votos |
|---|---|---|---|---|
| 1 | Gemini 4 Argon (High)Detalhes do modelo
| 1523.9035861299108 | 1515.0853098239602 – 1532.721862435861 | 4904 |
| 2 | Muse Wonder (Max)Detalhes do modelo
| 1508.8795055977137 | 1498.3089865891718 – 1519.4500246062555 | 3247 |
| 3 | Claude Opus 5.5 (High)Detalhes do modelo
| 1508.1664796431178 | 1500.8355453341774 – 1515.497413952058 | 8300 |
| 4 | Claude Fable 5 (High)Detalhes do modelo
| 1503.6013443401307 | 1499.3137424347174 – 1507.888946245544 | 42004 |
| 5 | Claude Opus 4.6 (High)Detalhes do modelo
| 1503.0532375944142 | 1499.711775283552 – 1506.3946999052766 | 81394 |
| 6 | Claude Fable 5.1 (Max)Detalhes do modelo
| 1502.2862278899863 | 1496.239481927182 – 1508.3329738527907 | 14590 |
| 7 | Claude Opus 4.7 (High)Detalhes do modelo
| 1501.0578036294407 | 1497.2977827395944 – 1504.8178245192871 | 65116 |
| 8 | Claude Opus 4.6Detalhes do modelo
| 1497.209105729648 | 1493.9537105713546 – 1500.4645008879415 | 86071 |
| 9 | Gemini 3.8 Flash (High)Detalhes do modelo
| 1496.3802615912373 | 1491.7511847575463 – 1501.0093384249283 | 37454 |
| 10 | Muse Spark 1.3 (Max)Detalhes do modelo
| 1494.412724849286 | 1488.8158760267218 – 1500.0095736718504 | 17561 |
| 11 | Claude Opus 4.7Detalhes do modelo
| 1493.5865745597428 | 1489.8257265063335 – 1497.3474226131518 | 66216 |
| 12 | Muse Spark 1.2 (xHigh)Detalhes do modelo
| 1493.0608667270417 | 1485.8976160964726 – 1500.224117357611 | 8248 |
| 13 | Muse Spark 1.1Detalhes do modelo
| 1490.1758377985552 | 1485.9299522977522 – 1494.4217232993585 | 42810 |
| 14 | Claude Opus 5 (Max)Detalhes do modelo
| 1489.9918464257669 | 1485.162055514534 – 1494.821637337 | 32495 |
| 15 | Claude Opus 5 (High)Detalhes do modelo
| 1489.905197282939 | 1486.2352631115743 – 1493.5751314543038 | 66824 |
| 16 | Muse SparkDetalhes do modelo
| 1489.0413932749987 | 1483.3120303674639 – 1494.7707561825337 | 14150 |
| 17 | Gemini 3.7 Flash (High)Detalhes do modelo
| 1487.5878753892953 | 1482.7056648473051 – 1492.4700859312854 | 27232 |
| 18 | Kimi K3 (Max)Detalhes do modelo
| 1487.071983223727 | 1482.4881210528476 – 1491.6558453946066 | 32795 |
| 19 | Gemini 3.1 Pro PreviewDetalhes do modelo
| 1486.9094358879568 | 1483.9491002818586 – 1489.869771494055 | 127649 |
| 20 | Gemini 3 ProDetalhes do modelo
| 1485.4590679512698 | 1481.6684829768922 – 1489.2496529256475 | 42072 |
| 21 | gpt-5.6-sol-xhighDetalhes do modelo
| 1484.7394950911005 | 1480.4011455154182 – 1489.077844666783 | 40442 |
| 22 | gpt-6.1-sol-maxDetalhes do modelo
| 1483.8469422064072 | 1475.7115409166886 – 1491.982343496126 | 6320 |
| 23 | gemini-3.6-flash-highDetalhes do modelo
| 1482.7020039923352 | 1478.278787574737 – 1487.1252204099333 | 36122 |
| 24 | qwen3.8-maxDetalhes do modelo
| 1482.3530183862679 | 1477.3762943638942 – 1487.3297424086413 | 27766 |
| 25 | claude-opus-4-8-highDetalhes do modelo
| 1481.4953019365078 | 1477.627444398396 – 1485.3631594746198 | 64100 |
| 26 | gpt-5.5-highDetalhes do modelo
| 1481.4402312219954 | 1477.7173368841902 – 1485.1631255598004 | 69401 |
| 27 | mimo-v2.6-proDetalhes do modelo
| 1479.194755229377 | 1469.827446672319 – 1488.5620637864351 | 4075 |
| 28 | glm-5.3-maxDetalhes do modelo
| 1478.538851947597 | 1473.3104541772093 – 1483.7672497179851 | 22543 |
| 29 | gemini-3.5-flash-highDetalhes do modelo
| 1477.4750000563504 | 1473.5839498078906 – 1481.3660503048102 | 48486 |
| 30 | gpt-6-astra-maxDetalhes do modelo
| 1477.319231586918 | 1471.0194563904267 – 1483.6190067834093 | 12163 |
| 31 | gpt-5.5Detalhes do modelo
| 1476.6721977017742 | 1472.9844992886817 – 1480.3598961148664 | 70985 |
| 32 | glm-5.2-maxDetalhes do modelo
| 1475.8811079028058 | 1471.702113628 – 1480.0601021776117 | 49820 |
| 33 | gemini-3.5-flash-mediumDetalhes do modelo
| 1475.6660417384694 | 1471.5227637939777 – 1479.809319682961 | 47292 |
| 34 | gpt-5.2-chat-latest-20260210Detalhes do modelo
| 1475.6373078168551 | 1471.595766527421 – 1479.6788491062891 | 35999 |
| 35 | gpt-5.4-highDetalhes do modelo
| 1475.121670399431 | 1471.3573998332465 – 1478.8859409656152 | 64776 |
| 36 | claude-sonnet-5.5-xhighDetalhes do modelo
| 1474.93871350729 | 1467.1980477406435 – 1482.6793792739365 | 6831 |
| 37 | grok-4.20-beta1Detalhes do modelo
| 1474.7302637533137 | 1470.1587183537176 – 1479.30180915291 | 27908 |
| 38 | deepseek-v4.1-flash-maxDetalhes do modelo
| 1474.6319979791695 | 1468.4086018074258 – 1480.8553941509128 | 12793 |
| 39 | qwen3.7-max-previewDetalhes do modelo
| 1474.346453572102 | 1464.6199672413577 – 1484.0729399028464 | 3934 |
| 40 | claude-opus-4-8Detalhes do modelo
| 1474.3188347223909 | 1470.4723897525055 – 1478.1652796922765 | 65172 |
| 41 | glm-5.3-flashDetalhes do modelo
| 1473.8381537025502 | 1468.9663672235586 – 1478.709940181542 | 32925 |
| 42 | claude-opus-4-5-20251101-high-32kDetalhes do modelo
| 1473.6637831259952 | 1469.8319461697308 – 1477.4956200822596 | 37509 |
| 43 | gpt-5.5-instantDetalhes do modelo
| 1473.1071293051452 | 1468.1056095656027 – 1478.1086490446878 | 27158 |
| 44 | gemini-3-flashDetalhes do modelo
| 1472.7953716618217 | 1468.45319359402 – 1477.1375497296233 | 31325 |
| 45 | claude-sonnet-4-6Detalhes do modelo
| 1472.102664549635 | 1468.5893014469252 – 1475.6160276523447 | 70931 |
| 46 | grok-4.20-beta-0309-reasoningDetalhes do modelo
| 1471.549619642707 | 1467.875302568203 – 1475.2239367172112 | 66436 |
| 47 | grok-4.20-multi-agent-beta-0309Detalhes do modelo
| 1470.3132698298646 | 1466.6139100756589 – 1474.0126295840703 | 64946 |
| 48 | claude-opus-4-5-20251101Detalhes do modelo
| 1469.6308482689085 | 1466.4996428508657 – 1472.762053686951 | 72899 |
| 49 | mimo-v2.5-proDetalhes do modelo
| 1467.2561325712447 | 1463.7152451466172 – 1470.7970199958725 | 75721 |
| 50 | ernie-5.1Detalhes do modelo
| 1467.0070290704896 | 1462.4672285410786 – 1471.5468295999005 | 39468 |
| 51 | gpt-5.6-terra-xhighDetalhes do modelo
| 1466.429395420974 | 1462.172843173263 – 1470.685947668685 | 43271 |
| 52 | grok-4.5Detalhes do modelo
| 1465.7091491137166 | 1461.370929075886 – 1470.0473691515474 | 39896 |
| 53 | grok-4.1-thinkingDetalhes do modelo
| 1465.1846500694908 | 1462.004123387286 – 1468.3651767516953 | 66509 |
| 54 | glm-5.1Detalhes do modelo
| 1465.1654788552419 | 1461.580487104311 – 1468.7504706061725 | 62889 |
| 55 | gpt-5.4Detalhes do modelo
| 1464.7413131497262 | 1461.0529932764323 – 1468.4296330230204 | 67870 |
| 56 | deepseek-v4-pro-high-20260813Detalhes do modelo
| 1464.5780398046181 | 1457.965912470948 – 1471.1901671382882 | 9800 |
| 57 | qwen3.5-max-previewDetalhes do modelo
| 1464.3590078312648 | 1459.47663173607 – 1469.2413839264598 | 22600 |
| 58 | claude-sonnet-5-highDetalhes do modelo
| 1461.0744345634098 | 1456.948350050117 – 1465.2005190767027 | 49595 |
| 59 | kimi-k2.6Detalhes do modelo
| 1460.8290167351456 | 1456.4017956312816 – 1465.2562378390096 | 40013 |
| 60 | qwen3.6-max-previewDetalhes do modelo
| 1460.5766319378215 | 1452.3859846240014 – 1468.7672792516416 | 5426 |
| 61 | gpt-6-sol-maxDetalhes do modelo
| 1459.0243436054134 | 1452.6775146046048 – 1465.3711726062222 | 12466 |
| 62 | grok-4.1Detalhes do modelo
| 1459.0230228462426 | 1455.857296116748 – 1462.1887495757371 | 68648 |
| 63 | gemini-3-flash (thinking-minimal)Detalhes do modelo
| 1458.2906894860828 | 1455.2694440204261 – 1461.3119349517394 | 91039 |
| 64 | deepseek-v4-proDetalhes do modelo
| 1457.7921446281084 | 1453.8943665565255 – 1461.6899226996911 | 57594 |
| 65 | glm-5Detalhes do modelo
| 1457.2666631824843 | 1453.0235883683322 – 1461.5097379966364 | 29272 |
| 66 | claude-sonnet-4-5-20250929-high-32kDetalhes do modelo
| 1456.3975511624515 | 1453.6369939887531 – 1459.1581083361496 | 83940 |
| 67 | dola-seed-2.0-proDetalhes do modelo
| 1456.1749800128516 | 1452.7803705261254 – 1459.569589499578 | 79140 |
| 68 | gpt-5.1-highDetalhes do modelo
| 1455.7154324566077 | 1452.0058982470682 – 1459.4249666661472 | 41651 |
| 69 | qwen3.7-plusDetalhes do modelo
| 1455.682715060256 | 1451.3500504663698 – 1460.0153796541422 | 42075 |
| 70 | claude-sonnet-4-5-20250929Detalhes do modelo
| 1454.9317881127183 | 1452.0697753175984 – 1457.7938009078384 | 82688 |
| 71 | deepseek-v4-pro-high-previewDetalhes do modelo
| 1454.8622356319663 | 1450.897719163462 – 1458.8267521004705 | 54902 |
| 72 | gemini-3.5-flash-liteDetalhes do modelo
| 1454.7574024087119 | 1450.2850641771397 – 1459.2297406402843 | 35851 |
| 73 | grok-4.6-highDetalhes do modelo
| 1454.4891469812887 | 1449.6545088049184 – 1459.3237851576594 | 28965 |
| 74 | hy3Detalhes do modelo
| 1453.1921880349164 | 1447.0448295263823 – 1459.3395465434508 | 12208 |
| 75 | gpt-5.6-luna-xhighDetalhes do modelo
| 1452.5662458726235 | 1448.2646893469653 – 1456.8678023982818 | 41109 |
| 76 | gemma-4-31bDetalhes do modelo
| 1452.1630800897058 | 1444.7266838974383 – 1459.5994762819735 | 6147 |
| 77 | mimo-v2.6-flashDetalhes do modelo
| 1450.9317048216278 | 1444.4428108493223 – 1457.4205987939336 | 10917 |
| 78 | gpt-5.3-chat-latestDetalhes do modelo
| 1450.0437252298389 | 1445.8059953600753 – 1454.2814550996025 | 34345 |
| 79 | kimi-k2.5-thinkingDetalhes do modelo
| 1449.8411507786782 | 1446.5619450079605 – 1453.1203565493959 | 74759 |
| 80 | claude-opus-4-1-20250805-thinking-16kDetalhes do modelo
| 1449.740317460105 | 1446.2906328710956 – 1453.1900020491144 | 49542 |
| 81 | ernie-5.0-preview-1203Detalhes do modelo
| 1448.5424126668336 | 1442.0407124873213 – 1455.0441128463456 | 9806 |
| 82 | claude-opus-4-1-20250805Detalhes do modelo
| 1448.08122844461 | 1445.1109252000028 – 1451.0515316892167 | 77238 |
| 83 | mimo-v2-proDetalhes do modelo
| 1447.7890437774308 | 1443.1265062446753 – 1452.4515813101862 | 25447 |
| 84 | Step 5 PreviewDetalhes do modelo
| 1447.2701609595606 | 1439.7616339961178 – 1454.7786879230032 | 7116 |
| 85 | gpt-5.4-mini-highDetalhes do modelo
| 1446.9993918152215 | 1443.2518078724324 – 1450.7469757580106 | 63449 |
| 86 | ernie-5.0-0110Detalhes do modelo
| 1446.191720989189 | 1442.2978210411227 – 1450.0856209372553 | 36487 |
| 87 | gemini-2.5-proDetalhes do modelo
| 1445.413742345976 | 1442.9529937841278 – 1447.8744909078243 | 125366 |
| 88 | gpt-4.5-preview-2025-02-27Detalhes do modelo
| 1444.6270945007745 | 1438.915346695519 – 1450.3388423060298 | 14547 |
| 89 | grok-4.7-xhighDetalhes do modelo
| 1443.9789336394695 | 1437.5593577926459 – 1450.3985094862933 | 11591 |
| 90 | qwen3.6-plusDetalhes do modelo
| 1443.05823916263 | 1438.9244329261805 – 1447.1920453990792 | 48165 |
| 91 | gpt-6-luna-maxDetalhes do modelo
| 1442.8129943072395 | 1438.1883147148455 – 1447.4376738996334 | 49617 |
| 92 | chatgpt-4o-latest-20250326Detalhes do modelo
| 1442.5967756964685 | 1439.7889839663826 – 1445.4045674265544 | 81914 |
| 93 | grok-4.3Detalhes do modelo
| 1441.7179508681295 | 1438.0914375496773 – 1445.3444641865815 | 71347 |
| 94 | qwen3.5-397b-a17bDetalhes do modelo
| 1441.5655970064536 | 1438.475745273247 – 1444.6554487396604 | 93567 |
| 95 | glm-4.7Detalhes do modelo
| 1441.3266291777354 | 1435.2694154856003 – 1447.3838428698703 | 12253 |
| 96 | minimax-m3Detalhes do modelo
| 1441.3155955735351 | 1437.475817974704 – 1445.1553731723666 | 63973 |
| 97 | inklingDetalhes do modelo
| 1440.8717396141749 | 1436.5585433735794 – 1445.1849358547706 | 40648 |
| 98 | deepseek-v4-flash-high-previewDetalhes do modelo
| 1438.671493377064 | 1434.5659037304447 – 1442.7770830236834 | 51809 |
| 99 | gpt-5.1Detalhes do modelo
| 1438.6083170544998 | 1435.0172736066443 – 1442.1993605023551 | 44434 |
| 100 | qwen3.8-27bDetalhes do modelo
| 1437.752104573814 | 1432.6435966790054 – 1442.8606124686223 | 23294 |
| 101 | gemma-4-26b-a4bDetalhes do modelo
| 1437.519731525164 | 1430.082988387981 – 1444.956474662347 | 6094 |
| 102 | gpt-5.2-highDetalhes do modelo
| 1437.2456671445352 | 1433.6930397578767 – 1440.798294531194 | 49655 |
| 103 | longcat-flash-chat-2602-expDetalhes do modelo
| 1436.2095073307323 | 1431.683963279935 – 1440.7350513815297 | 29291 |
| 104 | deepseek-v4-flashDetalhes do modelo
| 1435.6475480811423 | 1431.6117385720809 – 1439.6833575902037 | 51987 |
| 105 | gpt-5.2Detalhes do modelo
| 1435.4042188843448 | 1432.2311055571777 – 1438.577332211512 | 83855 |
| 106 | gpt-5-highDetalhes do modelo
| 1434.8035075319092 | 1430.298651716069 – 1439.3083633477495 | 31722 |
| 107 | qwen3-max-previewDetalhes do modelo
| 1434.162064836811 | 1429.6485753397656 – 1438.6755543338563 | 27370 |
| 108 | mimo-v2.5Detalhes do modelo
| 1433.780160902417 | 1429.557633161148 – 1438.002688643686 | 47362 |
| 109 | glm-5v-turboDetalhes do modelo
| 1433.736549912949 | 1427.304659531306 – 1440.168440294592 | 10482 |
| 110 | gemini-3.1-flash-lite-previewDetalhes do modelo
| 1432.9270943558301 | 1429.3054802422857 – 1436.5487084693743 | 64211 |
| 111 | mistral-large-4Detalhes do modelo
| 1431.770090901766 | 1424.517422756084 – 1439.0227590474483 | 7451 |
| 112 | o3-2025-04-16Detalhes do modelo
| 1431.6911628578932 | 1428.060676562721 – 1435.3216491530652 | 58908 |
| 113 | mimo-v2-omniDetalhes do modelo
| 1430.8611784892162 | 1425.3162063351756 – 1436.406150643257 | 20619 |
| 114 | kimi-k2.5-instantDetalhes do modelo
| 1430.5292467523177 | 1424.0246063901936 – 1437.0338871144418 | 8376 |
| 115 | grok-4-1-fast-reasoningDetalhes do modelo
| 1430.3748201667343 | 1427.1787436948255 – 1433.5708966386433 | 57541 |
| 116 | kimi-k2-thinking-turboDetalhes do modelo
| 1430.0979685766106 | 1427.01038052258 – 1433.185556630641 | 63368 |
| 117 | mistral-medium-3.5Detalhes do modelo
| 1426.4927030203044 | 1420.0936596589775 – 1432.8917463816313 | 11778 |
| 118 | gpt-5-chatDetalhes do modelo
| 1426.3530750230902 | 1422.0576138307385 – 1430.6485362154417 | 31188 |
| 119 | claude-opus-4-20250514-thinking-16kDetalhes do modelo
| 1426.2507043729925 | 1421.852257087295 – 1430.64915165869 | 35904 |
| 120 | amazon-nova-experimental-chat-26-02-10Detalhes do modelo
| 1426.110749622517 | 1416.4420641200911 – 1435.7794351249427 | 3526 |
| 121 | nvidia-nemotron-3-ultra-550b-a55b-nvfp4Detalhes do modelo
| 1426.020838970455 | 1419.1357703185906 – 1432.9059076223198 | 11567 |
| 122 | deepseek-v3.2-exp-thinkingDetalhes do modelo
| 1425.0893087677296 | 1418.526778901325 – 1431.6518386341343 | 8998 |
| 123 | deepseek-v3.2Detalhes do modelo
| 1424.6358414432184 | 1421.1447741191487 – 1428.1269087672881 | 48112 |
| 124 | muse-glimmerDetalhes do modelo
| 1424.5427613711804 | 1414.851912631111 – 1434.2336101112498 | 3897 |
| 125 | glm-4.6Detalhes do modelo
| 1424.1228406450284 | 1420.2224633968601 – 1428.0232178931967 | 35824 |
| 126 | qwen3-max-2025-09-23Detalhes do modelo
| 1423.4391668748913 | 1416.9558683513974 – 1429.9224653983854 | 9027 |
| 127 | deepseek-v3.2-thinkingDetalhes do modelo
| 1422.4348639375376 | 1418.861140947485 – 1426.0085869275902 | 42071 |
| 128 | qwen3-235b-a22b-instruct-2507Detalhes do modelo
| 1422.131004335956 | 1419.580313231772 – 1424.6816954401404 | 98134 |
| 129 | deepseek-v3.2-expDetalhes do modelo
| 1421.6981589625707 | 1415.321567134356 – 1428.0747507907854 | 12004 |
| 130 | deepseek-r1-0528Detalhes do modelo
| 1421.4290222328934 | 1415.7507882696264 – 1427.1072561961605 | 18167 |
| 131 | grok-4-fast-chatDetalhes do modelo
| 1418.6409385713011 | 1410.8344853574888 – 1426.4473917851135 | 6340 |
| 132 | kimi-k2-0905-previewDetalhes do modelo
| 1418.6124049646044 | 1412.0867538211378 – 1425.1380561080712 | 11589 |
| 133 | ernie-5.0-preview-1022Detalhes do modelo
| 1418.2896956862303 | 1409.533134941121 – 1427.0462564313395 | 4753 |
| 134 | kimi-k2-0711-previewDetalhes do modelo
| 1417.7665407204036 | 1412.8722655216814 – 1422.6608159191258 | 27146 |
| 135 | deepseek-v3.1Detalhes do modelo
| 1417.0286131400032 | 1410.9662146935234 – 1423.0910115864833 | 14610 |
| 136 | qwen3.5-122b-a10bDetalhes do modelo
| 1416.3143007175977 | 1412.0281971034565 – 1420.6004043317387 | 29732 |
| 137 | deepseek-v3.1-terminus-thinkingDetalhes do modelo
| 1416.0817707576773 | 1405.9747883285522 – 1426.1887531868026 | 3375 |
| 138 | nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4Detalhes do modelo
| 1415.8780242500409 | 1404.063094449479 – 1427.6929540506028 | 2523 |
| 139 | deepseek-v3.1-thinkingDetalhes do modelo
| 1415.7460338117382 | 1409.085952811824 – 1422.4061148116525 | 11459 |
| 140 | minimax-m2.7Detalhes do modelo
| 1415.0035341569967 | 1411.653118390283 – 1418.3539499237102 | 84977 |
| 141 | deepseek-v3.1-terminusDetalhes do modelo
| 1414.6891098049177 | 1404.9718876785898 – 1424.4063319312456 | 3608 |
| 142 | gpt-4.1-2025-04-14Detalhes do modelo
| 1414.5863221306088 | 1410.8727571505342 – 1418.2998871106836 | 50312 |
| 143 | claude-opus-4-20250514Detalhes do modelo
| 1414.2718576179084 | 1409.9497013134892 – 1418.5940139223278 | 43043 |
| 144 | claude-haiku-4-5-20251001Detalhes do modelo
| 1414.264434778655 | 1411.8605435448783 – 1416.6683260124319 | 149199 |
| 145 | mistral-large-3Detalhes do modelo
| 1414.2471003865203 | 1411.3861729230061 – 1417.1080278500342 | 84205 |
| 146 | qwen3-vl-235b-a22b-instructDetalhes do modelo
| 1413.3151783944136 | 1406.7915427149521 – 1419.8388140738748 | 11320 |
| 147 | amazon-nova-experimental-chat-26-01-10Detalhes do modelo
| 1412.624365730427 | 1402.9465755175795 – 1422.3021559432743 | 3539 |
| 148 | grok-3-preview-02-24Detalhes do modelo
| 1411.216599128157 | 1406.870585307241 – 1415.562612949073 | 32499 |
| 149 | grok-4-0709Detalhes do modelo
| 1410.8508236600535 | 1406.9078381491324 – 1414.7938091709743 | 39693 |
| 150 | glm-4.5Detalhes do modelo
| 1410.7960767851844 | 1405.8737096155037 – 1415.7184439548648 | 23796 |
| 151 | gemini-2.5-flashDetalhes do modelo
| 1409.2369734409983 | 1406.7997377325987 – 1411.6742091493982 | 125521 |
| 152 | hunyuan-hy3-previewDetalhes do modelo
| 1409.130181868211 | 1401.7234846571093 – 1416.5368790793127 | 6879 |
| 153 | qwen3.5-27bDetalhes do modelo
| 1408.6798859866929 | 1404.387434481456 – 1412.9723374919295 | 28671 |
| 154 | mistral-medium-2508Detalhes do modelo
| 1407.7304452648948 | 1405.1325563663845 – 1410.328334163405 | 95321 |
| 155 | grok-4-fast-reasoningDetalhes do modelo
| 1405.3445376293862 | 1400.281279849894 – 1410.4077954088784 | 18269 |
| 156 | Inkling SmallDetalhes do modelo
| 1403.9804130510786 | 1399.3141720479516 – 1408.6466540542056 | 32304 |
| 157 | gemini-2.5-flash-preview-09-2025Detalhes do modelo
| 1403.0210663070695 | 1398.9715804716816 – 1407.0705521424577 | 32995 |
| 158 | o1-2024-12-17Detalhes do modelo
| 1402.2836309363597 | 1397.8077390365602 – 1406.7595228361592 | 27807 |
| 159 | qwen3-235b-a22b-no-thinkingDetalhes do modelo
| 1402.0083471132168 | 1397.4768849255674 – 1406.539809300866 | 37484 |
| 160 | claude-sonnet-4-20250514-thinking-32kDetalhes do modelo
| 1401.916389751909 | 1397.4665038151325 – 1406.3662756886854 | 34132 |
| 161 | gpt-5.4-nano-highDetalhes do modelo
| 1401.189486781593 | 1397.408633326442 – 1404.9703402367438 | 62396 |
| 162 | longcat-flash-chatDetalhes do modelo
| 1400.6245122297169 | 1394.2074018192354 – 1407.0416226401983 | 11168 |
| 163 | qwen3-235b-a22b-thinking-2507Detalhes do modelo
| 1399.756218631016 | 1393.182836429032 – 1406.329600833 | 8823 |
| 164 | qwen3-next-80b-a3b-instructDetalhes do modelo
| 1398.5312003749314 | 1393.7574764680655 – 1403.3049242817972 | 22760 |
| 165 | deepseek-r1Detalhes do modelo
| 1398.0815872307085 | 1393.1856276066546 – 1402.9775468547625 | 18524 |
| 166 | qwen3.5-flashDetalhes do modelo
| 1395.9010074723885 | 1392.2341058384577 – 1399.5679091063196 | 61802 |
| 167 | deepseek-v3-0324Detalhes do modelo
| 1395.194455554951 | 1391.3016314438785 – 1399.0872796660235 | 44973 |
| 168 | qwen3-vl-235b-a22b-thinkingDetalhes do modelo
| 1394.9029244607184 | 1388.0733527194186 – 1401.7324962020182 | 7859 |
| 169 | qwen3.5-35b-a3bDetalhes do modelo
| 1394.0126320493666 | 1389.7806525536546 – 1398.2446115450787 | 30457 |
| 170 | hunyuan-vision-1.5-thinkingDetalhes do modelo
| 1393.775837041224 | 1381.360441869242 – 1406.191232213206 | 2170 |
| 171 | step-3.5-flashDetalhes do modelo
| 1392.8156971671676 | 1389.2627102562321 – 1396.368684078103 | 60332 |
| 172 | amazon-nova-experimental-chat-12-10Detalhes do modelo
| 1392.7082960826679 | 1383.2381683580277 – 1402.178423807308 | 3733 |
| 173 | mimo-v2-flash (non-thinking)Detalhes do modelo
| 1391.532906590089 | 1388.049830437727 – 1395.0159827424511 | 48088 |
| 174 | o4-mini-2025-04-16Detalhes do modelo
| 1391.0547755412438 | 1387.0639782002297 – 1395.0455728822576 | 44855 |
| 175 | claude-sonnet-4-20250514Detalhes do modelo
| 1390.8871111749847 | 1386.493048393148 – 1395.2811739568212 | 39163 |
| 176 | minimax-m2.5Detalhes do modelo
| 1390.6393248159263 | 1386.7507469142622 – 1394.5279027175907 | 42815 |
| 177 | gpt-5-mini-highDetalhes do modelo
| 1389.9554783950398 | 1385.3073419786917 – 1394.6036148113878 | 26804 |
| 178 | o1-previewDetalhes do modelo
| 1388.5845803615682 | 1383.5741361004004 – 1393.5950246227358 | 31122 |
| 179 | claude-3-7-sonnet-20250219-thinking-32kDetalhes do modelo
| 1388.3546057323908 | 1384.1509981217666 – 1392.558213343015 | 38159 |
| 180 | qwen3-coder-480b-a35b-instructDetalhes do modelo
| 1387.5520617800003 | 1382.5746531348318 – 1392.5294704251687 | 25195 |
| 181 | mistral-medium-2505Detalhes do modelo
| 1387.2615590253674 | 1382.5413079702723 – 1391.9818100804623 | 32782 |
| 182 | hunyuan-t1-20250711Detalhes do modelo
| 1387.0605832804686 | 1378.3546428241282 – 1395.766523736809 | 4595 |
| 183 | solar-pro4Detalhes do modelo
| 1386.425816378497 | 1381.111884284797 – 1391.739748472197 | 21281 |
| 184 | mimo-v2-flash (thinking)Detalhes do modelo
| 1386.171445554082 | 1380.000190994903 – 1392.3427001132611 | 11142 |
| 185 | minimax-m2.1-previewDetalhes do modelo
| 1384.437854918656 | 1379.2613612323398 – 1389.6143486049723 | 17239 |
| 186 | hunyuan-turbos-20250416Detalhes do modelo
| 1383.0699055796856 | 1376.5760871490186 – 1389.5637240103526 | 10626 |
| 187 | gpt-4.1-mini-2025-04-14Detalhes do modelo
| 1382.848314009792 | 1378.5149148398377 – 1387.1817131797459 | 38709 |
| 188 | qwen3-30b-a3b-instruct-2507Detalhes do modelo
| 1382.337590205451 | 1377.433598383406 – 1387.241582027496 | 23322 |
| 189 | gemini-2.5-flash-lite-preview-09-2025-no-thinkingDetalhes do modelo
| 1379.3400079841863 | 1375.918012936507 – 1382.7620030318656 | 47437 |
| 190 | trinity-large-previewDetalhes do modelo
| 1378.7059951599044 | 1374.4488270282775 – 1382.9631632915314 | 31266 |
| 191 | glm-4.6vDetalhes do modelo
| 1378.2509451177166 | 1367.0800899074904 – 1389.4218003279427 | 2837 |
| 192 | qwen3-235b-a22bDetalhes do modelo
| 1374.8337321780411 | 1370.1245448413072 – 1379.5429195147751 | 25948 |
| 193 | gemini-2.5-flash-lite-preview-06-17-thinkingDetalhes do modelo
| 1374.8136513863196 | 1370.2914434410661 – 1379.3358593315734 | 32381 |
| 194 | claude-3-5-sonnet-20241022Detalhes do modelo
| 1374.2560571692657 | 1371.0502522073134 – 1377.461862131218 | 87769 |
| 195 | qwen2.5-maxDetalhes do modelo
| 1373.7691794399948 | 1369.654191848113 – 1377.8841670318764 | 32487 |
| 196 | glm-4.5-airDetalhes do modelo
| 1372.982853047627 | 1368.7295054947192 – 1377.2362006005346 | 30660 |
| 197 | claude-3-7-sonnet-20250219Detalhes do modelo
| 1372.568246809387 | 1368.603421807264 – 1376.5330718115097 | 42572 |
| 198 | qwen3-next-80b-a3b-thinkingDetalhes do modelo
| 1369.19340021516 | 1363.3313404648811 – 1375.0554599654386 | 13474 |
| 199 | trinity-large-thinkingDetalhes do modelo
| 1367.2643500773938 | 1362.6705156925389 – 1371.858184462249 | 30337 |
| 200 | gemma-3-27b-itDetalhes do modelo
| 1365.4528659816333 | 1361.7493134028653 – 1369.1564185604013 | 46666 |
| 201 | glm-4.7-flashDetalhes do modelo
| 1364.5160203965402 | 1358.8016752228536 – 1370.230365570227 | 12021 |
| 202 | minimax-m1Detalhes do modelo
| 1363.8032373271456 | 1359.5108017970663 – 1368.095672857225 | 34303 |
| 203 | amazon-nova-experimental-chat-11-10Detalhes do modelo
| 1363.7360440709815 | 1359.458002357681 – 1368.0140857842819 | 26039 |
| 204 | grok-3-mini-highDetalhes do modelo
| 1363.712470681161 | 1358.239987764219 – 1369.184953598103 | 15596 |
| 205 | o3-mini-highDetalhes do modelo
| 1363.5818572513192 | 1358.314557739216 – 1368.8491567634221 | 18589 |
| 206 | nvidia-nemotron-3-super-120b-a12bDetalhes do modelo
| 1360.080568965112 | 1352.9580190563502 – 1367.2031188738738 | 7878 |
| 207 | gemini-2.0-flash-001Detalhes do modelo
| 1359.9029625115695 | 1356.098301182708 – 1363.707623840431 | 43446 |
| 208 | deepseek-v3Detalhes do modelo
| 1358.4093056127422 | 1353.6507156986147 – 1363.1678955268694 | 21770 |
| 209 | grok-3-mini-betaDetalhes do modelo
| 1357.9032444549125 | 1352.7679704464801 – 1363.0385184633446 | 20931 |
| 210 | mistral-small-2506Detalhes do modelo
| 1356.11304619412 | 1350.8899008979465 – 1361.3361914902935 | 17462 |
| 211 | intellect-3Detalhes do modelo
| 1355.799842133749 | 1347.5465103810252 – 1364.053173886473 | 5431 |
| 212 | command-a-03-2025Detalhes do modelo
| 1353.7064642233104 | 1350.2355794089472 – 1357.1773490376736 | 55766 |
| 213 | gemini-2.0-flash-lite-preview-02-05Detalhes do modelo
| 1353.5725305932897 | 1349.2478149769104 – 1357.8972462096688 | 24955 |
| 214 | glm-4.5vDetalhes do modelo
| 1352.1730669993844 | 1343.73602737484 – 1360.6101066239291 | 4821 |
| 215 | gpt-oss-120bDetalhes do modelo
| 1351.758607712953 | 1347.3939655717056 – 1356.1232498542006 | 30206 |
| 216 | nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4Detalhes do modelo
| 1351.3464741967668 | 1345.7883772973917 – 1356.9045710961418 | 19938 |
| 217 | gemini-1.5-pro-002Detalhes do modelo
| 1351.3340444210469 | 1347.9311214910852 – 1354.7369673510084 | 55606 |
| 218 | step-3Detalhes do modelo
| 1348.9346735694933 | 1341.4228903807139 – 1356.446456758273 | 6293 |
| 219 | hunyuan-turbos-20250226Detalhes do modelo
| 1348.835663090471 | 1337.129833306806 – 1360.5414928741357 | 2220 |
| 220 | o3-miniDetalhes do modelo
| 1348.0956335428316 | 1344.540776306856 – 1351.6504907788071 | 56741 |
| 221 | amazon-nova-experimental-chat-10-20Detalhes do modelo
| 1348.039262351034 | 1341.8981770193845 – 1354.1803476826835 | 11626 |
| 222 | llama-3.1-nemotron-ultra-253b-v1Detalhes do modelo
| 1347.5895912097421 | 1335.9116838621437 – 1359.2674985573408 | 2549 |
| 223 | qwen3-32bDetalhes do modelo
| 1346.8054887198539 | 1337.3482173985908 – 1356.2627600411167 | 3926 |
| 224 | amazon-nova-experimental-chat-10-09Detalhes do modelo
| 1346.144226731704 | 1335.2115576777112 – 1357.076895785697 | 2781 |
| 225 | gpt-4o-2024-05-13Detalhes do modelo
| 1346.1327118570525 | 1342.6666387157807 – 1349.5987849983242 | 112881 |
| 226 | qwen-plus-0125Detalhes do modelo
| 1345.8675535596203 | 1337.5357795548991 – 1354.1993275643415 | 5819 |
| 227 | minimax-m2Detalhes do modelo
| 1343.3349893374027 | 1335.5942275820846 – 1351.0757510927206 | 6856 |
| 228 | claude-3-5-sonnet-20240620Detalhes do modelo
| 1343.3127418379856 | 1339.8685898664085 – 1346.7568938095628 | 82419 |
| 229 | ling-flash-2.0Detalhes do modelo
| 1343.2712347594852 | 1335.991700200355 – 1350.5507693186155 | 6947 |
| 230 | mercury-2Detalhes do modelo
| 1343.069006624283 | 1332.5446126662619 – 1353.5934005823042 | 3197 |
| 231 | nvidia-llama-3.3-nemotron-super-49b-v1.5Detalhes do modelo
| 1342.9597918363067 | 1332.9657014224101 – 1352.9538822502032 | 3328 |
| 232 | glm-4-plus-0111Detalhes do modelo
| 1342.7320441410684 | 1334.315518702335 – 1351.1485695798017 | 5760 |
| 233 | gemma-3-12b-itDetalhes do modelo
| 1341.7699741013544 | 1332.2584502580542 – 1351.2814979446548 | 3829 |
| 234 | hunyuan-turbo-0110Detalhes do modelo
| 1340.660457909418 | 1329.1432620123817 – 1352.1776538064541 | 2290 |
| 235 | granite-4.2-30bDetalhes do modelo
| 1340.000374723593 | 1329.5301734074906 – 1350.4705760396955 | 3401 |
| 236 | gpt-5-nano-highDetalhes do modelo
| 1337.7094937450508 | 1330.790540839154 – 1344.628446650948 | 8132 |
| 237 | o1-miniDetalhes do modelo
| 1336.7897986815658 | 1333.1253913053822 – 1340.4542060577496 | 51981 |
| 238 | gemini-advanced-0514Detalhes do modelo
| 1336.0012163029576 | 1330.8476341282046 – 1341.1547984777105 | 50148 |
| 239 | grok-2-2024-08-13Detalhes do modelo
| 1335.6517300748503 | 1331.9584958591615 – 1339.344964290539 | 63498 |
| 240 | gpt-4o-2024-08-06Detalhes do modelo
| 1335.6068350919506 | 1331.3930451192557 – 1339.8206250646458 | 45499 |
| 241 | qwq-32bDetalhes do modelo
| 1335.575784131921 | 1331.1143344553827 – 1340.0372338084594 | 25178 |
| 242 | llama-3.1-405b-instruct-bf16Detalhes do modelo
| 1335.4995092610654 | 1331.7680267130743 – 1339.2309918090566 | 41375 |
| 243 | nova-2-liteDetalhes do modelo
| 1334.7838251387504 | 1328.7021671091286 – 1340.865483168372 | 12413 |
| 244 | llama-3.1-405b-instruct-fp8Detalhes do modelo
| 1333.6458026070518 | 1330.04051713739 – 1337.2510880767134 | 59656 |
| 245 | step-2-16k-exp-202412Detalhes do modelo
| 1333.4810910478302 | 1324.8948373842559 – 1342.0673447114043 | 4833 |
| 246 | olmo-3.1-32b-instructDetalhes do modelo
| 1329.2190544150728 | 1323.078057598094 – 1335.3600512320515 | 11817 |
| 247 | yi-lightningDetalhes do modelo
| 1328.2671994698494 | 1323.3227178006193 – 1333.2116811390795 | 27332 |
| 248 | llama-3.3-nemotron-49b-super-v1Detalhes do modelo
| 1327.7213807549465 | 1315.5895911900964 – 1339.8531703197964 | 2218 |
| 249 | llama-4-maverick-17b-128e-instructDetalhes do modelo
| 1326.9823064447999 | 1322.7033907496857 – 1331.2612221399143 | 39450 |
| 250 | qwen3-30b-a3bDetalhes do modelo
| 1326.720438450228 | 1321.9721027866842 – 1331.4687741137718 | 26157 |
| 251 | hunyuan-large-2025-02-10Detalhes do modelo
| 1326.3241660004594 | 1316.59735852408 – 1336.0509734768389 | 3738 |
| 252 | claude-3-5-haiku-20241022Detalhes do modelo
| 1324.7789160325767 | 1321.5165811951285 – 1328.041250870025 | 69061 |
| 253 | gpt-4-turbo-2024-04-09Detalhes do modelo
| 1324.5281327823136 | 1320.6013929849275 – 1328.4548725796997 | 98114 |
| 254 | gemini-1.5-pro-001Detalhes do modelo
| 1324.07991820254 | 1320.0938085503917 – 1328.0660278546884 | 79138 |
| 255 | deepseek-v2.5-1210Detalhes do modelo
| 1323.3651984000508 | 1315.09240105609 – 1331.6379957440113 | 6795 |
| 256 | ring-flash-2.0Detalhes do modelo
| 1322.5656963837991 | 1315.2905909795527 – 1329.8408017880456 | 6990 |
| 257 | claude-3-opus-20240229Detalhes do modelo
| 1322.2806893188556 | 1319.207104621092 – 1325.3542740166195 | 194909 |
| 258 | gpt-4.1-nano-2025-04-14Detalhes do modelo
| 1322.2743527841192 | 1314.544138136766 – 1330.0045674314724 | 6103 |
| 259 | molmo-2-8bDetalhes do modelo
| 1322.1853637400916 | 1301.0790772580974 – 1343.2916502220858 | 822 |
| 260 | llama-4-scout-17b-16e-instructDetalhes do modelo
| 1321.500615383975 | 1316.763226028046 – 1326.2380047399038 | 29826 |
| 261 | step-1o-turbo-202506Detalhes do modelo
| 1319.7270516295512 | 1312.8529434530099 – 1326.6011598060923 | 8901 |
| 262 | glm-4-plusDetalhes do modelo
| 1319.3530780094234 | 1314.4197529328667 – 1324.28640308598 | 26126 |
| 263 | qwen-max-0919Detalhes do modelo
| 1318.1116107513792 | 1312.4085263350073 – 1323.8146951677509 | 16478 |
| 264 | llama-3.3-70b-instructDetalhes do modelo
| 1318.0654473917496 | 1314.561524832038 – 1321.569369951461 | 54497 |
| 265 | gpt-4o-mini-2024-07-18Detalhes do modelo
| 1317.5796589492732 | 1314.0300165249307 – 1321.1293013736156 | 68705 |
| 266 | gemma-3n-e4b-itDetalhes do modelo
| 1317.544899498674 | 1312.3625379709893 – 1322.727261026359 | 22137 |
| 267 | gpt-oss-20bDetalhes do modelo
| 1317.4239729820094 | 1311.0092570097922 – 1323.8386889542264 | 10419 |
| 268 | qwen2.5-plus-1127Detalhes do modelo
| 1314.5867058095696 | 1308.2283063132618 – 1320.9451053058776 | 10187 |
| 269 | mistral-large-2407Detalhes do modelo
| 1314.4464446749162 | 1310.512481270608 – 1318.380408079224 | 45459 |
| 270 | athene-v2-chatDetalhes do modelo
| 1314.1169221112486 | 1309.549964045758 – 1318.6838801767394 | 24739 |
| 271 | nvidia-nemotron-3-nano-30b-a3b-bf16Detalhes do modelo
| 1313.581223762608 | 1308.103391527044 – 1319.059055998172 | 15770 |
| 272 | gpt-4-0125-previewDetalhes do modelo
| 1313.2848891967135 | 1309.1998392024286 – 1317.3699391909986 | 93439 |
| 273 | gpt-4-1106-previewDetalhes do modelo
| 1312.9502664751014 | 1309.0606039790914 – 1316.8399289711115 | 100105 |
| 274 | hunyuan-standard-2025-02-10Detalhes do modelo
| 1311.2674782726456 | 1301.6029936101359 – 1320.931962935155 | 3904 |
| 275 | gemini-1.5-flash-002Detalhes do modelo
| 1309.3034391516185 | 1305.0720509494897 – 1313.5348273537475 | 34902 |
| 276 | grok-2-mini-2024-08-13Detalhes do modelo
| 1308.3842576995858 | 1304.6504431197657 – 1312.1180722794056 | 52567 |
| 277 | deepseek-v2.5Detalhes do modelo
| 1307.1758939412227 | 1302.462735489023 – 1311.8890523934224 | 24572 |
| 278 | athene-70b-0725Detalhes do modelo
| 1306.6557894242824 | 1300.9810734913733 – 1312.3305053571914 | 19621 |
| 279 | olmo-3-32b-thinkDetalhes do modelo
| 1306.0780588606535 | 1297.8335878246548 – 1314.322529896652 | 5831 |
| 280 | mistral-large-2411Detalhes do modelo
| 1305.5745826443517 | 1301.118282988417 – 1310.0308823002865 | 28073 |
| 281 | mercuryDetalhes do modelo
| 1305.3724523175474 | 1291.5943717909743 – 1319.1505328441206 | 1965 |
| 282 | magistral-medium-2506Detalhes do modelo
| 1304.9249426844683 | 1298.4755371828421 – 1311.3743481860945 | 11510 |
| 283 | granite-4.1-8bDetalhes do modelo
| 1304.1677821649496 | 1294.1651614333718 – 1314.1704028965273 | 4180 |
| 284 | gemma-3-4b-itDetalhes do modelo
| 1303.262118441158 | 1293.945083293274 – 1312.5791535890423 | 4171 |
| 285 | qwen2.5-72b-instructDetalhes do modelo
| 1302.8538323153166 | 1298.7656146877564 – 1306.942049942877 | 39406 |
| 286 | mistral-small-3.1-24b-instruct-2503Detalhes do modelo
| 1302.7143700738427 | 1298.1704902747756 – 1307.2582498729096 | 32727 |
| 287 | llama-3.1-nemotron-70b-instructDetalhes do modelo
| 1298.720485273577 | 1290.9584352744746 – 1306.4825352726796 | 7140 |
| 288 | hunyuan-large-visionDetalhes do modelo
| 1293.7742282264853 | 1284.624989084926 – 1302.9234673680448 | 5279 |
| 289 | llama-3.1-70b-instructDetalhes do modelo
| 1293.3762260694427 | 1289.6286323610916 – 1297.1238197777939 | 55240 |
| 290 | granite-4.2-8bDetalhes do modelo
| 1290.1761926441807 | 1279.0036546892693 – 1301.3487305990918 | 3254 |
| 291 | amazon-nova-pro-v1.0Detalhes do modelo
| 1290.0971398947597 | 1285.5100342507922 – 1294.6842455387275 | 24745 |
| 292 | granite-4.2-3bDetalhes do modelo
| 1289.649448114749 | 1278.0496286874911 – 1301.2492675420067 | 3251 |
| 293 | gemma-2-27b-itDetalhes do modelo
| 1289.5141560661143 | 1286.1174752803583 – 1292.9108368518703 | 75754 |
| 294 | jamba-1.5-largeDetalhes do modelo
| 1289.4786953167436 | 1282.1742993808712 – 1296.783091252616 | 8662 |
| 295 | reka-core-20240904Detalhes do modelo
| 1288.064244040549 | 1280.883546516223 – 1295.2449415648748 | 7312 |
| 296 | gpt-4-0314Detalhes do modelo
| 1287.9515699941733 | 1283.1972900506698 – 1292.705849937677 | 54173 |
| 297 | ibm-granite-h-smallDetalhes do modelo
| 1287.4742107786171 | 1279.07433477961 – 1295.8740867776244 | 5630 |
| 298 | llama-3.1-nemotron-51b-instructDetalhes do modelo
| 1286.7061343368207 | 1276.7415619852575 – 1296.670706688384 | 3749 |
| 299 | olmo-3.1-32b-thinkDetalhes do modelo
| 1286.6578255934219 | 1279.3960957104057 – 1293.919555476438 | 8301 |
| 300 | gemini-1.5-flash-001Detalhes do modelo
| 1286.5573806808304 | 1282.0559970395389 – 1291.058764322122 | 62833 |
| 301 | llama-3.1-tulu-3-70bDetalhes do modelo
| 1286.1342771067814 | 1275.6770262852392 – 1296.5915279283236 | 2846 |
| 302 | claude-3-sonnet-20240229Detalhes do modelo
| 1281.449412868066 | 1277.46820593892 – 1285.4306197972123 | 109284 |
| 303 | gemma-2-9b-it-simpoDetalhes do modelo
| 1280.4096541583303 | 1273.5533775354634 – 1287.2659307811973 | 10072 |
| 304 | nemotron-4-340b-instructDetalhes do modelo
| 1277.2503679791023 | 1271.9335334749053 – 1282.567202483299 | 19659 |
| 305 | llama-3-70b-instructDetalhes do modelo
| 1276.6380976417288 | 1273.0537618900935 – 1280.222433393364 | 156876 |
| 306 | command-r-plus-08-2024Detalhes do modelo
| 1276.3819106946182 | 1269.804145679302 – 1282.9596757099343 | 9866 |
| 307 | gpt-4-0613Detalhes do modelo
| 1276.3446463311536 | 1272.294954095309 – 1280.3943385669982 | 88723 |
| 308 | mistral-small-24b-instruct-2501Detalhes do modelo
| 1274.4008385707102 | 1268.4792030976703 – 1280.3224740437502 | 14681 |
| 309 | glm-4-0520Detalhes do modelo
| 1273.4793154674621 | 1266.499402429966 – 1280.459228504958 | 9788 |
| 310 | reka-flash-20240904Detalhes do modelo
| 1272.491065255883 | 1265.4932496260212 – 1279.4888808857447 | 7536 |
| 311 | qwen2.5-coder-32b-instructDetalhes do modelo
| 1270.630787113044 | 1262.5026850749707 – 1278.7588891511175 | 5432 |
| 312 | c4ai-aya-expanse-32bDetalhes do modelo
| 1267.296902546597 | 1262.3966928153072 – 1272.1971122778868 | 27124 |
| 313 | gemma-2-9b-itDetalhes do modelo
| 1267.0416100345371 | 1263.2097959372045 – 1270.8734241318698 | 54611 |
| 314 | deepseek-coder-v2Detalhes do modelo
| 1265.4499583976717 | 1259.1779951041929 – 1271.7219216911503 | 15147 |
| 315 | qwen2-72b-instructDetalhes do modelo
| 1261.9149677912656 | 1256.9683731398916 – 1266.8615624426398 | 37325 |
| 316 | command-r-plusDetalhes do modelo
| 1261.879449378141 | 1257.563658062261 – 1266.1952406940213 | 77554 |
| 317 | claude-3-haiku-20240307Detalhes do modelo
| 1261.7688839616312 | 1258.0094260565577 – 1265.5283418667045 | 117701 |
| 318 | amazon-nova-lite-v1.0Detalhes do modelo
| 1260.443479357642 | 1255.2504819272754 – 1265.6364767880086 | 19372 |
| 319 | gemini-1.5-flash-8b-001Detalhes do modelo
| 1258.83103827752 | 1254.5223365605884 – 1263.1397399944517 | 35558 |
| 320 | phi-4Detalhes do modelo
| 1256.3106977286461 | 1251.6997685220442 – 1260.921626935248 | 24126 |
| 321 | olmo-2-0325-32b-instructDetalhes do modelo
| 1251.7073459406304 | 1240.9324442602885 – 1262.4822476209724 | 3334 |
| 322 | command-r-08-2024Detalhes do modelo
| 1250.526523412432 | 1243.924103751033 – 1257.128943073831 | 10140 |
| 323 | mistral-large-2402Detalhes do modelo
| 1242.6627869860827 | 1237.9540029344598 – 1247.3715710377057 | 62436 |
| 324 | amazon-nova-micro-v1.0Detalhes do modelo
| 1240.722799603062 | 1235.5432851785786 – 1245.9023140275453 | 19364 |
| 325 | jamba-1.5-miniDetalhes do modelo
| 1239.8118834129855 | 1232.5872861000223 – 1247.0364807259489 | 8858 |
| 326 | ministral-8b-2410Detalhes do modelo
| 1237.628832148178 | 1228.541892385522 – 1246.715771910834 | 4781 |
| 327 | gemini-pro-dev-apiDetalhes do modelo
| 1236.9321078338762 | 1229.6243300306467 – 1244.2398856371058 | 18354 |
| 328 | qwen1.5-110b-chatDetalhes do modelo
| 1234.270227713346 | 1228.726506935261 – 1239.8139484914307 | 26195 |
| 329 | reka-flash-21b-20240226-onlineDetalhes do modelo
| 1233.6664312431237 | 1226.2764174363754 – 1241.056445049872 | 15450 |
| 330 | qwen1.5-72b-chatDetalhes do modelo
| 1233.6428686465763 | 1228.3788039060205 – 1238.9069333871319 | 39302 |
| 331 | hunyuan-standard-256kDetalhes do modelo
| 1233.1823588022396 | 1221.4581154596372 – 1244.9066021448423 | 2728 |
| 332 | mixtral-8x22b-instruct-v0.1Detalhes do modelo
| 1229.7102453695306 | 1225.1576651248674 – 1234.2628256141936 | 51416 |
| 333 | command-rDetalhes do modelo
| 1226.9919775032906 | 1222.2179846104505 – 1231.7659703961308 | 54036 |
| 334 | reka-flash-21b-20240226Detalhes do modelo
| 1226.921154487324 | 1220.9856447145903 – 1232.8566642600574 | 24806 |
| 335 | gpt-3.5-turbo-0125Detalhes do modelo
| 1225.7069421076292 | 1221.0172695355361 – 1230.3966146797225 | 66207 |
| 336 | gemini-proDetalhes do modelo
| 1223.7230219942562 | 1212.003791206564 – 1235.4422527819484 | 6390 |
| 337 | llama-3-8b-instructDetalhes do modelo
| 1223.7186219614196 | 1219.9840632094645 – 1227.4531807133744 | 104642 |
| 338 | c4ai-aya-expanse-8bDetalhes do modelo
| 1223.1005545193354 | 1216.1202438575647 – 1230.0808651811064 | 9818 |
| 339 | mistral-mediumDetalhes do modelo
| 1222.8287922771121 | 1217.3485982430127 – 1228.3089863112116 | 34550 |
| 340 | llama-3.1-tulu-3-8bDetalhes do modelo
| 1220.5184472009425 | 1209.8481803339173 – 1231.1887140679676 | 2896 |
| 341 | zephyr-orpo-141b-A35b-v0.1Detalhes do modelo
| 1213.1395079674414 | 1202.368687453495 – 1223.9103284813878 | 4652 |
| 342 | yi-1.5-34b-chatDetalhes do modelo
| 1212.914849721644 | 1207.882483602434 – 1217.9472158408541 | 24146 |
| 343 | llama-3.1-8b-instructDetalhes do modelo
| 1211.2299856226907 | 1207.0682111539336 – 1215.3917600914476 | 49605 |
| 344 | granite-3.1-8b-instructDetalhes do modelo
| 1208.622146026009 | 1197.5318550473405 – 1219.7124370046777 | 3090 |
| 345 | gpt-3.5-turbo-1106Detalhes do modelo
| 1204.364340059646 | 1195.6453265231833 – 1213.083353596109 | 16619 |
| 346 | qwen1.5-32b-chatDetalhes do modelo
| 1204.1103677471672 | 1198.0028821369358 – 1210.2178533573986 | 21741 |
| 347 | gemma-2-2b-itDetalhes do modelo
| 1200.107577985056 | 1196.0020693310244 – 1204.2130866390876 | 46616 |
| 348 | phi-3-medium-4k-instructDetalhes do modelo
| 1198.0165863252016 | 1192.859214793157 – 1203.173957857246 | 25055 |
| 349 | mixtral-8x7b-instruct-v0.1Detalhes do modelo
| 1197.2836860825435 | 1193.026584743141 – 1201.540787421946 | 73503 |
| 350 | dbrx-instruct-previewDetalhes do modelo
| 1195.644694040372 | 1189.5412692003094 – 1201.7481188804347 | 32191 |
| 351 | qwen1.5-14b-chatDetalhes do modelo
| 1191.1910493867767 | 1184.0865965387777 – 1198.2955022347755 | 17839 |
| 352 | internlm2_5-20b-chatDetalhes do modelo
| 1190.8117947646228 | 1183.6292435416472 – 1197.9943459875985 | 9901 |
| 353 | deepseek-llm-67b-chatDetalhes do modelo
| 1185.0649345408938 | 1173.6066893679817 – 1196.5231797138058 | 4932 |
| 354 | wizardlm-70bDetalhes do modelo
| 1184.861374353948 | 1175.4455460845672 – 1194.2772026233283 | 8214 |
| 355 | yi-34b-chatDetalhes do modelo
| 1183.8297439055646 | 1177.0142621572884 – 1190.6452256538407 | 15483 |
| 356 | granite-3.0-8b-instructDetalhes do modelo
| 1183.260094120219 | 1174.5894378836997 – 1191.9307503567384 | 6638 |
| 357 | openchat-3.5Detalhes do modelo
| 1183.1723137224028 | 1173.534599727998 – 1192.8100277168076 | 7968 |
| 358 | openchat-3.5-0106Detalhes do modelo
| 1182.8674117836958 | 1174.8892396034762 – 1190.8455839639155 | 12637 |
| 359 | gemma-1.1-7b-itDetalhes do modelo
| 1182.6390377866628 | 1176.576967544324 – 1188.7011080290017 | 23893 |
| 360 | snowflake-arctic-instructDetalhes do modelo
| 1180.1750485719153 | 1174.2739280166177 – 1186.076169127213 | 32832 |
| 361 | granite-3.1-2b-instructDetalhes do modelo
| 1178.9662314210025 | 1167.788608628374 – 1190.143854213631 | 3188 |
| 362 | tulu-2-dpo-70bDetalhes do modelo
| 1177.7792727938313 | 1167.9932869938218 – 1187.5652585938408 | 6535 |
| 363 | openhermes-2.5-mistral-7bDetalhes do modelo
| 1176.0830716533176 | 1165.7004275445363 – 1186.4657157620989 | 5006 |
| 364 | vicuna-33bDetalhes do modelo
| 1173.0470526188437 | 1166.8647185096142 – 1179.2293867280732 | 22479 |
| 365 | phi-3-small-8k-instructDetalhes do modelo
| 1171.1821845528668 | 1165.27439271007 – 1177.0899763956636 | 17766 |
| 366 | starling-lm-7b-betaDetalhes do modelo
| 1171.0676014971825 | 1163.6771159444218 – 1178.4580870499433 | 16056 |
| 367 | llama-2-70b-chatDetalhes do modelo
| 1170.7444567018665 | 1165.2631903108231 – 1176.2257230929101 | 38492 |
| 368 | starling-lm-7b-alphaDetalhes do modelo
| 1167.5225981771234 | 1159.4751408881543 – 1175.5700554660925 | 10224 |
| 369 | llama-3.2-3b-instructDetalhes do modelo
| 1166.8651083152117 | 1159.1636238540268 – 1174.5665927763966 | 7936 |
| 370 | nous-hermes-2-mixtral-8x7b-dpoDetalhes do modelo
| 1164.5016256567585 | 1152.6148275087262 – 1176.388423804791 | 3777 |
| 371 | granite-3.0-2b-instructDetalhes do modelo
| 1156.7726303210832 | 1148.3938938579277 – 1165.1513667842385 | 6837 |
| 372 | llama2-70b-steerlm-chatDetalhes do modelo
| 1154.8201606405717 | 1142.2513297672056 – 1167.3889915139375 | 3585 |
| 373 | qwq-32b-previewDetalhes do modelo
| 1154.2708306144589 | 1142.7964639526465 – 1165.745197276271 | 3231 |
| 374 | solar-10.7b-instruct-v1.0Detalhes do modelo
| 1152.5476041466957 | 1139.4169548091202 – 1165.6782534842714 | 4155 |
| 375 | dolphin-2.2.1-mistral-7bDetalhes do modelo
| 1152.3942501203132 | 1137.120150033806 – 1167.6683502068204 | 1679 |
| 376 | mpt-30b-chatDetalhes do modelo
| 1150.8799674824436 | 1138.6780234231037 – 1163.0819115417835 | 2572 |
| 377 | wizardlm-13bDetalhes do modelo
| 1149.64459760492 | 1140.453363915853 – 1158.835831293987 | 7044 |
| 378 | mistral-7b-instruct-v0.2Detalhes do modelo
| 1149.5046977254435 | 1142.8667268103386 – 1156.1426686405484 | 19402 |
| 379 | falcon-180b-chatDetalhes do modelo
| 1148.254360652834 | 1131.2525455174882 – 1165.25617578818 | 1295 |
| 380 | qwen1.5-7b-chatDetalhes do modelo
| 1143.9513311181565 | 1134.0796770966228 – 1153.8229851396902 | 4737 |
| 381 | phi-3-mini-4k-instruct-june-2024Detalhes do modelo
| 1143.2247115055432 | 1136.7895889111574 – 1149.659834099929 | 12297 |
| 382 | vicuna-13bDetalhes do modelo
| 1141.6939704884644 | 1135.0168263559633 – 1148.3711146209655 | 19367 |
| 383 | llama-2-13b-chatDetalhes do modelo
| 1141.524498236474 | 1134.8159453224455 – 1148.2330511505027 | 19174 |
| 384 | qwen-14b-chatDetalhes do modelo
| 1139.4858669946632 | 1128.5698304228895 – 1150.4019035664367 | 4964 |
| 385 | palm-2Detalhes do modelo
| 1139.3068433915755 | 1129.973649009727 – 1148.6400377734242 | 8554 |
| 386 | gemma-7b-itDetalhes do modelo
| 1137.793303656876 | 1128.3275140481649 – 1147.2590932655871 | 8925 |
| 387 | codellama-34b-instructDetalhes do modelo
| 1136.9799793960992 | 1128.111565334232 – 1145.8483934579667 | 7366 |
| 388 | zephyr-7b-betaDetalhes do modelo
| 1130.9234420022556 | 1122.1168680905714 – 1139.7300159139397 | 11118 |
| 389 | phi-3-mini-128k-instructDetalhes do modelo
| 1129.9548237035706 | 1122.5432837902933 – 1137.3663636168476 | 20685 |
| 390 | phi-3-mini-4k-instructDetalhes do modelo
| 1128.2044719870635 | 1121.8159778377487 – 1134.592966136378 | 20118 |
| 391 | guanaco-33bDetalhes do modelo
| 1127.6154170390669 | 1115.5677514873616 – 1139.663082590772 | 2921 |
| 392 | zephyr-7b-alphaDetalhes do modelo
| 1127.0554893533538 | 1111.5115056249629 – 1142.5994730817447 | 1785 |
| 393 | stripedhyena-nous-7bDetalhes do modelo
| 1121.737603918081 | 1110.7858805141852 – 1132.6893273219769 | 5182 |
| 394 | codellama-70b-instructDetalhes do modelo
| 1119.2665476716975 | 1101.1871551892275 – 1137.3459401541677 | 1143 |
| 395 | gemma-1.1-2b-itDetalhes do modelo
| 1116.7463920974953 | 1109.0304212914723 – 1124.4623629035184 | 10854 |
| 396 | vicuna-7bDetalhes do modelo
| 1115.4351275019244 | 1106.3353227842501 – 1124.5349322195989 | 6923 |
| 397 | smollm2-1.7b-instructDetalhes do modelo
| 1114.8115680346432 | 1100.475331409424 – 1129.1478046598627 | 2199 |
| 398 | llama-3.2-1b-instructDetalhes do modelo
| 1111.1932734500465 | 1103.3149378770254 – 1119.0716090230678 | 8045 |
| 399 | mistral-7b-instructDetalhes do modelo
| 1110.4879069188864 | 1101.2284733185468 – 1119.7473405192259 | 8977 |
| 400 | llama-2-7b-chatDetalhes do modelo
| 1108.0282837939628 | 1100.9922043367717 – 1115.0643632511542 | 14148 |
| 401 | gemma-2b-itDetalhes do modelo
| 1093.7307071617818 | 1082.2770594044603 – 1105.184354919103 | 4780 |
| 402 | qwen1.5-4b-chatDetalhes do modelo
| 1091.2669922834275 | 1081.9530614648033 – 1100.5809231020519 | 7597 |
| 403 | olmo-7b-instructDetalhes do modelo
| 1073.7188718325006 | 1062.589787923825 – 1084.8479557411763 | 6328 |
| 404 | koala-13bDetalhes do modelo
| 1071.0496830738366 | 1061.2354867349857 – 1080.8638794126878 | 6965 |
| 405 | alpaca-13bDetalhes do modelo
| 1070.3679298833215 | 1058.9822480513483 – 1081.7536117152945 | 5745 |
| 406 | gpt4all-13b-snoozyDetalhes do modelo
| 1067.837108085924 | 1052.7024843643064 – 1082.9717318075418 | 1743 |
| 407 | mpt-7b-chatDetalhes do modelo
| 1063.5754407221034 | 1051.6703126082946 – 1075.4805688359122 | 3924 |
| 408 | chatglm3-6bDetalhes do modelo
| 1056.6926233986233 | 1045.0638690218045 – 1068.3213777754418 | 4658 |
| 409 | RWKV-4-Raven-14BDetalhes do modelo
| 1042.4604534369935 | 1031.142856083697 – 1053.77805079029 | 4845 |
| 410 | chatglm2-6bDetalhes do modelo
| 1024.8938986965288 | 1011.3597931022016 – 1038.428004290856 | 2658 |
| 411 | oasst-pythia-12bDetalhes do modelo
| 1023.6548211994834 | 1012.8594386861869 – 1034.45020371278 | 6310 |
| 412 | chatglm-6bDetalhes do modelo
| 995.9417400733207 | 983.4507909842296 – 1008.4326891624121 | 4914 |
| 413 | fastchat-t5-3bDetalhes do modelo
| 992.6838579422479 | 980.3908220886115 – 1004.9768937958845 | 4203 |
| 414 | dolly-v2-12bDetalhes do modelo
| 982.6233095251253 | 969.1941265609801 – 996.0524924892702 | 3412 |
| 415 | llama-13bDetalhes do modelo
| 975.3067896859363 | 959.6410905939842 – 990.9724887778884 | 2391 |
| 416 | stablelm-tuned-alpha-7bDetalhes do modelo
| 953.3231557218382 | 940.699725479514 – 965.9465859641628 | 3287 |
Metodologia · Arena (LMArena)
- Categoria da fonte
- overall
- Configuração
- text_style_control · latest
- Métrica
- Arena score (Bradley–Terry) · higher · styleControlled=true
- Fonte verificada
- Fonte
8b599a3c759427b568b742e7ceeca9a516933e25- Licença dos dados
- CC-BY-4.0
- Atribuição
- Arena (LMArena), Arena Leaderboard Dataset. Selected and normalized by AISubHub; original ranks and scores retained.
Foi observado um prefixo contínuo da fonte até o limite da próxima categoria. Os dados completos não foram obtidos.
- Linhas lidas
- 3900
- Total informado pela fonte
- 11033
- Linhas da categoria incluídas
- 416
- Próxima categoria
- chinese · row_idx 416