{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/math_level_5/","edition":"2026-W40","date":"2026-09-28","echelle":"score_publie est le score de la source, dans son unité. score_0_1 est ce score ramené entre 0 et 1 pour le calcul. niveau_suggere est le score IA que cette seule mesure indique : 100 pour le meilleur modèle au lancement du site, 50 pour GPT-4o de novembre 2024. difficulte est le score IA d'un modèle qui obtient la moitié (score_0_1 = 0,5), pente la raideur de la courbe.","licence":"Réutilisation libre en citant « Quelle IA, quelleia.com » et la date de l'édition. Les mesures renvoient à leurs sources d'origine.","benchmark":{"id":"math_level_5","nom":"MATH Level 5","tache":"maths","etat":"archive","echelle":"unite","modeles":94,"poids_general":0,"difficulte":49.1,"pente":0.1256,"en_une_phrase":"Les 1 324 problèmes les plus durs du jeu MATH, tirés de concours de lycée américains comme l'AMC et l'AIME.","notation":"Part de réponses finales justes ; l'équivalence avec la solution attendue est jugée par un modèle correcteur.","limites":"Jeu public depuis 2021, donc probablement vu à l'entraînement. Les meilleurs modèles dépassent 98 % : le test ne départage plus le haut du classement.","mainteneur":"Epoch AI pour l'évaluation ; jeu MATH de Hendrycks et al. (2021)","url":"https://epoch.ai/benchmarks/math-level-5","verifie":true},"tache":{"id":"maths","nom":"Mathématiques","poids_general":10,"benchmarks_actifs":8},"modeles_mesures":94,"mesures":108,"classement":[{"rang":1,"modele":"gpt-5","nom":"GPT-5","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5/","score_publie":0.9813066465256798,"score_0_1":0.9813,"niveau_suggere":80.6,"reflexion":"elevee","harnais":null,"configurations_mesurees":2,"date":"2025-10-29","source":"https://epoch.ai/benchmarks"},{"rang":2,"modele":"gpt-5-mini","nom":"GPT-5 mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-mini/","score_publie":0.978474320241692,"score_0_1":0.9785,"niveau_suggere":79.4,"reflexion":"elevee","harnais":null,"configurations_mesurees":2,"date":"2025-10-30","source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"o4-mini","nom":"o4-mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/o4-mini/","score_publie":0.978285498489426,"score_0_1":0.9783,"niveau_suggere":79.4,"reflexion":"elevee","harnais":null,"configurations_mesurees":1,"date":"2025-04-16","source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"o3","nom":"o3","editeur":"OpenAI","page":"https://quelleia.com/modeles/o3/","score_publie":0.9777190332326284,"score_0_1":0.9777,"niveau_suggere":79.2,"reflexion":"elevee","harnais":null,"configurations_mesurees":1,"date":"2025-04-16","source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"claude-sonnet-4-5","nom":"Claude Sonnet 4.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-4-5/","score_publie":0.9773413897280968,"score_0_1":0.9773,"niveau_suggere":79,"reflexion":"budget","harnais":null,"configurations_mesurees":1,"date":"2025-10-21","source":"https://epoch.ai/benchmarks"},{"rang":6,"modele":"qwen3-max","nom":"Qwen3-Max","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen3-max/","score_publie":0.9712990936555892,"score_0_1":0.9713,"niveau_suggere":77.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-10-09","source":"https://epoch.ai/benchmarks"},{"rang":7,"modele":"deepseek-r1-may-2025","nom":"DeepSeek-R1 (May 2025)","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-r1-may-2025/","score_publie":0.9663897280966768,"score_0_1":0.9664,"niveau_suggere":75.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-05-29","source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"o3-mini","nom":"o3-mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/o3-mini/","score_publie":0.9648791540785498,"score_0_1":0.9649,"niveau_suggere":75.4,"reflexion":"elevee","harnais":null,"configurations_mesurees":2,"date":"2025-02-13","source":"https://epoch.ai/benchmarks"},{"rang":9,"modele":"claude-haiku-4-5","nom":"Claude Haiku 4.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-haiku-4-5/","score_publie":0.9636087945413192,"score_0_1":0.9636,"niveau_suggere":75.1,"reflexion":"budget","harnais":null,"configurations_mesurees":2,"date":"2025-10-22","source":"https://epoch.ai/benchmarks"},{"rang":10,"modele":"gemini-2-5-pro-may-2025","nom":"Gemini 2.5 Pro (May 2025)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-5-pro-may-2025/","score_publie":0.959025679758308,"score_0_1":0.959,"niveau_suggere":74.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-05-08","source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"gemini-2-5-pro-mar-2025","nom":"Gemini 2.5 Pro (Mar 2025)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-5-pro-mar-2025/","score_publie":0.9556268882175226,"score_0_1":0.9556,"niveau_suggere":73.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-05-07","source":"https://epoch.ai/benchmarks"},{"rang":12,"modele":"gpt-5-nano","nom":"GPT-5 nano","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-nano/","score_publie":0.952416918429003,"score_0_1":0.9524,"niveau_suggere":72.9,"reflexion":"moyenne","harnais":null,"configurations_mesurees":2,"date":"2025-08-20","source":"https://epoch.ai/benchmarks"},{"rang":13,"modele":"o1","nom":"o1","editeur":"OpenAI","page":"https://quelleia.com/modeles/o1/","score_publie":0.947129909365559,"score_0_1":0.9471,"niveau_suggere":72,"reflexion":"elevee","harnais":null,"configurations_mesurees":2,"date":"2025-02-13","source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"deepseek-r1","nom":"DeepSeek-R1","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-r1/","score_publie":0.9305135951661632,"score_0_1":0.9305,"niveau_suggere":69.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-31","source":"https://epoch.ai/benchmarks"},{"rang":15,"modele":"claude-3-7-sonnet","nom":"Claude 3.7 Sonnet","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-7-sonnet/","score_publie":0.9116314199395772,"score_0_1":0.9116,"niveau_suggere":67.6,"reflexion":"budget","harnais":null,"configurations_mesurees":4,"date":"2025-03-13","source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"grok-3-mini","nom":"Grok-3 mini","editeur":"xAI","page":"https://quelleia.com/modeles/grok-3-mini/","score_publie":0.9093655589123868,"score_0_1":0.9094,"niveau_suggere":67.4,"reflexion":"faible","harnais":null,"configurations_mesurees":2,"date":"2025-04-10","source":"https://epoch.ai/benchmarks"},{"rang":17,"modele":"deepseek-r1-distill-llama-70b","nom":"DeepSeek-R1-Distill-Llama-70B","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-r1-distill-llama-70b/","score_publie":0.8989803625377644,"score_0_1":0.899,"niveau_suggere":66.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-03-10","source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"o1-mini","nom":"o1-mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/o1-mini/","score_publie":0.8918051359516617,"score_0_1":0.8918,"niveau_suggere":65.9,"reflexion":"elevee","harnais":null,"configurations_mesurees":2,"date":"2025-02-13","source":"https://epoch.ai/benchmarks"},{"rang":19,"modele":"grok-3","nom":"Grok 3","editeur":"xAI","page":"https://quelleia.com/modeles/grok-3/","score_publie":0.8874622356495468,"score_0_1":0.8875,"niveau_suggere":65.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-04-10","source":"https://epoch.ai/benchmarks"},{"rang":20,"modele":"gpt-4-1-mini","nom":"GPT-4.1 mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-1-mini/","score_publie":0.8729229607250756,"score_0_1":0.8729,"niveau_suggere":64.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-04-14","source":"https://epoch.ai/benchmarks"},{"rang":21,"modele":"deepseek-r1-distill-qwen-14b","nom":"DeepSeek-R1-Distill-Qwen-14B","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-r1-distill-qwen-14b/","score_publie":0.8712235649546828,"score_0_1":0.8712,"niveau_suggere":64.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-03-11","source":"https://epoch.ai/benchmarks"},{"rang":22,"modele":"claude-opus-4","nom":"Claude Opus 4","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4/","score_publie":0.850453172205438,"score_0_1":0.8505,"niveau_suggere":62.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-05-22","source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"claude-sonnet-4","nom":"Claude Sonnet 4","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-4/","score_publie":0.8436555891238671,"score_0_1":0.8437,"niveau_suggere":62.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-05-22","source":"https://epoch.ai/benchmarks"},{"rang":24,"modele":"gemini-2-0-pro","nom":"Gemini 2.0 Pro","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-0-pro/","score_publie":0.8345921450151057,"score_0_1":0.8346,"niveau_suggere":61.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-02-06","source":"https://epoch.ai/benchmarks"},{"rang":25,"modele":"gpt-4-1","nom":"GPT-4.1","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-1/","score_publie":0.8300604229607251,"score_0_1":0.8301,"niveau_suggere":61.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-04-14","source":"https://epoch.ai/benchmarks"},{"rang":26,"modele":"gemini-2-0-flash-feb-2025","nom":"Gemini 2.0 Flash (Feb 2025)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-0-flash-feb-2025/","score_publie":0.8216578549848943,"score_0_1":0.8217,"niveau_suggere":61.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-02-06","source":"https://epoch.ai/benchmarks"},{"rang":27,"modele":"o1-preview","nom":"o1-preview","editeur":"OpenAI","page":"https://quelleia.com/modeles/o1-preview/","score_publie":0.8164652567975831,"score_0_1":0.8165,"niveau_suggere":60.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":28,"modele":"mistral-medium-3","nom":"Mistral Medium 3","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-medium-3/","score_publie":0.8162764350453172,"score_0_1":0.8163,"niveau_suggere":60.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-05-07","source":"https://epoch.ai/benchmarks"},{"rang":29,"modele":"gpt-4-5","nom":"GPT-4.5","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-5/","score_publie":0.7862537764350453,"score_0_1":0.7863,"niveau_suggere":59.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-02-28","source":"https://epoch.ai/benchmarks"},{"rang":30,"modele":"deepseek-v3-mar-2025","nom":"DeepSeek-V3 (Mar 2025)","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v3-mar-2025/","score_publie":0.75547583081571,"score_0_1":0.7555,"niveau_suggere":58,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-04-01","source":"https://epoch.ai/benchmarks"},{"rang":31,"modele":"gemma-3-27b","nom":"Gemma 3 27B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-3-27b/","score_publie":0.740370090634441,"score_0_1":0.7404,"niveau_suggere":57.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-03-13","source":"https://epoch.ai/benchmarks"},{"rang":32,"modele":"llama-4-maverick","nom":"Llama 4 Maverick","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-4-maverick/","score_publie":0.7301737160120846,"score_0_1":0.7302,"niveau_suggere":57,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-04-08","source":"https://epoch.ai/benchmarks"},{"rang":33,"modele":"gemini-1-5-pro-sept-2024","nom":"Gemini 1.5 Pro (Sept 2024)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-1-5-pro-sept-2024/","score_publie":0.7039274924471299,"score_0_1":0.7039,"niveau_suggere":56,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":34,"modele":"gpt-4-1-nano","nom":"GPT-4.1 nano","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-1-nano/","score_publie":0.6999622356495468,"score_0_1":0.7,"niveau_suggere":55.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-04-14","source":"https://epoch.ai/benchmarks"},{"rang":35,"modele":"qwen3-235b-a22b","nom":"Qwen3-235B-A22B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen3-235b-a22b/","score_publie":0.6885699899295065,"score_0_1":0.6886,"niveau_suggere":55.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-06-03","source":"https://epoch.ai/benchmarks"},{"rang":36,"modele":"qwen2-5-max","nom":"Qwen2.5-Max","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-max/","score_publie":0.6718277945619335,"score_0_1":0.6718,"niveau_suggere":54.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-04-01","source":"https://epoch.ai/benchmarks"},{"rang":37,"modele":"qwen-plus-jan-2025","nom":"Qwen Plus (Jan 2025)","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-plus-jan-2025/","score_publie":0.6527567975830816,"score_0_1":0.6528,"niveau_suggere":54.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-04-07","source":"https://epoch.ai/benchmarks"},{"rang":38,"modele":"phi-4","nom":"Phi-4","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-4/","score_publie":0.6493580060422961,"score_0_1":0.6494,"niveau_suggere":54,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-31","source":"https://epoch.ai/benchmarks"},{"rang":39,"modele":"deepseek-v3","nom":"DeepSeek-V3","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v3/","score_publie":0.6485083081570997,"score_0_1":0.6485,"niveau_suggere":53.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":40,"modele":"grok-2-dec-2024","nom":"Grok-2 (Dec 2024)","editeur":"xAI","page":"https://quelleia.com/modeles/grok-2-dec-2024/","score_publie":0.6351963746223565,"score_0_1":0.6352,"niveau_suggere":53.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-02-17","source":"https://epoch.ai/benchmarks"},{"rang":41,"modele":"qwen2-5-72b","nom":"Qwen2.5-72B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-72b/","score_publie":0.631703172205438,"score_0_1":0.6317,"niveau_suggere":53.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":42,"modele":"llama-4-scout","nom":"Llama 4 Scout","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-4-scout/","score_publie":0.6227341389728097,"score_0_1":0.6227,"niveau_suggere":53.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-04-08","source":"https://epoch.ai/benchmarks"},{"rang":43,"modele":"gemini-1-5-flash-sep-2024","nom":"Gemini 1.5 Flash (Sep 2024)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-1-5-flash-sep-2024/","score_publie":0.6186744712990937,"score_0_1":0.6187,"niveau_suggere":52.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":44,"modele":"claude-3-5-sonnet-october-2024","nom":"Claude 3.5 Sonnet (October 2024)","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-5-sonnet-october-2024/","score_publie":0.5694864048338368,"score_0_1":0.5695,"niveau_suggere":51.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":45,"modele":"qwen-turbo","nom":"Qwen-Turbo","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-turbo/","score_publie":0.5623111782477341,"score_0_1":0.5623,"niveau_suggere":51.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-04-07","source":"https://epoch.ai/benchmarks"},{"rang":46,"modele":"qwen2-5-32b","nom":"Qwen2.5-32B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-32b/","score_publie":0.5607061933534743,"score_0_1":0.5607,"niveau_suggere":51,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-30","source":"https://epoch.ai/benchmarks"},{"rang":47,"modele":"gpt-4o-aug-2024","nom":"GPT-4o (Aug 2024)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4o-aug-2024/","score_publie":0.5327605740181269,"score_0_1":0.5328,"niveau_suggere":50.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":48,"modele":"gpt-4o-mini","nom":"GPT-4o mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4o-mini/","score_publie":0.5263406344410876,"score_0_1":0.5263,"niveau_suggere":49.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":49,"modele":"claude-3-5-sonnet","nom":"Claude 3.5 Sonnet","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-5-sonnet/","score_publie":0.5168051359516617,"score_0_1":0.5168,"niveau_suggere":49.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":50,"modele":"gpt-4o-may-2024","nom":"GPT-4o (May 2024)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4o-may-2024/","score_publie":0.5104796072507553,"score_0_1":0.5105,"niveau_suggere":49.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":51,"modele":"mistral-large-2-nov-2024","nom":"Mistral Large 2 (Nov 2024)","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-large-2-nov-2024/","score_publie":0.5028323262839879,"score_0_1":0.5028,"niveau_suggere":49.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-02-25","source":"https://epoch.ai/benchmarks"},{"rang":52,"modele":"llama-3-1-405b","nom":"Llama 3.1-405B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-1-405b/","score_publie":0.4977341389728096,"score_0_1":0.4977,"niveau_suggere":49,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":52,"modele":"gpt-4o-nov-2024","nom":"GPT-4o (Nov 2024)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4o-nov-2024/","score_publie":0.4977341389728096,"score_0_1":0.4977,"niveau_suggere":49,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-02-05","source":"https://epoch.ai/benchmarks"},{"rang":54,"modele":"mistral-small-3-1","nom":"Mistral Small 3.1","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-small-3-1/","score_publie":0.4677114803625378,"score_0_1":0.4677,"niveau_suggere":48,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-03-18","source":"https://epoch.ai/benchmarks"},{"rang":55,"modele":"gpt-4-turbo-apr-2024","nom":"GPT-4 Turbo (Apr 2024)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-turbo-apr-2024/","score_publie":0.467333836858006,"score_0_1":0.4673,"niveau_suggere":48,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-02-27","source":"https://epoch.ai/benchmarks"},{"rang":56,"modele":"claude-3-5-haiku","nom":"Claude 3.5 Haiku","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-5-haiku/","score_publie":0.4635574018126888,"score_0_1":0.4636,"niveau_suggere":47.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-03-12","source":"https://epoch.ai/benchmarks"},{"rang":57,"modele":"mistral-large-2-jul-2024","nom":"Mistral Large 2 (Jul 2024)","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-large-2-jul-2024/","score_publie":0.4481684290030212,"score_0_1":0.4482,"niveau_suggere":47.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":57,"modele":"mistral-small-3","nom":"Mistral Small 3","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-small-3/","score_publie":0.4481684290030212,"score_0_1":0.4482,"niveau_suggere":47.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-30","source":"https://epoch.ai/benchmarks"},{"rang":59,"modele":"tulu-3-tulu-3-70b","nom":"Tulu 3 (Tülu 3) 70B","editeur":"Allen Institute for AI","page":"https://quelleia.com/modeles/tulu-3-tulu-3-70b/","score_publie":0.426642749244713,"score_0_1":0.4266,"niveau_suggere":46.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":60,"modele":"llama-3-3-70b","nom":"Llama 3.3 70B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-3-70b/","score_publie":0.4159743202416918,"score_0_1":0.416,"niveau_suggere":46.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":61,"modele":"gemini-1-5-pro-may-2024","nom":"Gemini 1.5 Pro (May 2024)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-1-5-pro-may-2024/","score_publie":0.4074773413897281,"score_0_1":0.4075,"niveau_suggere":46.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":62,"modele":"gpt-4-turbo-nov-2023","nom":"GPT-4 Turbo (Nov 2023)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-turbo-nov-2023/","score_publie":0.4002077039274924,"score_0_1":0.4002,"niveau_suggere":45.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":63,"modele":"llama-3-2-90b","nom":"Llama 3.2 90B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-2-90b/","score_publie":0.3943542296072507,"score_0_1":0.3944,"niveau_suggere":45.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":64,"modele":"qwen2-72b","nom":"Qwen2-72B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-72b/","score_publie":0.3906722054380664,"score_0_1":0.3907,"niveau_suggere":45.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":65,"modele":"claude-3-opus","nom":"Claude 3 Opus","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-opus/","score_publie":0.3748111782477341,"score_0_1":0.3748,"niveau_suggere":45,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":66,"modele":"llama-3-1-70b","nom":"Llama 3.1-70B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-1-70b/","score_publie":0.366786253776435,"score_0_1":0.3668,"niveau_suggere":44.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":67,"modele":"gemma-2-27b","nom":"Gemma 2 27B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-2-27b/","score_publie":0.2788897280966767,"score_0_1":0.2789,"niveau_suggere":41.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":68,"modele":"wizardlm-2-8x22b","nom":"WizardLM-2 8x22B","editeur":"Microsoft","page":"https://quelleia.com/modeles/wizardlm-2-8x22b/","score_publie":0.2573640483383685,"score_0_1":0.2574,"niveau_suggere":40.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":69,"modele":"yi-1-5-34b","nom":"Yi-1.5-34B","editeur":"01.AI","page":"https://quelleia.com/modeles/yi-1-5-34b/","score_publie":0.2548149546827795,"score_0_1":0.2548,"niveau_suggere":40.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":70,"modele":"gemini-1-5-flash-may-2024","nom":"Gemini 1.5 Flash (May 2024)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-1-5-flash-may-2024/","score_publie":0.2512273413897281,"score_0_1":0.2512,"niveau_suggere":40.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":71,"modele":"mistral-large","nom":"Mistral Large","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-large/","score_publie":0.2446185800604229,"score_0_1":0.2446,"niveau_suggere":40.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":72,"modele":"mixtral-8x22b","nom":"Mixtral 8x22B","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mixtral-8x22b/","score_publie":0.2424471299093655,"score_0_1":0.2424,"niveau_suggere":40,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":73,"modele":"gpt-4-jun-2023","nom":"GPT-4 (Jun 2023)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-jun-2023/","score_publie":0.2297016616314199,"score_0_1":0.2297,"niveau_suggere":39.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":74,"modele":"llama-3-1-8b","nom":"Llama 3.1-8B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-1-8b/","score_publie":0.2287575528700906,"score_0_1":0.2288,"niveau_suggere":39.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":75,"modele":"hermes-2-theta-llama-3-70b","nom":"Hermes 2 Theta Llama-3 70B","editeur":"Nous Research","page":"https://quelleia.com/modeles/hermes-2-theta-llama-3-70b/","score_publie":0.226869335347432,"score_0_1":0.2269,"niveau_suggere":39.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":76,"modele":"llama-3-70b","nom":"Llama 3-70B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-70b/","score_publie":0.225547583081571,"score_0_1":0.2255,"niveau_suggere":39.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":77,"modele":"gemma-2-9b","nom":"Gemma 2 9B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-2-9b/","score_publie":0.2100641993957704,"score_0_1":0.2101,"niveau_suggere":38.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":78,"modele":"claude-3-sonnet","nom":"Claude 3 Sonnet","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-sonnet/","score_publie":0.1817409365558912,"score_0_1":0.1817,"niveau_suggere":37.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":79,"modele":"phi-3-medium-14b","nom":"phi-3-medium 14B","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-medium-14b/","score_publie":0.1756042296072507,"score_0_1":0.1756,"niveau_suggere":36.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-31","source":"https://epoch.ai/benchmarks"},{"rang":80,"modele":"gpt-3-5-turbo-nov-2023","nom":"GPT-3.5 Turbo (Nov 2023)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-5-turbo-nov-2023/","score_publie":0.158893504531722,"score_0_1":0.1589,"niveau_suggere":35.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":81,"modele":"ministral-8b","nom":"Ministral 8B","editeur":"Mistral AI","page":"https://quelleia.com/modeles/ministral-8b/","score_publie":0.149358006042296,"score_0_1":0.1494,"niveau_suggere":35.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":82,"modele":"claude-3-haiku","nom":"Claude 3 Haiku","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-haiku/","score_publie":0.1487915407854985,"score_0_1":0.1488,"niveau_suggere":35.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":83,"modele":"ministral-3b","nom":"Ministral 3B","editeur":"Mistral AI","page":"https://quelleia.com/modeles/ministral-3b/","score_publie":0.1444486404833836,"score_0_1":0.1444,"niveau_suggere":34.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":84,"modele":"claude-2","nom":"Claude 2","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-2/","score_publie":0.1172583081570997,"score_0_1":0.1173,"niveau_suggere":33,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":85,"modele":"dbrx","nom":"DBRX","editeur":"Databricks","page":"https://quelleia.com/modeles/dbrx/","score_publie":0.1165030211480362,"score_0_1":0.1165,"niveau_suggere":32.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":86,"modele":"gpt-3-5-turbo-jan-2024","nom":"GPT-3.5 Turbo (Jan 2024)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-5-turbo-jan-2024/","score_publie":0.1163141993957704,"score_0_1":0.1163,"niveau_suggere":32.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":87,"modele":"gemini-1-0-pro","nom":"Gemini 1.0 Pro","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-1-0-pro/","score_publie":0.1124433534743202,"score_0_1":0.1124,"niveau_suggere":32.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":88,"modele":"mistral-nemo","nom":"Mistral NeMo","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-nemo/","score_publie":0.1082892749244713,"score_0_1":0.1083,"niveau_suggere":32.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":89,"modele":"mixtral-8x7b","nom":"Mixtral 8x7B","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mixtral-8x7b/","score_publie":0.0995090634441087,"score_0_1":0.0995,"niveau_suggere":31.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":90,"modele":"deepseek-llm-67b","nom":"DeepSeek LLM 67B","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-llm-67b/","score_publie":0.0639161631419939,"score_0_1":0.0639,"niveau_suggere":27.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":91,"modele":"llama-3-8b","nom":"Llama 3-8B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-8b/","score_publie":0.0612726586102719,"score_0_1":0.0613,"niveau_suggere":27.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":92,"modele":"yi-34b","nom":"Yi-34B","editeur":"01.AI","page":"https://quelleia.com/modeles/yi-34b/","score_publie":0.0514539274924471,"score_0_1":0.0515,"niveau_suggere":25.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":93,"modele":"mistral-7b-v0-3","nom":"Mistral 7B v0.3","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-7b-v0-3/","score_publie":0.0368202416918429,"score_0_1":0.0368,"niveau_suggere":23.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"},{"rang":94,"modele":"llama-2-70b","nom":"Llama 2-70B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-70b/","score_publie":0.0328549848942598,"score_0_1":0.0329,"niveau_suggere":22.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":"2025-01-27","source":"https://epoch.ai/benchmarks"}]}