{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/livebench_maths/","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":"livebench_maths","nom":"LiveBench, mathématiques","tache":"maths","etat":"archive","echelle":"pourcent","modeles":48,"poids_general":0,"difficulte":51.4,"pente":0.0832,"en_une_phrase":"Des problèmes de mathématiques récents, de niveau concours et olympiades.","notation":"La part de bonnes réponses, vérifiée automatiquement.","limites":"Juge la réponse finale, sans regarder la démonstration. Dernière édition en juin 2026.","mainteneur":"LiveBench (Abacus.AI, NYU et coauteurs)","url":"https://livebench.ai","verifie":true},"tache":{"id":"maths","nom":"Mathématiques","poids_general":10,"benchmarks_actifs":8},"modeles_mesures":48,"mesures":54,"classement":[{"rang":1,"modele":"gpt-5-1","nom":"GPT-5.1","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-1/","score_publie":94.46,"score_0_1":0.9446,"niveau_suggere":85.5,"reflexion":"elevee","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":2,"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":90.2,"score_0_1":0.902,"niveau_suggere":78.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"deepseek-r1","nom":"DeepSeek-R1","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-r1/","score_publie":80.71,"score_0_1":0.8071,"niveau_suggere":68.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"o1","nom":"o1","editeur":"OpenAI","page":"https://quelleia.com/modeles/o1/","score_publie":80.32,"score_0_1":0.8032,"niveau_suggere":68.3,"reflexion":"elevee","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"claude-3-7-sonnet","nom":"Claude 3.7 Sonnet","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-7-sonnet/","score_publie":79,"score_0_1":0.79,"niveau_suggere":67.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":6,"modele":"qwq-32b","nom":"QwQ-32B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwq-32b/","score_publie":77.82,"score_0_1":0.7782,"niveau_suggere":66.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":7,"modele":"o3-mini","nom":"o3-mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/o3-mini/","score_publie":77.29,"score_0_1":0.7729,"niveau_suggere":66.2,"reflexion":"elevee","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"gemini-2-0-flash-thinking-jan-2025","nom":"Gemini 2.0 Flash Thinking (Jan 2025)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-0-flash-thinking-jan-2025/","score_publie":75.85,"score_0_1":0.7585,"niveau_suggere":65.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":9,"modele":"deepseek-v3-mar-2025","nom":"DeepSeek-V3 (Mar 2025)","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v3-mar-2025/","score_publie":73.52,"score_0_1":0.7352,"niveau_suggere":63.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":10,"modele":"gemini-2-0-flash-dec-2024","nom":"Gemini 2.0 Flash (Dec 2024)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-0-flash-dec-2024/","score_publie":72.36,"score_0_1":0.7236,"niveau_suggere":63,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"gemini-2-0-pro","nom":"Gemini 2.0 Pro","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-0-pro/","score_publie":70.97,"score_0_1":0.7097,"niveau_suggere":62.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":12,"modele":"gpt-4-5","nom":"GPT-4.5","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-5/","score_publie":69.33,"score_0_1":0.6933,"niveau_suggere":61.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":13,"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":65.62,"score_0_1":0.6562,"niveau_suggere":59.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"o1-mini","nom":"o1-mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/o1-mini/","score_publie":61.99,"score_0_1":0.6199,"niveau_suggere":57.3,"reflexion":"moyenne","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":15,"modele":"deepseek-v3","nom":"DeepSeek-V3","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v3/","score_publie":60.54,"score_0_1":0.6054,"niveau_suggere":56.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"deepseek-r1-distill-qwen-32b","nom":"DeepSeek-R1-Distill-Qwen-32B","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-r1-distill-qwen-32b/","score_publie":59.44,"score_0_1":0.5944,"niveau_suggere":56,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":17,"modele":"qwen2-5-max","nom":"Qwen2.5-Max","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-max/","score_publie":58.35,"score_0_1":0.5835,"niveau_suggere":55.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"qwq-32b-preview","nom":"QwQ-32B-Preview","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwq-32b-preview/","score_publie":58.26,"score_0_1":0.5826,"niveau_suggere":55.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":19,"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":58.11,"score_0_1":0.5811,"niveau_suggere":55.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":20,"modele":"gemini-2-0-flash-lite","nom":"Gemini 2.0 Flash-Lite","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-0-flash-lite/","score_publie":58.09,"score_0_1":0.5809,"niveau_suggere":55.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":21,"modele":"learnlm-1-5-pro-experimental","nom":"learnlm-1.5-pro-experimental","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/learnlm-1-5-pro-experimental/","score_publie":57.75,"score_0_1":0.5775,"niveau_suggere":55.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":22,"modele":"gemma-3-27b","nom":"Gemma 3 27B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-3-27b/","score_publie":55.39,"score_0_1":0.5539,"niveau_suggere":54,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"grok-2-dec-2024","nom":"Grok-2 (Dec 2024)","editeur":"xAI","page":"https://quelleia.com/modeles/grok-2-dec-2024/","score_publie":54.88,"score_0_1":0.5488,"niveau_suggere":53.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":24,"modele":"dracarys2-72b-instruct","nom":"Dracarys2-72B-Instruct","editeur":null,"page":"https://quelleia.com/modeles/dracarys2-72b-instruct/","score_publie":54.66,"score_0_1":0.5466,"niveau_suggere":53.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":25,"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":52.28,"score_0_1":0.5228,"niveau_suggere":52.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":26,"modele":"gpt-4o-aug-2024","nom":"GPT-4o (Aug 2024)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4o-aug-2024/","score_publie":49.54,"score_0_1":0.4954,"niveau_suggere":51.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":27,"modele":"qwen2-5-coder-32b-instruct","nom":"Qwen2.5-Coder-32B-Instruct","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-32b-instruct/","score_publie":46.61,"score_0_1":0.4661,"niveau_suggere":49.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":28,"modele":"claude-3-opus","nom":"Claude 3 Opus","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-opus/","score_publie":43.62,"score_0_1":0.4362,"niveau_suggere":48.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":29,"modele":"gpt-4o-nov-2024","nom":"GPT-4o (Nov 2024)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4o-nov-2024/","score_publie":42.87,"score_0_1":0.4287,"niveau_suggere":48,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":30,"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":42.55,"score_0_1":0.4255,"niveau_suggere":47.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":31,"modele":"llama-3-3-70b","nom":"Llama 3.3 70B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-3-70b/","score_publie":42.24,"score_0_1":0.4224,"niveau_suggere":47.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":32,"modele":"phi-4","nom":"Phi-4","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-4/","score_publie":41.98,"score_0_1":0.4198,"niveau_suggere":47.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":33,"modele":"sonar","nom":"sonar","editeur":"Perplexity","page":"https://quelleia.com/modeles/sonar/","score_publie":41.63,"score_0_1":0.4163,"niveau_suggere":47.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":34,"modele":"dracarys2-llama-3-1-70b-instruct","nom":"Dracarys2-Llama-3.1-70B-Instruct","editeur":null,"page":"https://quelleia.com/modeles/dracarys2-llama-3-1-70b-instruct/","score_publie":40.3,"score_0_1":0.403,"niveau_suggere":46.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":35,"modele":"mistral-small-3","nom":"Mistral Small 3","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-small-3/","score_publie":39.89,"score_0_1":0.3989,"niveau_suggere":46.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":36,"modele":"mistral-small-3-1","nom":"Mistral Small 3.1","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-small-3-1/","score_publie":39.43,"score_0_1":0.3943,"niveau_suggere":46.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":37,"modele":"amazon-nova-pro","nom":"Amazon Nova Pro","editeur":"Amazon","page":"https://quelleia.com/modeles/amazon-nova-pro/","score_publie":38.04,"score_0_1":0.3804,"niveau_suggere":45.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":38,"modele":"amazon-nova-lite","nom":"Amazon Nova Lite","editeur":"Amazon","page":"https://quelleia.com/modeles/amazon-nova-lite/","score_publie":36.7,"score_0_1":0.367,"niveau_suggere":44.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":39,"modele":"gpt-4o-mini","nom":"GPT-4o mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4o-mini/","score_publie":36.31,"score_0_1":0.3631,"niveau_suggere":44.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":40,"modele":"claude-3-5-haiku","nom":"Claude 3.5 Haiku","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-5-haiku/","score_publie":35.54,"score_0_1":0.3554,"niveau_suggere":44.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":41,"modele":"amazon-nova-micro","nom":"Amazon Nova Micro","editeur":"Amazon","page":"https://quelleia.com/modeles/amazon-nova-micro/","score_publie":34.49,"score_0_1":0.3449,"niveau_suggere":43.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":42,"modele":"gemma-2-27b","nom":"Gemma 2 27B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-2-27b/","score_publie":26.46,"score_0_1":0.2646,"niveau_suggere":39.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":43,"modele":"command-r","nom":"Command R+","editeur":"Cohere","page":"https://quelleia.com/modeles/command-r/","score_publie":21.27,"score_0_1":0.2127,"niveau_suggere":35.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":44,"modele":"gemma-2-9b","nom":"Gemma 2 9B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-2-9b/","score_publie":19.8,"score_0_1":0.198,"niveau_suggere":34.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":45,"modele":"c4ai-command-r-08-2024","nom":"c4ai-command-r-08-2024","editeur":"Cohere","page":"https://quelleia.com/modeles/c4ai-command-r-08-2024/","score_publie":19.39,"score_0_1":0.1939,"niveau_suggere":34.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":46,"modele":"phi-3-small-7-4b","nom":"phi-3-small 7.4B","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-small-7-4b/","score_publie":17.58,"score_0_1":0.1758,"niveau_suggere":32.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":47,"modele":"phi-3-mini-3-8b","nom":"phi-3-mini 3.8B","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-mini-3-8b/","score_publie":15.72,"score_0_1":0.1572,"niveau_suggere":31.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":48,"modele":"olmo-2-furious-13b","nom":"OLMo 2 Furious 13B","editeur":"Allen Institute for AI","page":"https://quelleia.com/modeles/olmo-2-furious-13b/","score_publie":13.64,"score_0_1":0.1364,"niveau_suggere":29.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"}]}