{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/cl_bench/","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":"cl_bench","nom":"CL-bench","tache":"donnees","etat":"actif","echelle":"unite","modeles":20,"poids_general":0,"difficulte":124.5,"pente":0.033,"en_une_phrase":"Apprendre un savoir nouveau fourni dans la consigne (un droit fictif, les règles d'un jeu inventé) et l'appliquer aussitôt.","notation":"Part des 1 899 tâches où la réponse satisfait tous les critères de la grille.","limites":"Notation en tout ou rien : une réponse presque juste vaut zéro, d'où des scores bas, 28 % au mieux.","mainteneur":"Tencent Hunyuan et université Fudan","url":"https://www.clbench.com/","verifie":true},"tache":{"id":"donnees","nom":"Données","poids_general":0,"benchmarks_actifs":0},"modeles_mesures":20,"mesures":23,"classement":[{"rang":1,"modele":"gpt-5-4","nom":"GPT-5.4","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-4/","score_publie":0.279,"score_0_1":0.279,"niveau_suggere":95.8,"reflexion":"maximale","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":2,"modele":"gpt-5-1","nom":"GPT-5.1","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-1/","score_publie":0.237,"score_0_1":0.237,"niveau_suggere":89.1,"reflexion":"elevee","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"grok-4-20","nom":"Grok 4.20","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-20/","score_publie":0.222,"score_0_1":0.222,"niveau_suggere":86.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"claude-opus-4-5","nom":"Claude Opus 4.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-5/","score_publie":0.211,"score_0_1":0.211,"niveau_suggere":84.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"gemini-3-1-pro","nom":"Gemini 3.1 Pro","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-1-pro/","score_publie":0.208,"score_0_1":0.208,"niveau_suggere":84,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":6,"modele":"claude-opus-4-6","nom":"Claude Opus 4.6","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-6/","score_publie":0.207,"score_0_1":0.207,"niveau_suggere":83.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":7,"modele":"qwen-3-6-plus","nom":"Qwen 3.6 Plus","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-3-6-plus/","score_publie":0.203,"score_0_1":0.203,"niveau_suggere":83.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"qwen-3-5-plus-hosted-397b-a17b","nom":"Qwen 3.5 Plus (hosted 397B-A17B)","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-3-5-plus-hosted-397b-a17b/","score_publie":0.198,"score_0_1":0.198,"niveau_suggere":82.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":9,"modele":"kimi-k2-5","nom":"Kimi K2.5","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k2-5/","score_publie":0.193,"score_0_1":0.193,"niveau_suggere":81.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":10,"modele":"glm-5","nom":"GLM-5","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-5/","score_publie":0.187,"score_0_1":0.187,"niveau_suggere":80,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"gpt-5-2","nom":"GPT-5.2","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-2/","score_publie":0.182,"score_0_1":0.182,"niveau_suggere":79,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":12,"modele":"o3","nom":"o3","editeur":"OpenAI","page":"https://quelleia.com/modeles/o3/","score_publie":0.178,"score_0_1":0.178,"niveau_suggere":78.2,"reflexion":"elevee","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":13,"modele":"kimi-k2-thinking","nom":"Kimi K2 Thinking","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k2-thinking/","score_publie":0.176,"score_0_1":0.176,"niveau_suggere":77.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"glm-4-7","nom":"GLM-4.7","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-4-7/","score_publie":0.159,"score_0_1":0.159,"niveau_suggere":74.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":15,"modele":"gemini-3-pro","nom":"Gemini 3 Pro","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-pro/","score_publie":0.158,"score_0_1":0.158,"niveau_suggere":73.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"mimo-v2-pro","nom":"MiMo-V2-Pro","editeur":"Xiaomi","page":"https://quelleia.com/modeles/mimo-v2-pro/","score_publie":0.157,"score_0_1":0.157,"niveau_suggere":73.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":17,"modele":"qwen3-max","nom":"Qwen3-Max","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen3-max/","score_publie":0.145,"score_0_1":0.145,"niveau_suggere":70.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"deepseek-v3-2-exp","nom":"DeepSeek-V3.2-Exp","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v3-2-exp/","score_publie":0.132,"score_0_1":0.132,"niveau_suggere":67.5,"reflexion":"elevee","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":19,"modele":"deepseek-v3-2","nom":"DeepSeek-V3.2","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v3-2/","score_publie":0.124,"score_0_1":0.124,"niveau_suggere":65.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":20,"modele":"minimax-m2-5","nom":"MiniMax-M2.5","editeur":"MiniMax","page":"https://quelleia.com/modeles/minimax-m2-5/","score_publie":0.114,"score_0_1":0.114,"niveau_suggere":62.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"}]}