{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/apex_agents/","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":"apex_agents","nom":"APEX-Agents","tache":"agents","etat":"actif","echelle":"unite","modeles":34,"poids_general":1.67,"difficulte":87.9,"pente":0.0842,"en_une_phrase":"480 missions de banque d'affaires, de conseil et de droit des sociétés, à mener dans des outils de bureau : tableurs, présentations, messagerie.","notation":"Part de missions où tous les critères de la grille sont remplis dès le premier essai, selon un modèle correcteur.","limites":"La correction est confiée à une IA. Le classement est tenu par Mercor, l'entreprise privée qui a conçu les missions.","mainteneur":"Mercor","url":"https://www.mercor.com/blog/introducing-apex-agents/","verifie":true},"tache":{"id":"agents","nom":"Agents","poids_general":15,"benchmarks_actifs":9},"modeles_mesures":34,"mesures":36,"classement":[{"rang":1,"modele":"claude-sonnet-5-5","nom":"Claude Sonnet 5.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-5-5/","score_publie":0.755,"score_0_1":0.755,"niveau_suggere":101.3,"reflexion":"maximale","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":2,"modele":"claude-opus-5-5","nom":"Claude Opus 5.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-5-5/","score_publie":0.735,"score_0_1":0.735,"niveau_suggere":100.1,"reflexion":"maximale","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"claude-fable-5-1","nom":"Claude Fable 5.1","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-fable-5-1/","score_publie":0.6859999999999999,"score_0_1":0.686,"niveau_suggere":97.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"gemini-3-7-flash","nom":"Gemini 3.7 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-7-flash/","score_publie":0.6779999999999999,"score_0_1":0.678,"niveau_suggere":96.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"claude-opus-5","nom":"Claude Opus 5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-5/","score_publie":0.658,"score_0_1":0.658,"niveau_suggere":95.7,"reflexion":"maximale","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":6,"modele":"grok-4-6","nom":"Grok 4.6","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-6/","score_publie":0.653,"score_0_1":0.653,"niveau_suggere":95.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":7,"modele":"gpt-6-astra","nom":"GPT-6 Astra","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-6-astra/","score_publie":0.647,"score_0_1":0.647,"niveau_suggere":95.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"gemini-3-8-flash","nom":"Gemini 3.8 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-8-flash/","score_publie":0.643,"score_0_1":0.643,"niveau_suggere":94.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":9,"modele":"claude-fable-5","nom":"Claude Fable 5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-fable-5/","score_publie":0.636,"score_0_1":0.636,"niveau_suggere":94.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":10,"modele":"gpt-5-6-terra","nom":"GPT-5.6 Terra","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-6-terra/","score_publie":0.5820000000000001,"score_0_1":0.582,"niveau_suggere":91.9,"reflexion":"maximale","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"muse-spark-1-3","nom":"Muse Spark 1.3","editeur":"Meta AI","page":"https://quelleia.com/modeles/muse-spark-1-3/","score_publie":0.578,"score_0_1":0.578,"niveau_suggere":91.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":12,"modele":"glm-5-3","nom":"GLM-5.3","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-5-3/","score_publie":0.5660000000000001,"score_0_1":0.566,"niveau_suggere":91.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":13,"modele":"grok-4-5","nom":"Grok 4.5","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-5/","score_publie":0.562,"score_0_1":0.562,"niveau_suggere":90.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"gpt-5-5","nom":"GPT-5.5","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-5/","score_publie":0.551,"score_0_1":0.551,"niveau_suggere":90.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":15,"modele":"claude-sonnet-5","nom":"Claude Sonnet 5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-5/","score_publie":0.545,"score_0_1":0.545,"niveau_suggere":90.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"glm-5-3-flash","nom":"GLM-5.3-Flash","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-5-3-flash/","score_publie":0.528,"score_0_1":0.528,"niveau_suggere":89.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":17,"modele":"gpt-5-4","nom":"GPT-5.4","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-4/","score_publie":0.524,"score_0_1":0.524,"niveau_suggere":89.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"gpt-5-6-sol","nom":"GPT-5.6 Sol","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-6-sol/","score_publie":0.514,"score_0_1":0.514,"niveau_suggere":88.6,"reflexion":"maximale","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":19,"modele":"kimi-k3","nom":"Kimi K3","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k3/","score_publie":0.506,"score_0_1":0.506,"niveau_suggere":88.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":20,"modele":"claude-opus-4-7","nom":"Claude Opus 4.7","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-7/","score_publie":0.492,"score_0_1":0.492,"niveau_suggere":87.6,"reflexion":"maximale","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":21,"modele":"claude-opus-4-8","nom":"Claude Opus 4.8","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-8/","score_publie":0.489,"score_0_1":0.489,"niveau_suggere":87.4,"reflexion":"maximale","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":22,"modele":"deepseek-v4-pro-0813","nom":"DeepSeek V4 Pro 0813","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v4-pro-0813/","score_publie":0.473,"score_0_1":0.473,"niveau_suggere":86.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"gemini-3-6-flash","nom":"Gemini 3.6 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-6-flash/","score_publie":0.469,"score_0_1":0.469,"niveau_suggere":86.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":24,"modele":"claude-opus-4-6","nom":"Claude Opus 4.6","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-6/","score_publie":0.4629999999999999,"score_0_1":0.463,"niveau_suggere":86.2,"reflexion":"maximale","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":25,"modele":"claude-sonnet-4-6","nom":"Claude Sonnet 4.6","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-4-6/","score_publie":0.43,"score_0_1":0.43,"niveau_suggere":84.6,"reflexion":"elevee","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":26,"modele":"glm-5-1","nom":"GLM-5.1","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-5-1/","score_publie":0.409,"score_0_1":0.409,"niveau_suggere":83.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":27,"modele":"minimax-m3","nom":"MiniMax-M3","editeur":"MiniMax","page":"https://quelleia.com/modeles/minimax-m3/","score_publie":0.377,"score_0_1":0.377,"niveau_suggere":82,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":28,"modele":"kimi-k2-7-code","nom":"Kimi K2.7 Code","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k2-7-code/","score_publie":0.376,"score_0_1":0.376,"niveau_suggere":81.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":29,"modele":"muse-spark-1-2","nom":"Muse Spark 1.2","editeur":"Meta AI","page":"https://quelleia.com/modeles/muse-spark-1-2/","score_publie":0.364,"score_0_1":0.364,"niveau_suggere":81.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":30,"modele":"gemini-3-1-pro","nom":"Gemini 3.1 Pro","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-1-pro/","score_publie":0.353,"score_0_1":0.353,"niveau_suggere":80.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":31,"modele":"inkling","nom":"Inkling","editeur":"Thinking Machines","page":"https://quelleia.com/modeles/inkling/","score_publie":0.3379999999999999,"score_0_1":0.338,"niveau_suggere":80,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":32,"modele":"gemini-3-5-flash","nom":"Gemini 3.5 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-5-flash/","score_publie":0.275,"score_0_1":0.275,"niveau_suggere":76.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":33,"modele":"qwen3-5-397b-a17b","nom":"Qwen3.5 397B-A17B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen3-5-397b-a17b/","score_publie":0.249,"score_0_1":0.249,"niveau_suggere":74.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":34,"modele":"gpt-oss-120b","nom":"gpt-oss-120b","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-oss-120b/","score_publie":0.044,"score_0_1":0.044,"niveau_suggere":51.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"}]}