{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/vending_bench_2/","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":"vending_bench_2","nom":"Vending-Bench 2","tache":"agents","etat":"actif","echelle":"dollars","modeles":56,"poids_general":1.67,"difficulte":87.5,"pente":0.0389,"en_une_phrase":"Gérer seul un distributeur automatique simulé pendant un an : stocks, prix, négociation avec les fournisseurs, imprévus.","notation":"Solde du compte en dollars à la fin de l'année simulée, en moyenne sur cinq parties.","limites":"Un seul scénario simulé. Andon Labs estime qu'une bonne stratégie humaine atteindrait environ 63 000 dollars, quatre fois le meilleur modèle.","mainteneur":"Andon Labs","url":"https://andonlabs.com/evals/vending-bench-2","verifie":true},"tache":{"id":"agents","nom":"Agents","poids_general":15,"benchmarks_actifs":9},"modeles_mesures":56,"mesures":62,"classement":[{"rang":1,"modele":"gpt-6-astra","nom":"GPT-6 Astra","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-6-astra/","score_publie":15514.701666666668,"score_0_1":0.5426,"niveau_suggere":91.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":2,"modele":"claude-opus-5","nom":"Claude Opus 5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-5/","score_publie":11181.87333333333,"score_0_1":0.5314,"niveau_suggere":90.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"claude-opus-4-7","nom":"Claude Opus 4.7","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-7/","score_publie":10936.763333333334,"score_0_1":0.5307,"niveau_suggere":90.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"gpt-5-6-sol","nom":"GPT-5.6 Sol","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-6-sol/","score_publie":9619.368,"score_0_1":0.5263,"niveau_suggere":90.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"grok-4-6","nom":"Grok 4.6","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-6/","score_publie":9047.0325,"score_0_1":0.5242,"niveau_suggere":90,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":6,"modele":"glm-5-2","nom":"GLM-5.2","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-5-2/","score_publie":8313.778333333335,"score_0_1":0.5213,"niveau_suggere":89.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":7,"modele":"glm-5-3","nom":"GLM-5.3","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-5-3/","score_publie":8163.609999999998,"score_0_1":0.5206,"niveau_suggere":89.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"claude-opus-4-6","nom":"Claude Opus 4.6","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-6/","score_publie":8017.594,"score_0_1":0.52,"niveau_suggere":89.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":9,"modele":"gpt-5-5","nom":"GPT-5.5","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-5/","score_publie":7523.843999999999,"score_0_1":0.5178,"niveau_suggere":89.4,"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":7343.206,"score_0_1":0.517,"niveau_suggere":89.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"claude-sonnet-4-6","nom":"Claude Sonnet 4.6","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-4-6/","score_publie":7204.139999999999,"score_0_1":0.5163,"niveau_suggere":89.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":12,"modele":"muse-spark-1-1","nom":"Muse Spark 1.1","editeur":"Meta AI","page":"https://quelleia.com/modeles/muse-spark-1-1/","score_publie":6520.474999999999,"score_0_1":0.5129,"niveau_suggere":88.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":13,"modele":"claude-sonnet-5","nom":"Claude Sonnet 5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-5/","score_publie":6377.701666666665,"score_0_1":0.5121,"niveau_suggere":88.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"kimi-k2-6","nom":"Kimi K2.6","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k2-6/","score_publie":6204.570000000001,"score_0_1":0.5112,"niveau_suggere":88.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":15,"modele":"gpt-5-4","nom":"GPT-5.4","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-4/","score_publie":6144.176,"score_0_1":0.5109,"niveau_suggere":88.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"gpt-5-3-codex","nom":"GPT-5.3 Codex","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-3-codex/","score_publie":5940.124000000002,"score_0_1":0.5097,"niveau_suggere":88.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":17,"modele":"claude-opus-4-8","nom":"Claude Opus 4.8","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-8/","score_publie":5787.428,"score_0_1":0.5088,"niveau_suggere":88.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"claude-fable-5","nom":"Claude Fable 5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-fable-5/","score_publie":5680.258,"score_0_1":0.5082,"niveau_suggere":88.4,"reflexion":"elevee","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":19,"modele":"glm-5-1","nom":"GLM-5.1","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-5-1/","score_publie":5634.406,"score_0_1":0.5079,"niveau_suggere":88.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":20,"modele":"gemini-3-pro","nom":"Gemini 3 Pro","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-pro/","score_publie":5478.158000000001,"score_0_1":0.5069,"niveau_suggere":88.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":21,"modele":"claude-fable-5-1","nom":"Claude Fable 5.1","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-fable-5-1/","score_publie":5421.556666666666,"score_0_1":0.5066,"niveau_suggere":88.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":22,"modele":"gemini-3-5-flash","nom":"Gemini 3.5 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-5-flash/","score_publie":5396.418333333334,"score_0_1":0.5064,"niveau_suggere":88.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"kimi-k3","nom":"Kimi K3","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k3/","score_publie":5165.035000000001,"score_0_1":0.5049,"niveau_suggere":88,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":24,"modele":"qwen-3-6-plus","nom":"Qwen 3.6 Plus","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-3-6-plus/","score_publie":5114.872000000001,"score_0_1":0.5046,"niveau_suggere":88,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":25,"modele":"gemini-3-8-flash","nom":"Gemini 3.8 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-8-flash/","score_publie":5093.793333333332,"score_0_1":0.5044,"niveau_suggere":88,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":26,"modele":"kimi-k2-7-code","nom":"Kimi K2.7 Code","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k2-7-code/","score_publie":5082.936,"score_0_1":0.5043,"niveau_suggere":88,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":27,"modele":"claude-opus-4-5","nom":"Claude Opus 4.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-5/","score_publie":4967.056666666668,"score_0_1":0.5035,"niveau_suggere":87.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":28,"modele":"grok-4-20","nom":"Grok 4.20","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-20/","score_publie":4662.846666666667,"score_0_1":0.5014,"niveau_suggere":87.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":29,"modele":"glm-5","nom":"GLM-5","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-5/","score_publie":4432.122000000001,"score_0_1":0.4996,"niveau_suggere":87.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":30,"modele":"qwen-3-6-max-preview","nom":"Qwen 3.6 Max (Preview)","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-3-6-max-preview/","score_publie":4254.1866666666665,"score_0_1":0.4982,"niveau_suggere":87.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":31,"modele":"gpt-5-6-luna","nom":"GPT-5.6 Luna","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-6-luna/","score_publie":4094.712,"score_0_1":0.4969,"niveau_suggere":87.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":32,"modele":"grok-4-5","nom":"Grok 4.5","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-5/","score_publie":3887.425999999999,"score_0_1":0.4951,"niveau_suggere":87,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":33,"modele":"claude-sonnet-4-5","nom":"Claude Sonnet 4.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-4-5/","score_publie":3838.74,"score_0_1":0.4947,"niveau_suggere":87,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":34,"modele":"gemini-3-1-pro","nom":"Gemini 3.1 Pro","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-1-pro/","score_publie":3774.254,"score_0_1":0.4941,"niveau_suggere":86.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":35,"modele":"gemini-3-flash","nom":"Gemini 3 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-flash/","score_publie":3634.715999999999,"score_0_1":0.4928,"niveau_suggere":86.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":36,"modele":"gpt-5-2","nom":"GPT-5.2","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-2/","score_publie":3591.326,"score_0_1":0.4924,"niveau_suggere":86.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":37,"modele":"deepseek-v4-pro","nom":"DeepSeek-V4-Pro","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v4-pro/","score_publie":3284.519999999999,"score_0_1":0.4893,"niveau_suggere":86.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":38,"modele":"glm-4-7","nom":"GLM-4.7","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-4-7/","score_publie":2376.816,"score_0_1":0.4782,"niveau_suggere":85.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":39,"modele":"minimax-m3","nom":"MiniMax-M3","editeur":"MiniMax","page":"https://quelleia.com/modeles/minimax-m3/","score_publie":2157.7716666666665,"score_0_1":0.4749,"niveau_suggere":85,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":40,"modele":"gpt-5-1","nom":"GPT-5.1","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-1/","score_publie":1473.432,"score_0_1":0.4618,"niveau_suggere":83.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":41,"modele":"kimi-k2-5","nom":"Kimi K2.5","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k2-5/","score_publie":1198.458,"score_0_1":0.4548,"niveau_suggere":82.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":42,"modele":"grok-4-1-fast","nom":"Grok 4.1 Fast","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-1-fast/","score_publie":1106.6280000000002,"score_0_1":0.452,"niveau_suggere":82.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":43,"modele":"deepseek-v3-2-exp","nom":"DeepSeek-V3.2-Exp","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v3-2-exp/","score_publie":1034.004,"score_0_1":0.4497,"niveau_suggere":82.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":44,"modele":"gemini-2-5-pro-jun-2025","nom":"Gemini 2.5 Pro (Jun 2025)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-5-pro-jun-2025/","score_publie":573.6420000000003,"score_0_1":0.4297,"niveau_suggere":80.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":45,"modele":"gemini-2-5-flash-jun-2025","nom":"Gemini 2.5 Flash (Jun 2025)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-5-flash-jun-2025/","score_publie":548.836,"score_0_1":0.4283,"niveau_suggere":80.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":46,"modele":"qwen-3-5-flash-hosted-35b-a3b","nom":"Qwen 3.5 Flash (hosted 35B-A3B)","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-3-5-flash-hosted-35b-a3b/","score_publie":462.6850000000002,"score_0_1":0.4225,"niveau_suggere":79.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":47,"modele":"claude-haiku-4-5","nom":"Claude Haiku 4.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-haiku-4-5/","score_publie":458.8859999999999,"score_0_1":0.4222,"niveau_suggere":79.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":48,"modele":"qwen3-5-27b","nom":"Qwen3.5-27B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen3-5-27b/","score_publie":201.976,"score_0_1":0.3949,"niveau_suggere":76.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":49,"modele":"minimax-m2","nom":"MiniMax-M2","editeur":"MiniMax","page":"https://quelleia.com/modeles/minimax-m2/","score_publie":160.5959999999999,"score_0_1":0.3874,"niveau_suggere":75.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":50,"modele":"qwen3-max","nom":"Qwen3-Max","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen3-max/","score_publie":71.56500000000018,"score_0_1":0.3614,"niveau_suggere":72.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":51,"modele":"grok-4-3-beta","nom":"Grok 4.3 Beta","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-3-beta/","score_publie":35.26166666666665,"score_0_1":0.3392,"niveau_suggere":70.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":52,"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":0.5440000000000417,"score_0_1":0.2243,"niveau_suggere":55.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":53,"modele":"qwen3-235b-a22b-thinking-jul-2025","nom":"Qwen3-235B-A22B-Thinking (Jul 2025)","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen3-235b-a22b-thinking-jul-2025/","score_publie":-11.340000000000078,"score_0_1":0.0178,"niveau_suggere":-15.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":54,"modele":"gpt-oss-120b","nom":"gpt-oss-120b","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-oss-120b/","score_publie":-21.532000000000053,"score_0_1":0.0178,"niveau_suggere":-15.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":55,"modele":"minimax-m2-5","nom":"MiniMax-M2.5","editeur":"MiniMax","page":"https://quelleia.com/modeles/minimax-m2-5/","score_publie":-23.15999999999999,"score_0_1":0.0178,"niveau_suggere":-15.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":56,"modele":"gpt-5-mini","nom":"GPT-5 mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-mini/","score_publie":-31.18399999999995,"score_0_1":0.0178,"niveau_suggere":-15.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"}]}