{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/terminal_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":"terminal_bench","nom":"Terminal-Bench 2.0","tache":"code","etat":"actif","echelle":"unite","modeles":45,"poids_general":1.15,"difficulte":78.1,"pente":0.1242,"en_une_phrase":"Mener à bien des tâches dans un terminal : comprendre le système, utiliser les programmes disponibles, enchaîner les commandes jusqu'au résultat.","notation":"Part de tâches réussies, en moyenne sur plusieurs passages ; chaque ligne associe un modèle et un harnais (Claude Code, Codex CLI, Terminus).","limites":"Le harnais compte autant que le modèle : un même modèle change de score selon l'agent qui le pilote. Les données suivent la version 2.0, déjà remplacée sur le site officiel.","mainteneur":"Stanford et Laude Institute","url":"https://www.tbench.ai/","verifie":true},"tache":{"id":"code","nom":"Code","poids_general":15,"benchmarks_actifs":13},"modeles_mesures":45,"mesures":202,"classement":[{"rang":1,"modele":"gpt-5-5","nom":"GPT-5.5","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-5/","score_publie":0.847191011236,"score_0_1":0.8472,"niveau_suggere":91.9,"reflexion":"inconnue","harnais":"NexAU-AHE","configurations_mesurees":5,"date":"2026-04-23","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":2,"modele":"gpt-5-4","nom":"GPT-5.4","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-4/","score_publie":0.818,"score_0_1":0.818,"niveau_suggere":90.2,"reflexion":"inconnue","harnais":"ForgeCode","configurations_mesurees":1,"date":"2026-03-12","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"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":0.8022471910110001,"score_0_1":0.8022,"niveau_suggere":89.4,"reflexion":"inconnue","harnais":"WOZCODE","configurations_mesurees":1,"date":"2026-04-16","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":3,"modele":"gemini-3-1-pro","nom":"Gemini 3.1 Pro","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-1-pro/","score_publie":0.8022471910110001,"score_0_1":0.8022,"niveau_suggere":89.4,"reflexion":"inconnue","harnais":"TongAgents","configurations_mesurees":5,"date":"2026-02-19","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":5,"modele":"claude-opus-4-6","nom":"Claude Opus 4.6","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-6/","score_publie":0.798,"score_0_1":0.798,"niveau_suggere":89.2,"reflexion":"inconnue","harnais":"ForgeCode","configurations_mesurees":12,"date":"2026-03-12","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":6,"modele":"gpt-5-3-codex","nom":"GPT-5.3 Codex","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-3-codex/","score_publie":0.7842696629210001,"score_0_1":0.7843,"niveau_suggere":88.5,"reflexion":"inconnue","harnais":"SageAgent","configurations_mesurees":10,"date":"2026-02-05","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":7,"modele":"gemini-3-pro","nom":"Gemini 3 Pro","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-pro/","score_publie":0.6942571785270001,"score_0_1":0.6943,"niveau_suggere":84.7,"reflexion":"inconnue","harnais":"Ante","configurations_mesurees":8,"date":"2025-11-18","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":8,"modele":"gpt-5-2-codex","nom":"GPT-5.2 Codex","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-2-codex/","score_publie":0.6651685393260001,"score_0_1":0.6652,"niveau_suggere":83.6,"reflexion":"inconnue","harnais":"Deep Agents","configurations_mesurees":1,"date":"2026-01-14","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":9,"modele":"gpt-5-2","nom":"GPT-5.2","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-2/","score_publie":0.6494382022470001,"score_0_1":0.6494,"niveau_suggere":83.1,"reflexion":"inconnue","harnais":"Droid","configurations_mesurees":6,"date":"2025-12-11","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":10,"modele":"gemini-3-flash","nom":"Gemini 3 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-flash/","score_publie":0.642696629213,"score_0_1":0.6427,"niveau_suggere":82.8,"reflexion":"inconnue","harnais":"Junie CLI","configurations_mesurees":4,"date":"2025-12-17","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":11,"modele":"claude-opus-4-5","nom":"Claude Opus 4.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-5/","score_publie":0.631460674157,"score_0_1":0.6315,"niveau_suggere":82.4,"reflexion":"inconnue","harnais":"Droid","configurations_mesurees":10,"date":"2025-11-24","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":12,"modele":"gpt-5-1-codex-mini","nom":"GPT-5.1-Codex-mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-1-codex-mini/","score_publie":0.615730337079,"score_0_1":0.6157,"niveau_suggere":81.9,"reflexion":"inconnue","harnais":"hookele","configurations_mesurees":3,"date":"2025-11-12","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":13,"modele":"gpt-5-1-codex-max","nom":"GPT-5.1-Codex-Max","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-1-codex-max/","score_publie":0.604494382022,"score_0_1":0.6045,"niveau_suggere":81.5,"reflexion":"inconnue","harnais":"Codex CLI","configurations_mesurees":1,"date":"2025-11-19","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":14,"modele":"gpt-5-1-codex","nom":"GPT-5.1-Codex","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-1-codex/","score_publie":0.578,"score_0_1":0.578,"niveau_suggere":80.6,"reflexion":"inconnue","harnais":"Codex CLI","configurations_mesurees":5,"date":"2025-11-16","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":15,"modele":"grok-4-20","nom":"Grok 4.20","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-20/","score_publie":0.573033707865,"score_0_1":0.573,"niveau_suggere":80.5,"reflexion":"inconnue","harnais":"Grok CLI","configurations_mesurees":2,"date":"2026-03-10","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":16,"modele":"claude-sonnet-4-6","nom":"Claude Sonnet 4.6","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-4-6/","score_publie":0.534269662921,"score_0_1":0.5343,"niveau_suggere":79.2,"reflexion":"inconnue","harnais":"Simplai Agent","configurations_mesurees":2,"date":"2026-02-17","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":17,"modele":"glm-5","nom":"GLM-5","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-5/","score_publie":0.524157303371,"score_0_1":0.5242,"niveau_suggere":78.9,"reflexion":"inconnue","harnais":"Terminus 2","configurations_mesurees":1,"date":"2026-02-11","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":18,"modele":"gpt-5","nom":"GPT-5","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5/","score_publie":0.49606741573,"score_0_1":0.4961,"niveau_suggere":78,"reflexion":"inconnue","harnais":"Codex CLI","configurations_mesurees":8,"date":"2025-08-07","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":19,"modele":"gpt-5-1","nom":"GPT-5.1","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-1/","score_publie":0.476,"score_0_1":0.476,"niveau_suggere":77.3,"reflexion":"moyenne","harnais":"Terminus 2","configurations_mesurees":3,"date":"2025-11-16","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":20,"modele":"claude-sonnet-4-5","nom":"Claude Sonnet 4.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-4-5/","score_publie":0.465168539326,"score_0_1":0.4652,"niveau_suggere":77,"reflexion":"inconnue","harnais":"CAMEL-AI","configurations_mesurees":12,"date":"2025-09-29","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":21,"modele":"minimax-m2-7","nom":"MiniMax-M2.7","editeur":"MiniMax","page":"https://quelleia.com/modeles/minimax-m2-7/","score_publie":0.450561797753,"score_0_1":0.4506,"niveau_suggere":76.5,"reflexion":"inconnue","harnais":"IndusAGI Coding Agent","configurations_mesurees":2,"date":"2026-03-18","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":22,"modele":"gpt-5-codex","nom":"GPT-5-Codex","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-codex/","score_publie":0.443258426966,"score_0_1":0.4433,"niveau_suggere":76.3,"reflexion":"inconnue","harnais":"Codex CLI","configurations_mesurees":6,"date":"2025-09-15","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":23,"modele":"kimi-k2-5","nom":"Kimi K2.5","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k2-5/","score_publie":0.43202247191,"score_0_1":0.432,"niveau_suggere":75.9,"reflexion":"inconnue","harnais":"Terminus 2","configurations_mesurees":1,"date":"2026-01-27","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":24,"modele":"minimax-m2-5","nom":"MiniMax-M2.5","editeur":"MiniMax","page":"https://quelleia.com/modeles/minimax-m2-5/","score_publie":0.426966292135,"score_0_1":0.427,"niveau_suggere":75.7,"reflexion":"inconnue","harnais":"cchuter","configurations_mesurees":2,"date":"2026-02-12","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":25,"modele":"deepseek-v3-2","nom":"DeepSeek-V3.2","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v3-2/","score_publie":0.395505617978,"score_0_1":0.3955,"niveau_suggere":74.7,"reflexion":"inconnue","harnais":"Terminus 2","configurations_mesurees":1,"date":"2025-12-01","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":26,"modele":"claude-opus-4-1","nom":"Claude Opus 4.1","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-1/","score_publie":0.38,"score_0_1":0.38,"niveau_suggere":74.2,"reflexion":"inconnue","harnais":"Terminus 2","configurations_mesurees":8,"date":"2025-10-31","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":27,"modele":"minimax-m2-1","nom":"MiniMax-M2.1","editeur":"MiniMax","page":"https://quelleia.com/modeles/minimax-m2-1/","score_publie":0.366292134831,"score_0_1":0.3663,"niveau_suggere":73.7,"reflexion":"inconnue","harnais":"Crux","configurations_mesurees":2,"date":"2025-12-23","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":28,"modele":"kimi-k2-thinking","nom":"Kimi K2 Thinking","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k2-thinking/","score_publie":0.357303370787,"score_0_1":0.3573,"niveau_suggere":73.4,"reflexion":"inconnue","harnais":"Terminus 2","configurations_mesurees":2,"date":"2025-11-06","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":29,"modele":"claude-haiku-4-5","nom":"Claude Haiku 4.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-haiku-4-5/","score_publie":0.355056179775,"score_0_1":0.3551,"niveau_suggere":73.3,"reflexion":"inconnue","harnais":"Goose","configurations_mesurees":9,"date":"2025-10-15","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":30,"modele":"gpt-5-mini","nom":"GPT-5 mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-mini/","score_publie":0.348314606742,"score_0_1":0.3483,"niveau_suggere":73,"reflexion":"inconnue","harnais":"spoox-o-m","configurations_mesurees":10,"date":"2025-08-07","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":31,"modele":"glm-4-7","nom":"GLM-4.7","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-4-7/","score_publie":0.333895131086,"score_0_1":0.3339,"niveau_suggere":72.5,"reflexion":"inconnue","harnais":"Terminus 2","configurations_mesurees":2,"date":"2025-12-22","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":32,"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":0.326404494382,"score_0_1":0.3264,"niveau_suggere":72.3,"reflexion":"inconnue","harnais":"Terminus 2","configurations_mesurees":8,"date":"2025-06-17","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":33,"modele":"minimax-m2","nom":"MiniMax-M2","editeur":"MiniMax","page":"https://quelleia.com/modeles/minimax-m2/","score_publie":0.300374531835,"score_0_1":0.3004,"niveau_suggere":71.3,"reflexion":"inconnue","harnais":"Terminus 2","configurations_mesurees":1,"date":"2025-10-27","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":34,"modele":"kimi-k2-jul-2025","nom":"Kimi K2 (Jul 2025)","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k2-jul-2025/","score_publie":0.278,"score_0_1":0.278,"niveau_suggere":70.4,"reflexion":"inconnue","harnais":"Terminus 2","configurations_mesurees":4,"date":"2025-11-01","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":35,"modele":"grok-4","nom":"Grok 4","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4/","score_publie":0.272,"score_0_1":0.272,"niveau_suggere":70.2,"reflexion":"inconnue","harnais":"OpenHands","configurations_mesurees":6,"date":"2025-11-02","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":36,"modele":"qwen3-coder-480b-a35b","nom":"Qwen3-Coder-480B-A35B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen3-coder-480b-a35b/","score_publie":0.27191011236,"score_0_1":0.2719,"niveau_suggere":70.2,"reflexion":"inconnue","harnais":"Dakou Agent","configurations_mesurees":5,"date":"2025-07-22","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":37,"modele":"grok-code-fast-1","nom":"grok-code-fast-1","editeur":"xAI","page":"https://quelleia.com/modeles/grok-code-fast-1/","score_publie":0.258426966292,"score_0_1":0.2584,"niveau_suggere":69.6,"reflexion":"inconnue","harnais":"mini-SWE-agent","configurations_mesurees":4,"date":"2025-08-28","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":38,"modele":"glm-4-6","nom":"GLM-4.6","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/glm-4-6/","score_publie":0.24531835206,"score_0_1":0.2453,"niveau_suggere":69,"reflexion":"inconnue","harnais":"Terminus 2","configurations_mesurees":2,"date":"2025-09-30","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":39,"modele":"qwen-3-6-35b-a3b","nom":"Qwen 3.6 35B-A3B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-3-6-35b-a3b/","score_publie":0.230337078652,"score_0_1":0.2303,"niveau_suggere":68.4,"reflexion":"inconnue","harnais":"little-coder","configurations_mesurees":1,"date":"2026-04-16","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":40,"modele":"gpt-5-nano","nom":"GPT-5 nano","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-nano/","score_publie":0.2179775280899999,"score_0_1":0.218,"niveau_suggere":67.8,"reflexion":"inconnue","harnais":"spoox-o-m","configurations_mesurees":9,"date":"2025-08-07","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":41,"modele":"gpt-oss-120b","nom":"gpt-oss-120b","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-oss-120b/","score_publie":0.187,"score_0_1":0.187,"niveau_suggere":66.3,"reflexion":"inconnue","harnais":"Terminus 2","configurations_mesurees":4,"date":"2025-11-01","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":42,"modele":"gemini-2-5-flash-sep-2025","nom":"Gemini 2.5 Flash (Sep 2025)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-5-flash-sep-2025/","score_publie":0.171,"score_0_1":0.171,"niveau_suggere":65.4,"reflexion":"inconnue","harnais":"mini-SWE-agent","configurations_mesurees":4,"date":"2025-11-03","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":43,"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":0.170786516854,"score_0_1":0.1708,"niveau_suggere":65.4,"reflexion":"inconnue","harnais":"mini-SWE-agent","configurations_mesurees":4,"date":"2025-06-17","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":44,"modele":"qwen3-5-9b","nom":"Qwen3.5-9B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen3-5-9b/","score_publie":0.092134831461,"score_0_1":0.0921,"niveau_suggere":59.7,"reflexion":"inconnue","harnais":"little-coder","configurations_mesurees":1,"date":"2026-03-02","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"rang":45,"modele":"gpt-oss-20b","nom":"gpt-oss-20b","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-oss-20b/","score_publie":0.034,"score_0_1":0.034,"niveau_suggere":51.2,"reflexion":"inconnue","harnais":"mini-SWE-agent","configurations_mesurees":4,"date":"2025-11-03","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"}]}