{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/blueprint_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":"blueprint_bench_2","nom":"Blueprint-Bench 2","tache":"vision","etat":"actif","echelle":"unite","modeles":26,"poids_general":1.67,"difficulte":99.1,"pente":0.1132,"en_une_phrase":"Dessiner le plan en 2D d'un appartement à partir d'une vingtaine de photos : pièces, portes, tailles relatives.","notation":"Ressemblance entre le plan produit et le vrai, ramenée de 0 (hasard) à 1 (plan parfait) ; calcul automatique, sans IA correctrice.","limites":"Une cinquantaine d'appartements seulement. Les humains testés obtiennent environ 0,59 et le meilleur modèle 0,50.","mainteneur":"Andon Labs","url":"https://andonlabs.com/evals/blueprint-bench-2","verifie":true},"tache":{"id":"vision","nom":"Vision et multimodal","poids_general":5,"benchmarks_actifs":3},"modeles_mesures":26,"mesures":26,"classement":[{"rang":1,"modele":"gpt-6-astra","nom":"GPT-6 Astra","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-6-astra/","score_publie":0.4967462039045553,"score_0_1":0.4967,"niveau_suggere":99,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":2,"modele":"claude-fable-5-1","nom":"Claude Fable 5.1","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-fable-5-1/","score_publie":0.4186550976138828,"score_0_1":0.4187,"niveau_suggere":96.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":3,"modele":"claude-fable-5","nom":"Claude Fable 5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-fable-5/","score_publie":0.3861171366594359,"score_0_1":0.3861,"niveau_suggere":95,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":3,"modele":"gemini-3-8-flash","nom":"Gemini 3.8 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-8-flash/","score_publie":0.3861171366594359,"score_0_1":0.3861,"niveau_suggere":95,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":5,"modele":"gpt-5-5","nom":"GPT-5.5","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-5/","score_publie":0.3622559652928415,"score_0_1":0.3623,"niveau_suggere":94.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":6,"modele":"gpt-5-6-sol","nom":"GPT-5.6 Sol","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-6-sol/","score_publie":0.336225596529284,"score_0_1":0.3362,"niveau_suggere":93.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":6,"modele":"gemini-3-5-flash","nom":"Gemini 3.5 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-5-flash/","score_publie":0.336225596529284,"score_0_1":0.3362,"niveau_suggere":93.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":8,"modele":"grok-4-6","nom":"Grok 4.6","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-6/","score_publie":0.3318872017353577,"score_0_1":0.3319,"niveau_suggere":92.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":9,"modele":"gemini-3-6-flash","nom":"Gemini 3.6 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-6-flash/","score_publie":0.3123644251626898,"score_0_1":0.3124,"niveau_suggere":92.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"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":0.3080260303687636,"score_0_1":0.308,"niveau_suggere":92,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":11,"modele":"claude-opus-5","nom":"Claude Opus 5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-5/","score_publie":0.3036876355748373,"score_0_1":0.3037,"niveau_suggere":91.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":12,"modele":"kimi-k3","nom":"Kimi K3","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k3/","score_publie":0.2950108459869848,"score_0_1":0.295,"niveau_suggere":91.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":13,"modele":"grok-4-5","nom":"Grok 4.5","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-5/","score_publie":0.2733188720173536,"score_0_1":0.2733,"niveau_suggere":90.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":14,"modele":"gpt-5-4","nom":"GPT-5.4","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-4/","score_publie":0.2711496746203904,"score_0_1":0.2711,"niveau_suggere":90.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":15,"modele":"gemini-3-1-pro","nom":"Gemini 3.1 Pro","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-1-pro/","score_publie":0.2646420824295011,"score_0_1":0.2646,"niveau_suggere":90.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":16,"modele":"claude-sonnet-5","nom":"Claude Sonnet 5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-5/","score_publie":0.2494577006507592,"score_0_1":0.2495,"niveau_suggere":89.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":17,"modele":"claude-opus-4-7","nom":"Claude Opus 4.7","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-7/","score_publie":0.245119305856833,"score_0_1":0.2451,"niveau_suggere":89.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":18,"modele":"gpt-5-6-luna","nom":"GPT-5.6 Luna","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-5-6-luna/","score_publie":0.2255965292841648,"score_0_1":0.2256,"niveau_suggere":88.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":19,"modele":"claude-opus-4-8","nom":"Claude Opus 4.8","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-opus-4-8/","score_publie":0.1453362255965291,"score_0_1":0.1453,"niveau_suggere":83.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":20,"modele":"claude-sonnet-4-6","nom":"Claude Sonnet 4.6","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-sonnet-4-6/","score_publie":0.0672451193058566,"score_0_1":0.0672,"niveau_suggere":75.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":21,"modele":"kimi-k2-6","nom":"Kimi K2.6","editeur":"Moonshot","page":"https://quelleia.com/modeles/kimi-k2-6/","score_publie":0.0390455531453362,"score_0_1":0.039,"niveau_suggere":70.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":22,"modele":"grok-4-20","nom":"Grok 4.20","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-20/","score_publie":0,"score_0_1":0,"niveau_suggere":58.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":22,"modele":"gemini-3-flash","nom":"Gemini 3 Flash","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-3-flash/","score_publie":0,"score_0_1":0,"niveau_suggere":58.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":22,"modele":"grok-4-3-beta","nom":"Grok 4.3 Beta","editeur":"xAI","page":"https://quelleia.com/modeles/grok-4-3-beta/","score_publie":0,"score_0_1":0,"niveau_suggere":58.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":22,"modele":"claude-haiku-4-5","nom":"Claude Haiku 4.5","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-haiku-4-5/","score_publie":0,"score_0_1":0,"niveau_suggere":58.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"},{"rang":22,"modele":"gemini-robotics-er-1-6","nom":"Gemini Robotics-ER 1.6","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-robotics-er-1-6/","score_publie":0,"score_0_1":0,"niveau_suggere":58.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2"}]}