{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/cadeval/","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":"cadeval","nom":"CadEval","tache":"vision","etat":"archive","echelle":"unite","modeles":15,"poids_general":0,"difficulte":66.5,"pente":0.0672,"en_une_phrase":"Écrire le code OpenSCAD d'une pièce en 3D décrite en texte, de la plus simple à celle qui enchaîne cinq opérations.","notation":"Part de pièces dont le rendu 3D colle au modèle de référence : volume, dimensions et écart de surface inférieur à 1 mm.","limites":"Petit jeu de tâches tenu par une seule personne et figé en avril 2025. L'auteur estime qu'environ 5 % des pièces justes sont refusées à tort.","mainteneur":"Will Patrick","url":"https://willpatrick.xyz/technology/2025/04/23/teaching-llms-how-to-solid-model.html","verifie":true},"tache":{"id":"vision","nom":"Vision et multimodal","poids_general":5,"benchmarks_actifs":3},"modeles_mesures":15,"mesures":15,"classement":[{"rang":1,"modele":"o3","nom":"o3","editeur":"OpenAI","page":"https://quelleia.com/modeles/o3/","score_publie":0.74,"score_0_1":0.74,"niveau_suggere":82.1,"reflexion":"moyenne","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":2,"modele":"gemini-2-5-pro-mar-2025","nom":"Gemini 2.5 Pro (Mar 2025)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-5-pro-mar-2025/","score_publie":0.64,"score_0_1":0.64,"niveau_suggere":75.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"o4-mini","nom":"o4-mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/o4-mini/","score_publie":0.62,"score_0_1":0.62,"niveau_suggere":73.8,"reflexion":"moyenne","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"o1","nom":"o1","editeur":"OpenAI","page":"https://quelleia.com/modeles/o1/","score_publie":0.56,"score_0_1":0.56,"niveau_suggere":70.1,"reflexion":"moyenne","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"claude-3-7-sonnet","nom":"Claude 3.7 Sonnet","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-7-sonnet/","score_publie":0.54,"score_0_1":0.54,"niveau_suggere":68.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"o3-mini","nom":"o3-mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/o3-mini/","score_publie":0.54,"score_0_1":0.54,"niveau_suggere":68.9,"reflexion":"moyenne","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":7,"modele":"claude-3-5-sonnet-october-2024","nom":"Claude 3.5 Sonnet (October 2024)","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-5-sonnet-october-2024/","score_publie":0.48,"score_0_1":0.48,"niveau_suggere":65.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"gpt-4-1","nom":"GPT-4.1","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-1/","score_publie":0.42,"score_0_1":0.42,"niveau_suggere":61.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":9,"modele":"gemini-1-5-pro-sept-2024","nom":"Gemini 1.5 Pro (Sept 2024)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-1-5-pro-sept-2024/","score_publie":0.34,"score_0_1":0.34,"niveau_suggere":56.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":10,"modele":"claude-3-5-haiku","nom":"Claude 3.5 Haiku","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-5-haiku/","score_publie":0.32,"score_0_1":0.32,"niveau_suggere":55.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"gemini-2-0-flash-feb-2025","nom":"Gemini 2.0 Flash (Feb 2025)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-2-0-flash-feb-2025/","score_publie":0.3,"score_0_1":0.3,"niveau_suggere":53.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":12,"modele":"gpt-4o-aug-2024","nom":"GPT-4o (Aug 2024)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4o-aug-2024/","score_publie":0.26,"score_0_1":0.26,"niveau_suggere":50.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":13,"modele":"ml-elephant","nom":"ml-elephant","editeur":null,"page":"https://quelleia.com/modeles/ml-elephant/","score_publie":0.2,"score_0_1":0.2,"niveau_suggere":45.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"gpt-4-1-mini","nom":"GPT-4.1 mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-1-mini/","score_publie":0.16,"score_0_1":0.16,"niveau_suggere":41.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":15,"modele":"claude-3-haiku","nom":"Claude 3 Haiku","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-3-haiku/","score_publie":0.12,"score_0_1":0.12,"niveau_suggere":36.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"}]}