{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/openbookqa/","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":"openbookqa","nom":"OpenBookQA","tache":"autre","etat":"archive","echelle":"unite","modeles":42,"poids_general":0,"difficulte":1.2,"pente":0.0336,"en_une_phrase":"Des questions de sciences élémentaires qui demandent de combiner un fait du cours avec du bon sens.","notation":"Part de bonnes réponses à quatre choix ; le hasard donne 25 %.","limites":"Test de 2018, aujourd'hui saturé. Les scores viennent d'articles aux réglages variés.","mainteneur":"Allen Institute for AI","url":"https://allenai.org/data/open-book-qa","verifie":true},"tache":{"id":"autre","nom":"Tests historiques","poids_general":0,"benchmarks_actifs":0},"modeles_mesures":42,"mesures":70,"classement":[{"rang":1,"modele":"phi-3-small-7-4b","nom":"phi-3-small 7.4B","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-small-7-4b/","score_publie":0.88,"score_0_1":0.84,"niveau_suggere":50.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":1,"modele":"phi-3-mini-3-8b","nom":"phi-3-mini 3.8B","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-mini-3-8b/","score_publie":0.88,"score_0_1":0.84,"niveau_suggere":50.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"phi-3-medium-14b","nom":"phi-3-medium 14B","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-medium-14b/","score_publie":0.874,"score_0_1":0.832,"niveau_suggere":48.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"gpt-3-5-turbo-nov-2023","nom":"GPT-3.5 Turbo (Nov 2023)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-5-turbo-nov-2023/","score_publie":0.86,"score_0_1":0.8133,"niveau_suggere":44.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"mixtral-8x7b","nom":"Mixtral 8x7B","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mixtral-8x7b/","score_publie":0.858,"score_0_1":0.8107,"niveau_suggere":44.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":6,"modele":"llama-3-8b","nom":"Llama 3-8B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-8b/","score_publie":0.826,"score_0_1":0.768,"niveau_suggere":36.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":7,"modele":"mistral-7b-v0-1","nom":"Mistral 7B v0.1","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-7b-v0-1/","score_publie":0.798,"score_0_1":0.7307,"niveau_suggere":30.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"gemma-7b","nom":"Gemma 7B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-7b/","score_publie":0.786,"score_0_1":0.7147,"niveau_suggere":28.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":9,"modele":"phi-2","nom":"Phi-2","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-2/","score_publie":0.736,"score_0_1":0.648,"niveau_suggere":19.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":10,"modele":"palm-540b","nom":"PaLM (540B)","editeur":"Google Research","page":"https://quelleia.com/modeles/palm-540b/","score_publie":0.68,"score_0_1":0.5733,"niveau_suggere":10,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"instructgpt-175b","nom":"InstructGPT 175B","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-175b/","score_publie":0.654,"score_0_1":0.5387,"niveau_suggere":5.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":7,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":12,"modele":"falcon-180b","nom":"Falcon-180B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-180b/","score_publie":0.642,"score_0_1":0.5227,"niveau_suggere":3.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":13,"modele":"glam","nom":"GLaM","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/glam/","score_publie":0.63,"score_0_1":0.5067,"niveau_suggere":2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"llama-2-70b","nom":"Llama 2-70B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-70b/","score_publie":0.602,"score_0_1":0.4693,"niveau_suggere":-2.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"llama-65b","nom":"LLaMA-65B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-65b/","score_publie":0.602,"score_0_1":0.4693,"niveau_suggere":-2.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"llama-33b","nom":"LLaMA-33B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-33b/","score_publie":0.586,"score_0_1":0.448,"niveau_suggere":-5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"llama-2-7b","nom":"Llama 2-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-7b/","score_publie":0.586,"score_0_1":0.448,"niveau_suggere":-5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"llama-2-34b","nom":"Llama 2-34B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-34b/","score_publie":0.582,"score_0_1":0.4427,"niveau_suggere":-5.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":19,"modele":"palm-2-m","nom":"PaLM 2-M","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-m/","score_publie":0.574,"score_0_1":0.432,"niveau_suggere":-6.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":20,"modele":"llama-7b","nom":"LLaMA-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-7b/","score_publie":0.572,"score_0_1":0.4293,"niveau_suggere":-7.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":21,"modele":"llama-2-13b","nom":"Llama 2-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-13b/","score_publie":0.57,"score_0_1":0.4267,"niveau_suggere":-7.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":22,"modele":"falcon-40b","nom":"Falcon-40B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-40b/","score_publie":0.566,"score_0_1":0.4213,"niveau_suggere":-8.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"llama-13b","nom":"LLaMA-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-13b/","score_publie":0.564,"score_0_1":0.4187,"niveau_suggere":-8.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":24,"modele":"palm-2-s","nom":"PaLM 2-S","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-s/","score_publie":0.562,"score_0_1":0.416,"niveau_suggere":-8.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":25,"modele":"mpt-30b","nom":"MPT-30B","editeur":"MosaicML","page":"https://quelleia.com/modeles/mpt-30b/","score_publie":0.52,"score_0_1":0.36,"niveau_suggere":-15.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":26,"modele":"falcon-7b","nom":"Falcon-7B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-7b/","score_publie":0.516,"score_0_1":0.3547,"niveau_suggere":-16.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":27,"modele":"mpt-7b","nom":"MPT-7B","editeur":"MosaicML","page":"https://quelleia.com/modeles/mpt-7b/","score_publie":0.514,"score_0_1":0.352,"niveau_suggere":-16.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":28,"modele":"palm-62b","nom":"PaLM 62B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-62b/","score_publie":0.504,"score_0_1":0.3387,"niveau_suggere":-18.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":29,"modele":"xgen-7b","nom":"XGen-7B","editeur":"Salesforce","page":"https://quelleia.com/modeles/xgen-7b/","score_publie":0.402,"score_0_1":0.2027,"niveau_suggere":-39.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":30,"modele":"redpajama-incite-7b-base","nom":"RedPajama-INCITE-7B-Base","editeur":null,"page":"https://quelleia.com/modeles/redpajama-incite-7b-base/","score_publie":0.4,"score_0_1":0.2,"niveau_suggere":-40,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":31,"modele":"opt-13b","nom":"opt-13b","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-13b/","score_publie":0.398,"score_0_1":0.1973,"niveau_suggere":-40.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":32,"modele":"dolly-2-0-12b","nom":"Dolly 2.0-12b","editeur":"Databricks","page":"https://quelleia.com/modeles/dolly-2-0-12b/","score_publie":0.392,"score_0_1":0.1893,"niveau_suggere":-42,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":33,"modele":"open-llama-7b","nom":"open_llama_7b","editeur":null,"page":"https://quelleia.com/modeles/open-llama-7b/","score_publie":0.39,"score_0_1":0.1867,"niveau_suggere":-42.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":34,"modele":"gpt-neox-20b","nom":"GPT-NeoX-20B","editeur":"EleutherAI","page":"https://quelleia.com/modeles/gpt-neox-20b/","score_publie":0.388,"score_0_1":0.184,"niveau_suggere":-43.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":35,"modele":"gpt-j-6b","nom":"GPT-J-6B","editeur":"EleutherAI","page":"https://quelleia.com/modeles/gpt-j-6b/","score_publie":0.382,"score_0_1":0.176,"niveau_suggere":-44.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":36,"modele":"phi-1-5","nom":"Phi-1.5","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-1-5/","score_publie":0.372,"score_0_1":0.1627,"niveau_suggere":-47.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":37,"modele":"cerebras-gpt-13b","nom":"Cerebras-GPT-13B","editeur":"Cerebras Systems","page":"https://quelleia.com/modeles/cerebras-gpt-13b/","score_publie":0.358,"score_0_1":0.144,"niveau_suggere":-51.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":38,"modele":"vicuna-13b-v1-1","nom":"vicuna-13b-v1.1","editeur":null,"page":"https://quelleia.com/modeles/vicuna-13b-v1-1/","score_publie":0.33,"score_0_1":0.1067,"niveau_suggere":-62,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":39,"modele":"stablelm-tuned-alpha-7b","nom":"stablelm-tuned-alpha-7b","editeur":"Stability AI","page":"https://quelleia.com/modeles/stablelm-tuned-alpha-7b/","score_publie":0.324,"score_0_1":0.0987,"niveau_suggere":-64.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":40,"modele":"opt-1-3b","nom":"OPT-1.3B","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-1-3b/","score_publie":0.24,"score_0_1":0,"niveau_suggere":-135.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":41,"modele":"gpt-neo-2-7b","nom":"GPT-Neo-2.7B","editeur":"EleutherAI","page":"https://quelleia.com/modeles/gpt-neo-2-7b/","score_publie":0.232,"score_0_1":0,"niveau_suggere":-135.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":42,"modele":"gpt-2-1-5b","nom":"GPT-2 (1.5B)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-2-1-5b/","score_publie":0.224,"score_0_1":0,"niveau_suggere":-135.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"}]}