{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/gsm8k/","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":"gsm8k","nom":"GSM8K","tache":"maths","etat":"archive","echelle":"unite","modeles":82,"poids_general":0,"difficulte":2.7,"pente":0.0479,"en_une_phrase":"Des problèmes d'arithmétique de niveau école et collège, rédigés en langage courant, à résoudre en quelques étapes de calcul.","notation":"Part de réponses numériques exactement justes.","limites":"Saturé et très présent dans les données d'entraînement. Il ne sert plus qu'à situer d'anciens modèles.","mainteneur":"OpenAI (Cobbe et al., 2021)","url":"https://github.com/openai/grade-school-math","verifie":true},"tache":{"id":"maths","nom":"Mathématiques","poids_general":10,"benchmarks_actifs":8},"modeles_mesures":82,"mesures":170,"classement":[{"rang":1,"modele":"deepseek-coder-v2-236b","nom":"DeepSeek-Coder-V2 236B","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-coder-v2-236b/","score_publie":0.945,"score_0_1":0.945,"niveau_suggere":62.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":2,"modele":"qwen2-5-coder-14b-instruct","nom":"Qwen2.5-Coder-14B-Instruct","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-14b-instruct/","score_publie":0.942,"score_0_1":0.942,"niveau_suggere":60.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"qwen2-5-coder-32b-instruct","nom":"Qwen2.5-Coder-32B-Instruct","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-32b-instruct/","score_publie":0.93,"score_0_1":0.93,"niveau_suggere":56.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"gpt-4-mar-2023","nom":"GPT-4 (Mar 2023)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-mar-2023/","score_publie":0.92,"score_0_1":0.92,"niveau_suggere":53.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"gpt-4o-mini","nom":"GPT-4o mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4o-mini/","score_publie":0.913,"score_0_1":0.913,"niveau_suggere":51.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":6,"modele":"qwen2-5-coder-32b","nom":"Qwen2.5-Coder-32B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-32b/","score_publie":0.911,"score_0_1":0.911,"niveau_suggere":51.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":7,"modele":"gpt-4-jun-2023","nom":"GPT-4 (Jun 2023)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-jun-2023/","score_publie":0.8999,"score_0_1":0.8999,"niveau_suggere":48.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"phi-3-5-moe","nom":"Phi-3.5-MoE","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-5-moe/","score_publie":0.887,"score_0_1":0.887,"niveau_suggere":45.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"qwen2-5-coder-14b","nom":"Qwen2.5-Coder-14B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-14b/","score_publie":0.887,"score_0_1":0.887,"niveau_suggere":45.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":10,"modele":"deepseek-coder-v2-lite-instruct","nom":"DeepSeek-Coder-V2-Lite-Instruct","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-coder-v2-lite-instruct/","score_publie":0.876,"score_0_1":0.876,"niveau_suggere":43.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"claude-instant","nom":"Claude Instant","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-instant/","score_publie":0.867,"score_0_1":0.867,"niveau_suggere":41.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"qwen2-5-coder-7b","nom":"Qwen2.5-Coder (7B)","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-7b/","score_publie":0.867,"score_0_1":0.867,"niveau_suggere":41.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":13,"modele":"phi-3-5-mini","nom":"Phi-3.5-mini","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-5-mini/","score_publie":0.862,"score_0_1":0.862,"niveau_suggere":40.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"gemma-2-9b","nom":"Gemma 2 9B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-2-9b/","score_publie":0.849,"score_0_1":0.849,"niveau_suggere":38.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":15,"modele":"mistral-nemo","nom":"Mistral NeMo","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-nemo/","score_publie":0.842,"score_0_1":0.842,"niveau_suggere":37.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"gemini-1-5-flash-may-2024","nom":"Gemini 1.5 Flash (May 2024)","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemini-1-5-flash-may-2024/","score_publie":0.824,"score_0_1":0.824,"niveau_suggere":34.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"llama-3-1-8b","nom":"Llama 3.1-8B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-1-8b/","score_publie":0.824,"score_0_1":0.824,"niveau_suggere":34.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"qwen2-5-coder-3b-instruct","nom":"Qwen2.5-Coder-3B-Instruct","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-3b-instruct/","score_publie":0.807,"score_0_1":0.807,"niveau_suggere":32.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":19,"modele":"davinci-003","nom":"davinci-003","editeur":"OpenAI","page":"https://quelleia.com/modeles/davinci-003/","score_publie":0.782,"score_0_1":0.782,"niveau_suggere":29.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":20,"modele":"yi-34b","nom":"Yi-34B","editeur":"01.AI","page":"https://quelleia.com/modeles/yi-34b/","score_publie":0.76,"score_0_1":0.76,"niveau_suggere":26.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":21,"modele":"qwen2-5-coder-3b","nom":"Qwen2.5-Coder-3B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-3b/","score_publie":0.757,"score_0_1":0.757,"niveau_suggere":26.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":22,"modele":"mixtral-8x7b","nom":"Mixtral 8x7B","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mixtral-8x7b/","score_publie":0.744,"score_0_1":0.744,"niveau_suggere":25,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"stable-beluga-2","nom":"Stable Beluga 2","editeur":"Stability AI","page":"https://quelleia.com/modeles/stable-beluga-2/","score_publie":0.696,"score_0_1":0.696,"niveau_suggere":20,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"llama-2-70b","nom":"Llama 2-70B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-70b/","score_publie":0.696,"score_0_1":0.696,"niveau_suggere":20,"reflexion":"inconnue","harnais":null,"configurations_mesurees":8,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":25,"modele":"deepseek-coder-v2-lite-base","nom":"DeepSeek-Coder-V2-Lite-Base","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-coder-v2-lite-base/","score_publie":0.671,"score_0_1":0.671,"niveau_suggere":17.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":26,"modele":"qwen2-5-coder-1-5b","nom":"Qwen2.5-Coder (1.5B)","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-1-5b/","score_publie":0.658,"score_0_1":0.658,"niveau_suggere":16.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":27,"modele":"internlm-20b","nom":"internlm-20b","editeur":"Shanghai AI Laboratory","page":"https://quelleia.com/modeles/internlm-20b/","score_publie":0.629,"score_0_1":0.629,"niveau_suggere":13.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":28,"modele":"qwen-14b","nom":"Qwen-14B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-14b/","score_publie":0.613,"score_0_1":0.613,"niveau_suggere":12.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":29,"modele":"gpt-3-5-turbo-jun-2023","nom":"GPT-3.5 Turbo (Jun 2023)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-5-turbo-jun-2023/","score_publie":0.5777,"score_0_1":0.5777,"niveau_suggere":9.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":30,"modele":"starcoder-2-15b","nom":"StarCoder 2 15B","editeur":"Hugging Face","page":"https://quelleia.com/modeles/starcoder-2-15b/","score_publie":0.577,"score_0_1":0.577,"niveau_suggere":9.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":31,"modele":"davinci-002","nom":"davinci-002","editeur":"OpenAI","page":"https://quelleia.com/modeles/davinci-002/","score_publie":0.568,"score_0_1":0.568,"niveau_suggere":8.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":32,"modele":"palm-540b","nom":"PaLM (540B)","editeur":"Google Research","page":"https://quelleia.com/modeles/palm-540b/","score_publie":0.565,"score_0_1":0.565,"niveau_suggere":8.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":33,"modele":"falcon-180b","nom":"Falcon-180B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-180b/","score_publie":0.544,"score_0_1":0.544,"niveau_suggere":6.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":33,"modele":"llama-65b","nom":"LLaMA-65B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-65b/","score_publie":0.544,"score_0_1":0.544,"niveau_suggere":6.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":33,"modele":"mistral-7b-v0-1","nom":"Mistral 7B v0.1","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-7b-v0-1/","score_publie":0.544,"score_0_1":0.544,"niveau_suggere":6.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":36,"modele":"falcon-2-11b","nom":"Falcon 2 11B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-2-11b/","score_publie":0.5383,"score_0_1":0.5383,"niveau_suggere":5.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":37,"modele":"baichuan2-13b","nom":"Baichuan2-13B","editeur":"Baichuan","page":"https://quelleia.com/modeles/baichuan2-13b/","score_publie":0.528,"score_0_1":0.528,"niveau_suggere":5.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":38,"modele":"qwen-7b","nom":"Qwen-7B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-7b/","score_publie":0.517,"score_0_1":0.517,"niveau_suggere":4.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":39,"modele":"gemma-7b","nom":"Gemma 7B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-7b/","score_publie":0.464,"score_0_1":0.464,"niveau_suggere":-0.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":40,"modele":"nemotron-4-15b","nom":"Nemotron-4 15B","editeur":"NVIDIA","page":"https://quelleia.com/modeles/nemotron-4-15b/","score_publie":0.46,"score_0_1":0.46,"niveau_suggere":-0.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":41,"modele":"baichuan2-13b-chat","nom":"Baichuan2-13B-Chat","editeur":"Baichuan AI","page":"https://quelleia.com/modeles/baichuan2-13b-chat/","score_publie":0.457,"score_0_1":0.457,"niveau_suggere":-0.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":42,"modele":"yi-6b","nom":"Yi 6B","editeur":"01.AI","page":"https://quelleia.com/modeles/yi-6b/","score_publie":0.449,"score_0_1":0.449,"niveau_suggere":-1.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":43,"modele":"llama-33b","nom":"LLaMA-33B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-33b/","score_publie":0.441,"score_0_1":0.441,"niveau_suggere":-2.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":44,"modele":"llama-2-34b","nom":"Llama 2-34B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-34b/","score_publie":0.422,"score_0_1":0.422,"niveau_suggere":-3.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":45,"modele":"intellect-1","nom":"INTELLECT-1","editeur":"Prime Intellect","page":"https://quelleia.com/modeles/intellect-1/","score_publie":0.3858,"score_0_1":0.3858,"niveau_suggere":-7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":46,"modele":"codeqwen1-5-7b","nom":"CodeQwen1.5-7B","editeur":"Alibaba","page":"https://quelleia.com/modeles/codeqwen1-5-7b/","score_publie":0.377,"score_0_1":0.377,"niveau_suggere":-7.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":47,"modele":"llama-2-13b","nom":"Llama 2-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-13b/","score_publie":0.369,"score_0_1":0.369,"niveau_suggere":-8.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":9,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":48,"modele":"mistral-7b-v0-2","nom":"Mistral 7B v0.2","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-7b-v0-2/","score_publie":0.354,"score_0_1":0.354,"niveau_suggere":-9.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":48,"modele":"deepseek-coder-33b","nom":"DeepSeek Coder 33B","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-coder-33b/","score_publie":0.354,"score_0_1":0.354,"niveau_suggere":-9.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":50,"modele":"qwen2-5-coder-0-5b","nom":"Qwen2.5-Coder-0.5B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-0-5b/","score_publie":0.345,"score_0_1":0.345,"niveau_suggere":-10.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":51,"modele":"mpt-30b","nom":"MPT-30B","editeur":"MosaicML","page":"https://quelleia.com/modeles/mpt-30b/","score_publie":0.344,"score_0_1":0.344,"niveau_suggere":-10.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":52,"modele":"falcon-40b","nom":"Falcon-40B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-40b/","score_publie":0.338,"score_0_1":0.338,"niveau_suggere":-11.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":53,"modele":"palm-62b","nom":"PaLM 62B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-62b/","score_publie":0.33,"score_0_1":0.33,"niveau_suggere":-12.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":54,"modele":"starcoder-2-7b","nom":"StarCoder 2 7B","editeur":"Hugging Face","page":"https://quelleia.com/modeles/starcoder-2-7b/","score_publie":0.327,"score_0_1":0.327,"niveau_suggere":-12.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":55,"modele":"chatglm2-6b","nom":"chatglm2-6b","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/chatglm2-6b/","score_publie":0.324,"score_0_1":0.324,"niveau_suggere":-12.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":56,"modele":"internlm-7b","nom":"internlm-7b","editeur":"Shanghai AI Laboratory","page":"https://quelleia.com/modeles/internlm-7b/","score_publie":0.312,"score_0_1":0.312,"niveau_suggere":-13.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":57,"modele":"vicuna-13b-v1-1","nom":"vicuna-13b-v1.1","editeur":null,"page":"https://quelleia.com/modeles/vicuna-13b-v1-1/","score_publie":0.2813,"score_0_1":0.2813,"niveau_suggere":-16.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":58,"modele":"baichuan-1-13b","nom":"Baichuan 1-13B","editeur":"Baichuan","page":"https://quelleia.com/modeles/baichuan-1-13b/","score_publie":0.268,"score_0_1":0.268,"niveau_suggere":-18.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":59,"modele":"baichuan-2-7b","nom":"Baichuan 2-7B","editeur":"Baichuan","page":"https://quelleia.com/modeles/baichuan-2-7b/","score_publie":0.246,"score_0_1":0.246,"niveau_suggere":-20.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":60,"modele":"vicuna-13b-v1-3","nom":"Vicuna-13B-v1.3","editeur":"Large Model Systems Organization","page":"https://quelleia.com/modeles/vicuna-13b-v1-3/","score_publie":0.226,"score_0_1":0.226,"niveau_suggere":-23,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":61,"modele":"starcoder-2-3b","nom":"StarCoder 2 3B","editeur":"Hugging Face","page":"https://quelleia.com/modeles/starcoder-2-3b/","score_publie":0.216,"score_0_1":0.216,"niveau_suggere":-24.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":62,"modele":"deepseek-coder-6-7b","nom":"DeepSeek Coder 6.7B","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-coder-6-7b/","score_publie":0.213,"score_0_1":0.213,"niveau_suggere":-24.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":63,"modele":"qwen-1-8b","nom":"Qwen-1_8B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-1-8b/","score_publie":0.212,"score_0_1":0.212,"niveau_suggere":-24.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":64,"modele":"llama-13b","nom":"LLaMA-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-13b/","score_publie":0.2055,"score_0_1":0.2055,"niveau_suggere":-25.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":65,"modele":"gemma-2b","nom":"Gemma 2B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-2b/","score_publie":0.177,"score_0_1":0.177,"niveau_suggere":-29.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":66,"modele":"llama-2-7b","nom":"Llama 2-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-7b/","score_publie":0.167,"score_0_1":0.167,"niveau_suggere":-30.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":7,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":67,"modele":"internlm-chat-20b","nom":"internlm-chat-20b","editeur":"Shanghai AI Laboratory","page":"https://quelleia.com/modeles/internlm-chat-20b/","score_publie":0.157,"score_0_1":0.157,"niveau_suggere":-32.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":68,"modele":"llama-7b","nom":"LLaMA-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-7b/","score_publie":0.11,"score_0_1":0.11,"niveau_suggere":-40.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":6,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":69,"modele":"bloom-176b","nom":"BLOOM-176B","editeur":"Hugging Face","page":"https://quelleia.com/modeles/bloom-176b/","score_publie":0.095,"score_0_1":0.095,"niveau_suggere":-44.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":70,"modele":"baichuan1-7b","nom":"Baichuan1-7B","editeur":"Baichuan","page":"https://quelleia.com/modeles/baichuan1-7b/","score_publie":0.092,"score_0_1":0.092,"niveau_suggere":-45.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":71,"modele":"mpt-7b","nom":"MPT-7B","editeur":"MosaicML","page":"https://quelleia.com/modeles/mpt-7b/","score_publie":0.091,"score_0_1":0.091,"niveau_suggere":-45.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":72,"modele":"gpt-3-175b-davinci","nom":"GPT-3 175B (davinci)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-175b-davinci/","score_publie":0.09,"score_0_1":0.09,"niveau_suggere":-45.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":73,"modele":"falcon-7b","nom":"Falcon-7B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-7b/","score_publie":0.068,"score_0_1":0.068,"niveau_suggere":-51.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":6,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":74,"modele":"deepseek-coder-1-3b","nom":"DeepSeek Coder 1.3B","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-coder-1-3b/","score_publie":0.044,"score_0_1":0.044,"niveau_suggere":-61.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":75,"modele":"opt-175b","nom":"OPT-175B","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-175b/","score_publie":0.04,"score_0_1":0.04,"niveau_suggere":-63.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":76,"modele":"opt-66b","nom":"OPT-66B","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-66b/","score_publie":0.018,"score_0_1":0.018,"niveau_suggere":-80.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":77,"modele":"gpt-3-6-7b","nom":"GPT-3 6.7B","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-6-7b/","score_publie":0.016,"score_0_1":0.016,"niveau_suggere":-83.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":78,"modele":"gpt-3-xl-babbage","nom":"GPT-3 XL (babbage)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-xl-babbage/","score_publie":0.007,"score_0_1":0.007,"niveau_suggere":-93.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":79,"modele":"gpt-3-medium","nom":"GPT-3 Medium","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-medium/","score_publie":0.006,"score_0_1":0.006,"niveau_suggere":-93.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":79,"modele":"instructgpt-6b","nom":"InstructGPT 6B","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-6b/","score_publie":0.006,"score_0_1":0.006,"niveau_suggere":-93.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":81,"modele":"instructgpt-350m","nom":"InstructGPT 350M","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-350m/","score_publie":0.004,"score_0_1":0.004,"niveau_suggere":-93.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":82,"modele":"instructgpt-1-3b","nom":"InstructGPT 1.3B","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-1-3b/","score_publie":0,"score_0_1":0,"niveau_suggere":-93.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"}]}