{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/arc_ai2/","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":"arc_ai2","nom":"ARC (AI2 Reasoning Challenge)","tache":"autre","etat":"archive","echelle":"unite","modeles":76,"poids_general":0,"difficulte":2,"pente":0.0385,"en_une_phrase":"Des questions de sciences de niveau école et collège, à choix multiples, choisies pour résister à une simple recherche de mots-clés.","notation":"Part de bonnes réponses sur la partie difficile du jeu (Challenge) ; le hasard donne 25 %.","limites":"Test de 2018, saturé par les modèles récents. À ne pas confondre avec ARC-AGI, qui porte sur des puzzles de grilles.","mainteneur":"Allen Institute for AI","url":"https://allenai.org/data/arc","verifie":true},"tache":{"id":"autre","nom":"Tests historiques","poids_general":0,"benchmarks_actifs":0},"modeles_mesures":76,"mesures":134,"classement":[{"rang":1,"modele":"deepseek-v3","nom":"DeepSeek-V3","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v3/","score_publie":0.953,"score_0_1":0.9373,"niveau_suggere":72.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":1,"modele":"llama-3-1-405b","nom":"Llama 3.1-405B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-1-405b/","score_publie":0.953,"score_0_1":0.9373,"niveau_suggere":72.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"qwen2-5-72b","nom":"Qwen2.5-72B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-72b/","score_publie":0.945,"score_0_1":0.9267,"niveau_suggere":67.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"deepseek-v2-moe-236b-may-2024","nom":"DeepSeek-V2 (MoE-236B, May 2024)","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v2-moe-236b-may-2024/","score_publie":0.922,"score_0_1":0.896,"niveau_suggere":57.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"phi-3-medium-14b","nom":"phi-3-medium 14B","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-medium-14b/","score_publie":0.916,"score_0_1":0.888,"niveau_suggere":55.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":6,"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":0.907,"score_0_1":0.876,"niveau_suggere":52.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":7,"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":0.874,"score_0_1":0.832,"niveau_suggere":43.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"mixtral-8x7b","nom":"Mixtral 8x7B","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mixtral-8x7b/","score_publie":0.873,"score_0_1":0.8307,"niveau_suggere":43.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":9,"modele":"claude-instant","nom":"Claude Instant","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-instant/","score_publie":0.863,"score_0_1":0.8173,"niveau_suggere":40.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":10,"modele":"stable-beluga-2","nom":"Stable Beluga 2","editeur":"Stability AI","page":"https://quelleia.com/modeles/stable-beluga-2/","score_publie":0.861,"score_0_1":0.8147,"niveau_suggere":40.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"davinci-002","nom":"davinci-002","editeur":"OpenAI","page":"https://quelleia.com/modeles/davinci-002/","score_publie":0.852,"score_0_1":0.8027,"niveau_suggere":38.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"palm-540b","nom":"PaLM (540B)","editeur":"Google Research","page":"https://quelleia.com/modeles/palm-540b/","score_publie":0.852,"score_0_1":0.8027,"niveau_suggere":38.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":13,"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":0.849,"score_0_1":0.7987,"niveau_suggere":37.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"qwen-14b","nom":"Qwen-14B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-14b/","score_publie":0.844,"score_0_1":0.792,"niveau_suggere":36.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":15,"modele":"llama-3-8b","nom":"Llama 3-8B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-8b/","score_publie":0.828,"score_0_1":0.7707,"niveau_suggere":33.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"internlm-20b","nom":"internlm-20b","editeur":"Shanghai AI Laboratory","page":"https://quelleia.com/modeles/internlm-20b/","score_publie":0.817,"score_0_1":0.756,"niveau_suggere":31.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":17,"modele":"mistral-7b-v0-1","nom":"Mistral 7B v0.1","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-7b-v0-1/","score_publie":0.786,"score_0_1":0.7147,"niveau_suggere":25.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"llama-2-70b","nom":"Llama 2-70B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-70b/","score_publie":0.783,"score_0_1":0.7107,"niveau_suggere":25.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"gemma-7b","nom":"Gemma 7B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-7b/","score_publie":0.783,"score_0_1":0.7107,"niveau_suggere":25.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":20,"modele":"phi-2","nom":"Phi-2","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-2/","score_publie":0.759,"score_0_1":0.6787,"niveau_suggere":21.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":21,"modele":"qwen-7b","nom":"Qwen-7B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-7b/","score_publie":0.753,"score_0_1":0.6707,"niveau_suggere":20.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":22,"modele":"qwen2-5-coder-32b","nom":"Qwen2.5-Coder-32B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-32b/","score_publie":0.705,"score_0_1":0.6067,"niveau_suggere":13.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"llama-65b","nom":"LLaMA-65B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-65b/","score_publie":0.695,"score_0_1":0.5933,"niveau_suggere":11.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"internlm-7b","nom":"internlm-7b","editeur":"Shanghai AI Laboratory","page":"https://quelleia.com/modeles/internlm-7b/","score_publie":0.695,"score_0_1":0.5933,"niveau_suggere":11.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":25,"modele":"palm-2-l","nom":"PaLM 2-L","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-l/","score_publie":0.692,"score_0_1":0.5893,"niveau_suggere":11.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":26,"modele":"falcon-180b","nom":"Falcon-180B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-180b/","score_publie":0.678,"score_0_1":0.5707,"niveau_suggere":9.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":27,"modele":"llama-33b","nom":"LLaMA-33B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-33b/","score_publie":0.675,"score_0_1":0.5667,"niveau_suggere":8.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":28,"modele":"qwen2-5-coder-14b","nom":"Qwen2.5-Coder-14B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-14b/","score_publie":0.66,"score_0_1":0.5467,"niveau_suggere":6.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":29,"modele":"palm-2-m","nom":"PaLM 2-M","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-m/","score_publie":0.649,"score_0_1":0.532,"niveau_suggere":5.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":30,"modele":"deepseek-coder-v2-236b","nom":"DeepSeek-Coder-V2 236B","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-coder-v2-236b/","score_publie":0.643,"score_0_1":0.524,"niveau_suggere":4.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":31,"modele":"falcon-40b","nom":"Falcon-40B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-40b/","score_publie":0.6186,"score_0_1":0.4915,"niveau_suggere":1.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":32,"modele":"chatglm2-6b","nom":"chatglm2-6b","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/chatglm2-6b/","score_publie":0.61,"score_0_1":0.48,"niveau_suggere":-0.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":33,"modele":"qwen2-5-coder-7b","nom":"Qwen2.5-Coder (7B)","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-7b/","score_publie":0.609,"score_0_1":0.4787,"niveau_suggere":-0.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":34,"modele":"llama-2-13b","nom":"Llama 2-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-13b/","score_publie":0.603,"score_0_1":0.4707,"niveau_suggere":-1.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":6,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":35,"modele":"palm-2-s","nom":"PaLM 2-S","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-s/","score_publie":0.596,"score_0_1":0.4613,"niveau_suggere":-2.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":36,"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":0.573,"score_0_1":0.4307,"niveau_suggere":-5.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":37,"modele":"yi-9b","nom":"Yi-9B","editeur":"01.AI","page":"https://quelleia.com/modeles/yi-9b/","score_publie":0.556,"score_0_1":0.408,"niveau_suggere":-7.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":38,"modele":"nemotron-4-15b","nom":"Nemotron-4 15B","editeur":"NVIDIA","page":"https://quelleia.com/modeles/nemotron-4-15b/","score_publie":0.555,"score_0_1":0.4067,"niveau_suggere":-7.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":39,"modele":"intellect-1","nom":"INTELLECT-1","editeur":"Prime Intellect","page":"https://quelleia.com/modeles/intellect-1/","score_publie":0.5452,"score_0_1":0.3936,"niveau_suggere":-9.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":40,"modele":"llama-2-34b","nom":"Llama 2-34B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-34b/","score_publie":0.545,"score_0_1":0.3933,"niveau_suggere":-9.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":41,"modele":"instructgpt-175b","nom":"InstructGPT 175B","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-175b/","score_publie":0.532,"score_0_1":0.376,"niveau_suggere":-11.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":41,"modele":"qwen-1-8b","nom":"Qwen-1_8B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-1-8b/","score_publie":0.532,"score_0_1":0.376,"niveau_suggere":-11.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":43,"modele":"qwen2-5-coder-3b","nom":"Qwen2.5-Coder-3B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-3b/","score_publie":0.529,"score_0_1":0.372,"niveau_suggere":-11.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":44,"modele":"llama-13b","nom":"LLaMA-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-13b/","score_publie":0.527,"score_0_1":0.3693,"niveau_suggere":-11.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":45,"modele":"palm-62b","nom":"PaLM 62B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-62b/","score_publie":0.525,"score_0_1":0.3667,"niveau_suggere":-12.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":46,"modele":"mpt-30b","nom":"MPT-30B","editeur":"MosaicML","page":"https://quelleia.com/modeles/mpt-30b/","score_publie":0.506,"score_0_1":0.3413,"niveau_suggere":-15.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":47,"modele":"yi-6b","nom":"Yi 6B","editeur":"01.AI","page":"https://quelleia.com/modeles/yi-6b/","score_publie":0.503,"score_0_1":0.3373,"niveau_suggere":-15.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":48,"modele":"falcon-7b","nom":"Falcon-7B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-7b/","score_publie":0.4786,"score_0_1":0.3048,"niveau_suggere":-19.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":7,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":49,"modele":"llama-7b","nom":"LLaMA-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-7b/","score_publie":0.476,"score_0_1":0.3013,"niveau_suggere":-19.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":50,"modele":"starcoder-2-15b","nom":"StarCoder 2 15B","editeur":"Hugging Face","page":"https://quelleia.com/modeles/starcoder-2-15b/","score_publie":0.472,"score_0_1":0.296,"niveau_suggere":-20.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":51,"modele":"llama-2-7b","nom":"Llama 2-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-7b/","score_publie":0.459,"score_0_1":0.2787,"niveau_suggere":-22.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":6,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":52,"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":0.452,"score_0_1":0.2693,"niveau_suggere":-23.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":53,"modele":"phi-1-5","nom":"Phi-1.5","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-1-5/","score_publie":0.444,"score_0_1":0.2587,"niveau_suggere":-25.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":54,"modele":"vicuna-13b-v1-1","nom":"vicuna-13b-v1.1","editeur":null,"page":"https://quelleia.com/modeles/vicuna-13b-v1-1/","score_publie":0.432,"score_0_1":0.2427,"niveau_suggere":-27.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":55,"modele":"mpt-7b","nom":"MPT-7B","editeur":"MosaicML","page":"https://quelleia.com/modeles/mpt-7b/","score_publie":0.426,"score_0_1":0.2347,"niveau_suggere":-28.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":56,"modele":"deepseek-coder-33b","nom":"DeepSeek Coder 33B","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-coder-33b/","score_publie":0.422,"score_0_1":0.2293,"niveau_suggere":-29.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":57,"modele":"gemma-2b","nom":"Gemma 2B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-2b/","score_publie":0.421,"score_0_1":0.228,"niveau_suggere":-29.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":58,"modele":"xgen-7b","nom":"XGen-7B","editeur":"Salesforce","page":"https://quelleia.com/modeles/xgen-7b/","score_publie":0.412,"score_0_1":0.216,"niveau_suggere":-31.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":59,"modele":"gpt-neox-20b","nom":"GPT-NeoX-20B","editeur":"EleutherAI","page":"https://quelleia.com/modeles/gpt-neox-20b/","score_publie":0.411,"score_0_1":0.2147,"niveau_suggere":-31.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":60,"modele":"dolly-2-0-12b","nom":"Dolly 2.0-12b","editeur":"Databricks","page":"https://quelleia.com/modeles/dolly-2-0-12b/","score_publie":0.396,"score_0_1":0.1947,"niveau_suggere":-34.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":61,"modele":"redpajama-incite-7b-base","nom":"RedPajama-INCITE-7B-Base","editeur":null,"page":"https://quelleia.com/modeles/redpajama-incite-7b-base/","score_publie":0.391,"score_0_1":0.188,"niveau_suggere":-36,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":62,"modele":"starcoder-2-7b","nom":"StarCoder 2 7B","editeur":"Hugging Face","page":"https://quelleia.com/modeles/starcoder-2-7b/","score_publie":0.387,"score_0_1":0.1827,"niveau_suggere":-36.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":62,"modele":"open-llama-7b","nom":"open_llama_7b","editeur":null,"page":"https://quelleia.com/modeles/open-llama-7b/","score_publie":0.387,"score_0_1":0.1827,"niveau_suggere":-36.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":64,"modele":"baichuan2-13b","nom":"Baichuan2-13B","editeur":"Baichuan","page":"https://quelleia.com/modeles/baichuan2-13b/","score_publie":0.38,"score_0_1":0.1733,"niveau_suggere":-38.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":65,"modele":"deepseek-coder-6-7b","nom":"DeepSeek Coder 6.7B","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-coder-6-7b/","score_publie":0.364,"score_0_1":0.152,"niveau_suggere":-42.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":66,"modele":"gpt-j-6b","nom":"GPT-J-6B","editeur":"EleutherAI","page":"https://quelleia.com/modeles/gpt-j-6b/","score_publie":0.363,"score_0_1":0.1507,"niveau_suggere":-42.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":67,"modele":"opt-13b","nom":"opt-13b","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-13b/","score_publie":0.358,"score_0_1":0.144,"niveau_suggere":-44.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":68,"modele":"codeqwen1-5-7b","nom":"CodeQwen1.5-7B","editeur":"Alibaba","page":"https://quelleia.com/modeles/codeqwen1-5-7b/","score_publie":0.357,"score_0_1":0.1427,"niveau_suggere":-44.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":69,"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":0.344,"score_0_1":0.1253,"niveau_suggere":-48.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":70,"modele":"starcoder-2-3b","nom":"StarCoder 2 3B","editeur":"Hugging Face","page":"https://quelleia.com/modeles/starcoder-2-3b/","score_publie":0.342,"score_0_1":0.1227,"niveau_suggere":-49.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":71,"modele":"baichuan-2-7b","nom":"Baichuan 2-7B","editeur":"Baichuan","page":"https://quelleia.com/modeles/baichuan-2-7b/","score_publie":0.325,"score_0_1":0.1,"niveau_suggere":-55.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":72,"modele":"cerebras-gpt-13b","nom":"Cerebras-GPT-13B","editeur":"Cerebras Systems","page":"https://quelleia.com/modeles/cerebras-gpt-13b/","score_publie":0.324,"score_0_1":0.0987,"niveau_suggere":-55.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":73,"modele":"stablelm-tuned-alpha-7b","nom":"stablelm-tuned-alpha-7b","editeur":"Stability AI","page":"https://quelleia.com/modeles/stablelm-tuned-alpha-7b/","score_publie":0.27,"score_0_1":0.0267,"niveau_suggere":-91.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"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":0.254,"score_0_1":0.0053,"niveau_suggere":-117.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":75,"modele":"gpt-2-1-5b","nom":"GPT-2 (1.5B)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-2-1-5b/","score_publie":0.25,"score_0_1":0,"niveau_suggere":-117.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":76,"modele":"opt-1-3b","nom":"OPT-1.3B","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-1-3b/","score_publie":0.232,"score_0_1":0,"niveau_suggere":-117.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"}]}