{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/hellaswag/","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":"hellaswag","nom":"HellaSwag","tache":"autre","etat":"archive","echelle":"unite","modeles":75,"poids_general":0,"difficulte":-54.7,"pente":0.0156,"en_une_phrase":"Choisir la suite la plus plausible d'une courte scène du quotidien parmi quatre propositions, dont trois pièges écrits par une machine.","notation":"Part de bonnes réponses ; le hasard donne 25 %.","limites":"Test de 2019, saturé et largement présent dans les données d'entraînement. Il ne dit rien des modèles actuels.","mainteneur":"Zellers et al. (université de Washington et Allen Institute for AI)","url":"https://rowanzellers.com/hellaswag/","verifie":true},"tache":{"id":"autre","nom":"Tests historiques","poids_general":0,"benchmarks_actifs":0},"modeles_mesures":75,"mesures":113,"classement":[{"rang":1,"modele":"gpt-4-mar-2023","nom":"GPT-4 (Mar 2023)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4-mar-2023/","score_publie":0.953,"score_0_1":0.9373,"niveau_suggere":118.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":2,"modele":"llama-3-1-405b","nom":"Llama 3.1-405B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-1-405b/","score_publie":0.892,"score_0_1":0.856,"niveau_suggere":59.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"falcon-180b","nom":"Falcon-180B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-180b/","score_publie":0.89,"score_0_1":0.8533,"niveau_suggere":57.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"deepseek-v3","nom":"DeepSeek-V3","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v3/","score_publie":0.889,"score_0_1":0.852,"niveau_suggere":57.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"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":0.871,"score_0_1":0.828,"niveau_suggere":45.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":6,"modele":"palm-2-l","nom":"PaLM 2-L","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-l/","score_publie":0.868,"score_0_1":0.824,"niveau_suggere":44,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":7,"modele":"mixtral-8x7b","nom":"Mixtral 8x7B","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mixtral-8x7b/","score_publie":0.867,"score_0_1":0.8227,"niveau_suggere":43.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"davinci-003","nom":"davinci-003","editeur":"OpenAI","page":"https://quelleia.com/modeles/davinci-003/","score_publie":0.855,"score_0_1":0.8067,"niveau_suggere":36.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":9,"modele":"llama-2-70b","nom":"Llama 2-70B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-70b/","score_publie":0.853,"score_0_1":0.804,"niveau_suggere":35.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":10,"modele":"falcon-40b","nom":"Falcon-40B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-40b/","score_publie":0.8528,"score_0_1":0.8037,"niveau_suggere":35.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"qwen2-5-72b","nom":"Qwen2.5-72B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-72b/","score_publie":0.848,"score_0_1":0.7973,"niveau_suggere":32.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":12,"modele":"llama-65b","nom":"LLaMA-65B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-65b/","score_publie":0.842,"score_0_1":0.7893,"niveau_suggere":29.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":13,"modele":"stable-beluga-2","nom":"Stable Beluga 2","editeur":"Stability AI","page":"https://quelleia.com/modeles/stable-beluga-2/","score_publie":0.841,"score_0_1":0.788,"niveau_suggere":29.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"palm-2-m","nom":"PaLM 2-M","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-m/","score_publie":0.84,"score_0_1":0.7867,"niveau_suggere":28.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":15,"modele":"palm-540b","nom":"PaLM (540B)","editeur":"Google Research","page":"https://quelleia.com/modeles/palm-540b/","score_publie":0.838,"score_0_1":0.784,"niveau_suggere":27.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"qwen2-5-coder-32b","nom":"Qwen2.5-Coder-32B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-32b/","score_publie":0.83,"score_0_1":0.7733,"niveau_suggere":23.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":17,"modele":"falcon-2-11b","nom":"Falcon 2 11B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-2-11b/","score_publie":0.8291,"score_0_1":0.7721,"niveau_suggere":23.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"llama-33b","nom":"LLaMA-33B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-33b/","score_publie":0.828,"score_0_1":0.7707,"niveau_suggere":22.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":19,"modele":"phi-3-medium-14b","nom":"phi-3-medium 14B","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-medium-14b/","score_publie":0.824,"score_0_1":0.7653,"niveau_suggere":20.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":19,"modele":"megatron-turing-nlg-530b","nom":"Megatron-Turing NLG 530B","editeur":"Microsoft","page":"https://quelleia.com/modeles/megatron-turing-nlg-530b/","score_publie":0.824,"score_0_1":0.7653,"niveau_suggere":20.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":19,"modele":"nemotron-4-15b","nom":"Nemotron-4 15B","editeur":"NVIDIA","page":"https://quelleia.com/modeles/nemotron-4-15b/","score_publie":0.824,"score_0_1":0.7653,"niveau_suggere":20.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":22,"modele":"gemma-7b","nom":"Gemma 7B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-7b/","score_publie":0.822,"score_0_1":0.7627,"niveau_suggere":20,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"palm-2-s","nom":"PaLM 2-S","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-s/","score_publie":0.82,"score_0_1":0.76,"niveau_suggere":19,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":24,"modele":"davinci-002","nom":"davinci-002","editeur":"OpenAI","page":"https://quelleia.com/modeles/davinci-002/","score_publie":0.815,"score_0_1":0.7533,"niveau_suggere":16.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":25,"modele":"mistral-7b-v0-1","nom":"Mistral 7B v0.1","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-7b-v0-1/","score_publie":0.81,"score_0_1":0.7467,"niveau_suggere":14.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":26,"modele":"llama-2-13b","nom":"Llama 2-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-13b/","score_publie":0.807,"score_0_1":0.7427,"niveau_suggere":13.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":27,"modele":"qwen2-5-coder-14b","nom":"Qwen2.5-Coder-14B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-14b/","score_publie":0.802,"score_0_1":0.736,"niveau_suggere":10.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":28,"modele":"instructgpt-175b","nom":"InstructGPT 175B","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-175b/","score_publie":0.793,"score_0_1":0.724,"niveau_suggere":7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":9,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":29,"modele":"gopher-280b","nom":"Gopher (280B)","editeur":"DeepMind","page":"https://quelleia.com/modeles/gopher-280b/","score_publie":0.792,"score_0_1":0.7227,"niveau_suggere":6.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":29,"modele":"llama-13b","nom":"LLaMA-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-13b/","score_publie":0.792,"score_0_1":0.7227,"niveau_suggere":6.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":31,"modele":"opt-175b","nom":"OPT-175B","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-175b/","score_publie":0.791,"score_0_1":0.7213,"niveau_suggere":6.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":32,"modele":"internlm-20b","nom":"internlm-20b","editeur":"Shanghai AI Laboratory","page":"https://quelleia.com/modeles/internlm-20b/","score_publie":0.781,"score_0_1":0.708,"niveau_suggere":2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":32,"modele":"falcon-7b","nom":"Falcon-7B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-7b/","score_publie":0.781,"score_0_1":0.708,"niveau_suggere":2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":7,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":34,"modele":"gpt-3-175b-davinci","nom":"GPT-3 175B (davinci)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-175b-davinci/","score_publie":0.775,"score_0_1":0.7,"niveau_suggere":-0.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":35,"modele":"glam","nom":"GLaM","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/glam/","score_publie":0.772,"score_0_1":0.696,"niveau_suggere":-1.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":35,"modele":"llama-2-7b","nom":"Llama 2-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-7b/","score_publie":0.772,"score_0_1":0.696,"niveau_suggere":-1.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":37,"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":0.77,"score_0_1":0.6933,"niveau_suggere":-2.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":38,"modele":"qwen2-5-coder-7b","nom":"Qwen2.5-Coder (7B)","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-7b/","score_publie":0.768,"score_0_1":0.6907,"niveau_suggere":-3.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":39,"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":0.767,"score_0_1":0.6893,"niveau_suggere":-3.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":40,"modele":"yi-9b","nom":"Yi-9B","editeur":"01.AI","page":"https://quelleia.com/modeles/yi-9b/","score_publie":0.764,"score_0_1":0.6853,"niveau_suggere":-4.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":40,"modele":"mpt-7b","nom":"MPT-7B","editeur":"MosaicML","page":"https://quelleia.com/modeles/mpt-7b/","score_publie":0.764,"score_0_1":0.6853,"niveau_suggere":-4.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":42,"modele":"llama-7b","nom":"LLaMA-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-7b/","score_publie":0.762,"score_0_1":0.6827,"niveau_suggere":-5.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":43,"modele":"opt-66b","nom":"OPT-66B","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-66b/","score_publie":0.745,"score_0_1":0.66,"niveau_suggere":-12.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":44,"modele":"bloom-176b","nom":"BLOOM-176B","editeur":"Hugging Face","page":"https://quelleia.com/modeles/bloom-176b/","score_publie":0.744,"score_0_1":0.6587,"niveau_suggere":-12.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":44,"modele":"yi-6b","nom":"Yi 6B","editeur":"01.AI","page":"https://quelleia.com/modeles/yi-6b/","score_publie":0.744,"score_0_1":0.6587,"niveau_suggere":-12.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":46,"modele":"xgen-7b","nom":"XGen-7B","editeur":"Salesforce","page":"https://quelleia.com/modeles/xgen-7b/","score_publie":0.742,"score_0_1":0.656,"niveau_suggere":-13.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":47,"modele":"open-llama-7b","nom":"open_llama_7b","editeur":null,"page":"https://quelleia.com/modeles/open-llama-7b/","score_publie":0.718,"score_0_1":0.624,"niveau_suggere":-22.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":48,"modele":"intellect-1","nom":"INTELLECT-1","editeur":"Prime Intellect","page":"https://quelleia.com/modeles/intellect-1/","score_publie":0.7142,"score_0_1":0.6189,"niveau_suggere":-23.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":49,"modele":"gemma-2b","nom":"Gemma 2B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-2b/","score_publie":0.714,"score_0_1":0.6187,"niveau_suggere":-23.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":50,"modele":"qwen2-5-coder-3b","nom":"Qwen2.5-Coder-3B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-coder-3b/","score_publie":0.709,"score_0_1":0.612,"niveau_suggere":-25.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":51,"modele":"baichuan2-13b","nom":"Baichuan2-13B","editeur":"Baichuan","page":"https://quelleia.com/modeles/baichuan2-13b/","score_publie":0.708,"score_0_1":0.6107,"niveau_suggere":-25.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":51,"modele":"dolly-2-0-12b","nom":"Dolly 2.0-12b","editeur":"Databricks","page":"https://quelleia.com/modeles/dolly-2-0-12b/","score_publie":0.708,"score_0_1":0.6107,"niveau_suggere":-25.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":53,"modele":"internlm-7b","nom":"internlm-7b","editeur":"Shanghai AI Laboratory","page":"https://quelleia.com/modeles/internlm-7b/","score_publie":0.706,"score_0_1":0.608,"niveau_suggere":-26.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":54,"modele":"gpt-neox-20b","nom":"GPT-NeoX-20B","editeur":"EleutherAI","page":"https://quelleia.com/modeles/gpt-neox-20b/","score_publie":0.705,"score_0_1":0.6067,"niveau_suggere":-27,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":55,"modele":"redpajama-incite-7b-base","nom":"RedPajama-INCITE-7B-Base","editeur":null,"page":"https://quelleia.com/modeles/redpajama-incite-7b-base/","score_publie":0.703,"score_0_1":0.604,"niveau_suggere":-27.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":56,"modele":"opt-13b","nom":"opt-13b","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-13b/","score_publie":0.699,"score_0_1":0.5987,"niveau_suggere":-29.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":57,"modele":"gpt-3-6-7b","nom":"GPT-3 6.7B","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-6-7b/","score_publie":0.682,"score_0_1":0.576,"niveau_suggere":-35.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":58,"modele":"baichuan-2-7b","nom":"Baichuan 2-7B","editeur":"Baichuan","page":"https://quelleia.com/modeles/baichuan-2-7b/","score_publie":0.68,"score_0_1":0.5733,"niveau_suggere":-35.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":59,"modele":"instructgpt-6b","nom":"InstructGPT 6B","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-6b/","score_publie":0.676,"score_0_1":0.568,"niveau_suggere":-37.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":60,"modele":"gpt-j-6b","nom":"GPT-J-6B","editeur":"EleutherAI","page":"https://quelleia.com/modeles/gpt-j-6b/","score_publie":0.662,"score_0_1":0.5493,"niveau_suggere":-42,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":61,"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":0.618,"score_0_1":0.4907,"niveau_suggere":-57.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":62,"modele":"cerebras-gpt-13b","nom":"Cerebras-GPT-13B","editeur":"Cerebras Systems","page":"https://quelleia.com/modeles/cerebras-gpt-13b/","score_publie":0.594,"score_0_1":0.4587,"niveau_suggere":-65.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":63,"modele":"vicuna-13b-v1-1","nom":"vicuna-13b-v1.1","editeur":null,"page":"https://quelleia.com/modeles/vicuna-13b-v1-1/","score_publie":0.578,"score_0_1":0.4373,"niveau_suggere":-70.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":64,"modele":"chatglm2-6b","nom":"chatglm2-6b","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/chatglm2-6b/","score_publie":0.57,"score_0_1":0.4267,"niveau_suggere":-73.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":65,"modele":"instructgpt-1-3b","nom":"InstructGPT 1.3B","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-1-3b/","score_publie":0.561,"score_0_1":0.4147,"niveau_suggere":-76.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":66,"modele":"gpt-3-xl-babbage","nom":"GPT-3 XL (babbage)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-xl-babbage/","score_publie":0.555,"score_0_1":0.4067,"niveau_suggere":-78.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":67,"modele":"phi-2","nom":"Phi-2","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-2/","score_publie":0.536,"score_0_1":0.3813,"niveau_suggere":-85.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":68,"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":0.484,"score_0_1":0.312,"niveau_suggere":-105.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":69,"modele":"phi-1-5","nom":"Phi-1.5","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-1-5/","score_publie":0.476,"score_0_1":0.3013,"niveau_suggere":-108.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":70,"modele":"gpt-3-medium","nom":"GPT-3 Medium","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-medium/","score_publie":0.435,"score_0_1":0.2467,"niveau_suggere":-126,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":71,"modele":"instructgpt-350m","nom":"InstructGPT 350M","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-350m/","score_publie":0.429,"score_0_1":0.2387,"niveau_suggere":-128.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":72,"modele":"gpt-neo-2-7b","nom":"GPT-Neo-2.7B","editeur":"EleutherAI","page":"https://quelleia.com/modeles/gpt-neo-2-7b/","score_publie":0.427,"score_0_1":0.236,"niveau_suggere":-129.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":73,"modele":"opt-1-3b","nom":"OPT-1.3B","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-1-3b/","score_publie":0.415,"score_0_1":0.22,"niveau_suggere":-135.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":74,"modele":"stablelm-tuned-alpha-7b","nom":"stablelm-tuned-alpha-7b","editeur":"Stability AI","page":"https://quelleia.com/modeles/stablelm-tuned-alpha-7b/","score_publie":0.407,"score_0_1":0.2093,"niveau_suggere":-139.6,"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":0.4,"score_0_1":0.2,"niveau_suggere":-143.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"}]}