{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/boolq/","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":"boolq","nom":"BoolQ","tache":"autre","etat":"archive","echelle":"unite","modeles":76,"poids_general":0,"difficulte":-22.1,"pente":0.0226,"en_une_phrase":"Répondre par oui ou par non à une vraie question d'internaute, à partir d'un court passage de texte.","notation":"Part de bonnes réponses ; le hasard donne 50 %.","limites":"Test de 2019 saturé. Avec deux réponses possibles, les écarts entre modèles sont minces.","mainteneur":"Google AI Language (Clark et al., 2019)","url":"https://github.com/google-research-datasets/boolean-questions","verifie":true},"tache":{"id":"autre","nom":"Tests historiques","poids_general":0,"benchmarks_actifs":0},"modeles_mesures":76,"mesures":136,"classement":[{"rang":1,"modele":"t5-11b","nom":"T5-11B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/t5-11b/","score_publie":0.912,"score_0_1":0.824,"niveau_suggere":46.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":2,"modele":"palm-2-l","nom":"PaLM 2-L","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-l/","score_publie":0.909,"score_0_1":0.818,"niveau_suggere":44.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"t5-3b","nom":"T5-3B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/t5-3b/","score_publie":0.899,"score_0_1":0.798,"niveau_suggere":38.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"inflection-1","nom":"Inflection-1","editeur":"Inflection AI","page":"https://quelleia.com/modeles/inflection-1/","score_publie":0.897,"score_0_1":0.794,"niveau_suggere":37.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"stable-beluga-2","nom":"Stable Beluga 2","editeur":"Stability AI","page":"https://quelleia.com/modeles/stable-beluga-2/","score_publie":0.894,"score_0_1":0.788,"niveau_suggere":36.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":6,"modele":"falcon-180b","nom":"Falcon-180B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-180b/","score_publie":0.89,"score_0_1":0.78,"niveau_suggere":34,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":7,"modele":"gpt-4o-mini","nom":"GPT-4o mini","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-4o-mini/","score_publie":0.887,"score_0_1":0.774,"niveau_suggere":32.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":7,"modele":"palm-540b","nom":"PaLM (540B)","editeur":"Google Research","page":"https://quelleia.com/modeles/palm-540b/","score_publie":0.887,"score_0_1":0.774,"niveau_suggere":32.5,"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":0.886,"score_0_1":0.772,"niveau_suggere":32,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":9,"modele":"palm-2-m","nom":"PaLM 2-M","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-m/","score_publie":0.886,"score_0_1":0.772,"niveau_suggere":32,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"davinci-003","nom":"davinci-003","editeur":"OpenAI","page":"https://quelleia.com/modeles/davinci-003/","score_publie":0.881,"score_0_1":0.762,"niveau_suggere":29.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"palm-2-s","nom":"PaLM 2-S","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-s/","score_publie":0.881,"score_0_1":0.762,"niveau_suggere":29.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":13,"modele":"davinci-002","nom":"davinci-002","editeur":"OpenAI","page":"https://quelleia.com/modeles/davinci-002/","score_publie":0.877,"score_0_1":0.754,"niveau_suggere":27.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"internlm-20b","nom":"internlm-20b","editeur":"Shanghai AI Laboratory","page":"https://quelleia.com/modeles/internlm-20b/","score_publie":0.875,"score_0_1":0.75,"niveau_suggere":26.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":15,"modele":"mistral-7b-v0-1","nom":"Mistral 7B v0.1","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-7b-v0-1/","score_publie":0.874,"score_0_1":0.748,"niveau_suggere":26.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"llama-65b","nom":"LLaMA-65B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-65b/","score_publie":0.871,"score_0_1":0.742,"niveau_suggere":24.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":17,"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":0.87,"score_0_1":0.74,"niveau_suggere":24.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"qwen-14b","nom":"Qwen-14B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-14b/","score_publie":0.862,"score_0_1":0.724,"niveau_suggere":20.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":19,"modele":"llama-33b","nom":"LLaMA-33B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-33b/","score_publie":0.861,"score_0_1":0.722,"niveau_suggere":20.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":20,"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":0.858,"score_0_1":0.716,"niveau_suggere":18.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":21,"modele":"gemma-2-9b","nom":"Gemma 2 9B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-2-9b/","score_publie":0.857,"score_0_1":0.714,"niveau_suggere":18.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":22,"modele":"t5-large","nom":"T5-Large","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/t5-large/","score_publie":0.854,"score_0_1":0.708,"niveau_suggere":17.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"mpt-30b","nom":"MPT-30B","editeur":"MosaicML","page":"https://quelleia.com/modeles/mpt-30b/","score_publie":0.85,"score_0_1":0.7,"niveau_suggere":15.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":24,"modele":"megatron-turing-nlg-530b","nom":"Megatron-Turing NLG 530B","editeur":"Microsoft","page":"https://quelleia.com/modeles/megatron-turing-nlg-530b/","score_publie":0.8483,"score_0_1":0.6966,"niveau_suggere":14.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":25,"modele":"palm-62b","nom":"PaLM 62B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-62b/","score_publie":0.848,"score_0_1":0.696,"niveau_suggere":14.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":26,"modele":"phi-3-5-moe","nom":"Phi-3.5-MoE","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-5-moe/","score_publie":0.846,"score_0_1":0.692,"niveau_suggere":13.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":27,"modele":"chinchilla","nom":"Chinchilla","editeur":"DeepMind","page":"https://quelleia.com/modeles/chinchilla/","score_publie":0.837,"score_0_1":0.674,"niveau_suggere":10.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":27,"modele":"llama-2-34b","nom":"Llama 2-34B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-34b/","score_publie":0.837,"score_0_1":0.674,"niveau_suggere":10.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":29,"modele":"vicuna-13b-v1-1","nom":"vicuna-13b-v1.1","editeur":null,"page":"https://quelleia.com/modeles/vicuna-13b-v1-1/","score_publie":0.835,"score_0_1":0.67,"niveau_suggere":9.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":30,"modele":"mistral-7b-v0-2","nom":"Mistral 7B v0.2","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-7b-v0-2/","score_publie":0.832,"score_0_1":0.664,"niveau_suggere":8.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":30,"modele":"gemma-7b","nom":"Gemma 7B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-7b/","score_publie":0.832,"score_0_1":0.664,"niveau_suggere":8.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":32,"modele":"falcon-40b","nom":"Falcon-40B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-40b/","score_publie":0.831,"score_0_1":0.662,"niveau_suggere":7.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":33,"modele":"llama-3-1-8b","nom":"Llama 3.1-8B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-1-8b/","score_publie":0.828,"score_0_1":0.656,"niveau_suggere":6.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":34,"modele":"mistral-nemo","nom":"Mistral NeMo","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-nemo/","score_publie":0.825,"score_0_1":0.65,"niveau_suggere":5.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":35,"modele":"llama-2-13b","nom":"Llama 2-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-13b/","score_publie":0.824,"score_0_1":0.648,"niveau_suggere":5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":36,"modele":"t5-base","nom":"T5-Base","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/t5-base/","score_publie":0.814,"score_0_1":0.628,"niveau_suggere":1.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":37,"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":0.808,"score_0_1":0.616,"niveau_suggere":-1.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":38,"modele":"gopher-280b","nom":"Gopher (280B)","editeur":"DeepMind","page":"https://quelleia.com/modeles/gopher-280b/","score_publie":0.794,"score_0_1":0.588,"niveau_suggere":-6.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":39,"modele":"opt-175b","nom":"OPT-175B","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-175b/","score_publie":0.793,"score_0_1":0.586,"niveau_suggere":-6.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":40,"modele":"chatglm2-6b","nom":"chatglm2-6b","editeur":"Z.ai (Zhipu AI)","page":"https://quelleia.com/modeles/chatglm2-6b/","score_publie":0.79,"score_0_1":0.58,"niveau_suggere":-7.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":41,"modele":"llama-13b","nom":"LLaMA-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-13b/","score_publie":0.787,"score_0_1":0.574,"niveau_suggere":-8.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":42,"modele":"phi-3-5-mini","nom":"Phi-3.5-mini","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-5-mini/","score_publie":0.78,"score_0_1":0.56,"niveau_suggere":-11.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":43,"modele":"llama-2-7b","nom":"Llama 2-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-7b/","score_publie":0.779,"score_0_1":0.558,"niveau_suggere":-11.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":6,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":44,"modele":"instructgpt-175b","nom":"InstructGPT 175B","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-175b/","score_publie":0.775,"score_0_1":0.55,"niveau_suggere":-13.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":9,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":45,"modele":"llama-7b","nom":"LLaMA-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-7b/","score_publie":0.765,"score_0_1":0.53,"niveau_suggere":-16.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":6,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":46,"modele":"qwen-7b","nom":"Qwen-7B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-7b/","score_publie":0.764,"score_0_1":0.528,"niveau_suggere":-17.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":46,"modele":"t5-small","nom":"T5-Small","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/t5-small/","score_publie":0.764,"score_0_1":0.528,"niveau_suggere":-17.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":48,"modele":"opt-66b","nom":"OPT-66B","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-66b/","score_publie":0.76,"score_0_1":0.52,"niveau_suggere":-18.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":49,"modele":"phi-1-5","nom":"Phi-1.5","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-1-5/","score_publie":0.758,"score_0_1":0.516,"niveau_suggere":-19.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":50,"modele":"falcon-7b","nom":"Falcon-7B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-7b/","score_publie":0.753,"score_0_1":0.506,"niveau_suggere":-21,"reflexion":"inconnue","harnais":null,"configurations_mesurees":6,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":51,"modele":"mpt-7b","nom":"MPT-7B","editeur":"MosaicML","page":"https://quelleia.com/modeles/mpt-7b/","score_publie":0.75,"score_0_1":0.5,"niveau_suggere":-22.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":52,"modele":"xgen-7b","nom":"XGen-7B","editeur":"Salesforce","page":"https://quelleia.com/modeles/xgen-7b/","score_publie":0.743,"score_0_1":0.486,"niveau_suggere":-24.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":53,"modele":"gpt-3-175b-davinci","nom":"GPT-3 175B (davinci)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-175b-davinci/","score_publie":0.722,"score_0_1":0.444,"niveau_suggere":-32,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":54,"modele":"open-llama-7b","nom":"open_llama_7b","editeur":null,"page":"https://quelleia.com/modeles/open-llama-7b/","score_publie":0.706,"score_0_1":0.412,"niveau_suggere":-37.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":55,"modele":"bloom-176b","nom":"BLOOM-176B","editeur":"Hugging Face","page":"https://quelleia.com/modeles/bloom-176b/","score_publie":0.704,"score_0_1":0.408,"niveau_suggere":-38.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":56,"modele":"gemma-2b","nom":"Gemma 2B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-2b/","score_publie":0.694,"score_0_1":0.388,"niveau_suggere":-42.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":57,"modele":"redpajama-incite-7b-base","nom":"RedPajama-INCITE-7B-Base","editeur":null,"page":"https://quelleia.com/modeles/redpajama-incite-7b-base/","score_publie":0.693,"score_0_1":0.386,"niveau_suggere":-42.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":58,"modele":"qwen-1-8b","nom":"Qwen-1_8B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen-1-8b/","score_publie":0.68,"score_0_1":0.36,"niveau_suggere":-47.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":59,"modele":"baichuan2-13b","nom":"Baichuan2-13B","editeur":"Baichuan","page":"https://quelleia.com/modeles/baichuan2-13b/","score_publie":0.67,"score_0_1":0.34,"niveau_suggere":-51.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":60,"modele":"gpt-3-6-7b","nom":"GPT-3 6.7B","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-6-7b/","score_publie":0.656,"score_0_1":0.312,"niveau_suggere":-57.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":61,"modele":"gpt-j-6b","nom":"GPT-J-6B","editeur":"EleutherAI","page":"https://quelleia.com/modeles/gpt-j-6b/","score_publie":0.654,"score_0_1":0.308,"niveau_suggere":-57.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":62,"modele":"opt-13b","nom":"opt-13b","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-13b/","score_publie":0.65,"score_0_1":0.3,"niveau_suggere":-59.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":63,"modele":"gpt-neox-20b","nom":"GPT-NeoX-20B","editeur":"EleutherAI","page":"https://quelleia.com/modeles/gpt-neox-20b/","score_publie":0.649,"score_0_1":0.298,"niveau_suggere":-60,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":64,"modele":"internlm-7b","nom":"internlm-7b","editeur":"Shanghai AI Laboratory","page":"https://quelleia.com/modeles/internlm-7b/","score_publie":0.641,"score_0_1":0.282,"niveau_suggere":-63.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":65,"modele":"baichuan-2-7b","nom":"Baichuan 2-7B","editeur":"Baichuan","page":"https://quelleia.com/modeles/baichuan-2-7b/","score_publie":0.632,"score_0_1":0.264,"niveau_suggere":-67.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":66,"modele":"instructgpt-6b","nom":"InstructGPT 6B","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-6b/","score_publie":0.62,"score_0_1":0.24,"niveau_suggere":-73.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":67,"modele":"gpt-2-1-5b","nom":"GPT-2 (1.5B)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-2-1-5b/","score_publie":0.618,"score_0_1":0.236,"niveau_suggere":-74.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":67,"modele":"gpt-neo-2-7b","nom":"GPT-Neo-2.7B","editeur":"EleutherAI","page":"https://quelleia.com/modeles/gpt-neo-2-7b/","score_publie":0.618,"score_0_1":0.236,"niveau_suggere":-74.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":69,"modele":"cerebras-gpt-13b","nom":"Cerebras-GPT-13B","editeur":"Cerebras Systems","page":"https://quelleia.com/modeles/cerebras-gpt-13b/","score_publie":0.611,"score_0_1":0.222,"niveau_suggere":-77.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":70,"modele":"opt-1-3b","nom":"OPT-1.3B","editeur":"Meta AI","page":"https://quelleia.com/modeles/opt-1-3b/","score_publie":0.596,"score_0_1":0.192,"niveau_suggere":-85.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":71,"modele":"stablelm-tuned-alpha-7b","nom":"stablelm-tuned-alpha-7b","editeur":"Stability AI","page":"https://quelleia.com/modeles/stablelm-tuned-alpha-7b/","score_publie":0.59,"score_0_1":0.18,"niveau_suggere":-89.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":72,"modele":"gpt-3-medium","nom":"GPT-3 Medium","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-medium/","score_publie":0.581,"score_0_1":0.162,"niveau_suggere":-94.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":73,"modele":"gpt-3-xl-babbage","nom":"GPT-3 XL (babbage)","editeur":"OpenAI","page":"https://quelleia.com/modeles/gpt-3-xl-babbage/","score_publie":0.574,"score_0_1":0.148,"niveau_suggere":-99.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":74,"modele":"dolly-2-0-12b","nom":"Dolly 2.0-12b","editeur":"Databricks","page":"https://quelleia.com/modeles/dolly-2-0-12b/","score_publie":0.563,"score_0_1":0.126,"niveau_suggere":-107.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":75,"modele":"instructgpt-350m","nom":"InstructGPT 350M","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-350m/","score_publie":0.464,"score_0_1":0,"niveau_suggere":-225.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":76,"modele":"instructgpt-1-3b","nom":"InstructGPT 1.3B","editeur":"OpenAI","page":"https://quelleia.com/modeles/instructgpt-1-3b/","score_publie":0.451,"score_0_1":0,"niveau_suggere":-225.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"}]}