{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/benchmarks/triviaqa/","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":"triviaqa","nom":"TriviaQA","tache":"autre","etat":"archive","echelle":"unite","modeles":38,"poids_general":0,"difficulte":-88.5,"pente":0.0109,"en_une_phrase":"Des questions de culture générale écrites par des amateurs de quiz, à réponse courte.","notation":"Part de réponses exactement identiques à la réponse attendue.","limites":"Test de 2017, largement mémorisé par les modèles. Les résultats viennent d'articles aux réglages variés.","mainteneur":"Joshi et al. (université de Washington, 2017)","url":"https://nlp.cs.washington.edu/triviaqa/","verifie":true},"tache":{"id":"autre","nom":"Tests historiques","poids_general":0,"benchmarks_actifs":0},"modeles_mesures":38,"mesures":115,"classement":[{"rang":1,"modele":"llama-2-70b","nom":"Llama 2-70B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-70b/","score_publie":0.876,"score_0_1":0.876,"niveau_suggere":90.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":2,"modele":"claude-2","nom":"Claude 2","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-2/","score_publie":0.875,"score_0_1":0.875,"niveau_suggere":89.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":3,"modele":"claude-1-3","nom":"Claude 1.3","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-1-3/","score_publie":0.867,"score_0_1":0.867,"niveau_suggere":83.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":4,"modele":"palm-2-l","nom":"PaLM 2-L","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-l/","score_publie":0.861,"score_0_1":0.861,"niveau_suggere":78.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":5,"modele":"llama-65b","nom":"LLaMA-65B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-65b/","score_publie":0.86,"score_0_1":0.86,"niveau_suggere":78,"reflexion":"inconnue","harnais":null,"configurations_mesurees":8,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":6,"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":0.858,"score_0_1":0.858,"niveau_suggere":76.5,"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":0.848,"score_0_1":0.848,"niveau_suggere":69.1,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":8,"modele":"llama-2-34b","nom":"Llama 2-34B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-34b/","score_publie":0.846,"score_0_1":0.846,"niveau_suggere":67.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":9,"modele":"llama-33b","nom":"LLaMA-33B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-33b/","score_publie":0.838,"score_0_1":0.838,"niveau_suggere":62.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":8,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":10,"modele":"deepseek-v3","nom":"DeepSeek-V3","editeur":"DeepSeek","page":"https://quelleia.com/modeles/deepseek-v3/","score_publie":0.829,"score_0_1":0.829,"niveau_suggere":56.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":11,"modele":"llama-3-1-405b","nom":"Llama 3.1-405B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-1-405b/","score_publie":0.827,"score_0_1":0.827,"niveau_suggere":55,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":12,"modele":"mixtral-8x7b","nom":"Mixtral 8x7B","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mixtral-8x7b/","score_publie":0.822,"score_0_1":0.822,"niveau_suggere":51.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":13,"modele":"palm-2-m","nom":"PaLM 2-M","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-m/","score_publie":0.817,"score_0_1":0.817,"niveau_suggere":48.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":14,"modele":"palm-540b","nom":"PaLM (540B)","editeur":"Google Research","page":"https://quelleia.com/modeles/palm-540b/","score_publie":0.814,"score_0_1":0.814,"niveau_suggere":46.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":15,"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":0.8,"score_0_1":0.8,"niveau_suggere":38.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":16,"modele":"falcon-40b","nom":"Falcon-40B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-40b/","score_publie":0.799,"score_0_1":0.799,"niveau_suggere":38,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":17,"modele":"llama-2-13b","nom":"Llama 2-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-13b/","score_publie":0.796,"score_0_1":0.796,"niveau_suggere":36.3,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":18,"modele":"claude-instant","nom":"Claude Instant","editeur":"Anthropic","page":"https://quelleia.com/modeles/claude-instant/","score_publie":0.789,"score_0_1":0.789,"niveau_suggere":32.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":19,"modele":"llama-13b","nom":"LLaMA-13B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-13b/","score_publie":0.779,"score_0_1":0.779,"niveau_suggere":27,"reflexion":"inconnue","harnais":null,"configurations_mesurees":8,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":20,"modele":"glam","nom":"GLaM","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/glam/","score_publie":0.758,"score_0_1":0.758,"niveau_suggere":16.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":21,"modele":"mistral-7b-v0-1","nom":"Mistral 7B v0.1","editeur":"Mistral AI","page":"https://quelleia.com/modeles/mistral-7b-v0-1/","score_publie":0.752,"score_0_1":0.752,"niveau_suggere":13.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":21,"modele":"palm-2-s","nom":"PaLM 2-S","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/palm-2-s/","score_publie":0.752,"score_0_1":0.752,"niveau_suggere":13.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":23,"modele":"phi-3-medium-14b","nom":"phi-3-medium 14B","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-3-medium-14b/","score_publie":0.739,"score_0_1":0.739,"niveau_suggere":6.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":24,"modele":"llama-2-7b","nom":"Llama 2-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-2-7b/","score_publie":0.737,"score_0_1":0.737,"niveau_suggere":6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":25,"modele":"mpt-30b","nom":"MPT-30B","editeur":"MosaicML","page":"https://quelleia.com/modeles/mpt-30b/","score_publie":0.736,"score_0_1":0.736,"niveau_suggere":5.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":26,"modele":"gemma-7b","nom":"Gemma 7B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-7b/","score_publie":0.723,"score_0_1":0.723,"niveau_suggere":-0.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":2,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":27,"modele":"qwen2-5-72b","nom":"Qwen2.5-72B","editeur":"Alibaba","page":"https://quelleia.com/modeles/qwen2-5-72b/","score_publie":0.719,"score_0_1":0.719,"niveau_suggere":-2.4,"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":0.712,"score_0_1":0.712,"niveau_suggere":-5.5,"reflexion":"inconnue","harnais":null,"configurations_mesurees":9,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":29,"modele":"llama-7b","nom":"LLaMA-7B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-7b/","score_publie":0.71,"score_0_1":0.71,"niveau_suggere":-6.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":8,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":30,"modele":"llama-3-8b","nom":"Llama 3-8B","editeur":"Meta AI","page":"https://quelleia.com/modeles/llama-3-8b/","score_publie":0.677,"score_0_1":0.677,"niveau_suggere":-20.7,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":31,"modele":"chinchilla","nom":"Chinchilla","editeur":"DeepMind","page":"https://quelleia.com/modeles/chinchilla/","score_publie":0.646,"score_0_1":0.646,"niveau_suggere":-33.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":3,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":31,"modele":"falcon-7b","nom":"Falcon-7B","editeur":"Technology Innovation Institute","page":"https://quelleia.com/modeles/falcon-7b/","score_publie":0.646,"score_0_1":0.646,"niveau_suggere":-33.4,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":33,"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":0.64,"score_0_1":0.64,"niveau_suggere":-35.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":34,"modele":"mpt-7b","nom":"MPT-7B","editeur":"MosaicML","page":"https://quelleia.com/modeles/mpt-7b/","score_publie":0.616,"score_0_1":0.616,"niveau_suggere":-45.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":4,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":35,"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":0.581,"score_0_1":0.581,"niveau_suggere":-58.6,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":36,"modele":"gopher-280b","nom":"Gopher (280B)","editeur":"DeepMind","page":"https://quelleia.com/modeles/gopher-280b/","score_publie":0.572,"score_0_1":0.572,"niveau_suggere":-61.9,"reflexion":"inconnue","harnais":null,"configurations_mesurees":5,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":37,"modele":"gemma-2b","nom":"Gemma 2B","editeur":"Google DeepMind","page":"https://quelleia.com/modeles/gemma-2b/","score_publie":0.532,"score_0_1":0.532,"niveau_suggere":-76.8,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"},{"rang":38,"modele":"phi-2","nom":"Phi-2","editeur":"Microsoft","page":"https://quelleia.com/modeles/phi-2/","score_publie":0.452,"score_0_1":0.452,"niveau_suggere":-106.2,"reflexion":"inconnue","harnais":null,"configurations_mesurees":1,"date":null,"source":"https://epoch.ai/benchmarks"}]}