{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/modeles/gpt-5/","edition":"2026-W40","date":"2026-09-28","echelle":"Score IA : 100 pour le meilleur modèle au lancement du site, 50 pour GPT-4o de novembre 2024. bas et haut bornent l'intervalle à 90 %.","licence":"Réutilisation libre en citant « Quelle IA, quelleia.com » et la date de l'édition. Les mesures renvoient à leurs sources d'origine.","modele":{"liens":[{"type":"essayer","libelle":"Application de l'éditeur : ChatGPT","url":"https://chatgpt.com"},{"type":"openrouter","libelle":"Utiliser par API sur OpenRouter","url":"https://openrouter.ai/openai/gpt-5"},{"type":"api","libelle":"Documentation de l'API (OpenAI)","url":"https://platform.openai.com/docs"},{"type":"editeur","libelle":"Site de l'éditeur (OpenAI)","url":"https://openai.com"}],"id":"gpt-5","nom":"GPT-5","editeur":"OpenAI","pays":"États-Unis","date_sortie":"2025-08-07","nouveau":false,"poids_ouverts":false,"acces":"API access","licence":"proprietary","local":null,"prix_eur_par_million":{"entree":1.0838,"sortie":8.6707},"hebergeable_ue":true,"classe_energie":"E","contexte_jetons":400000,"entrees":["text","image"],"niveaux_reflexion":["minimal","low","medium","high"],"connaissances_jusqu_a":"2024-09-30","general":{"score":79.8,"bas":77.9,"haut":81.6,"mesures":42,"poids_couvert":100,"sources":31,"provisoire":false,"historique":false,"rang":59,"groupe":7},"taches":{"raisonnement":{"score":79,"bas":75.5,"haut":82.4,"mesures":9,"benchmarks_tache":9,"couverture":100,"provisoire":false,"rang":46},"code":{"score":78.2,"bas":75,"haut":81.4,"mesures":6,"benchmarks_tache":13,"couverture":46,"provisoire":false,"rang":42},"agents":{"score":78.5,"bas":68.9,"haut":88,"mesures":5,"benchmarks_tache":9,"couverture":56,"provisoire":false,"rang":17},"usage":{"score":78.7,"bas":70.5,"haut":86.9,"mesures":1,"benchmarks_tache":1,"couverture":100,"provisoire":false,"rang":72},"maths":{"score":82.6,"bas":81,"haut":84.3,"mesures":7,"benchmarks_tache":8,"couverture":88,"provisoire":false,"rang":40},"sciences":{"score":80.6,"bas":75.4,"haut":85.7,"mesures":4,"benchmarks_tache":5,"couverture":80,"provisoire":false,"rang":40},"francais":{"score":74.8,"bas":65.1,"haut":84.5,"mesures":7,"benchmarks_tache":10,"couverture":81,"provisoire":false,"rang":48},"vision":{"score":77.7,"bas":69.5,"haut":85.9,"mesures":1,"benchmarks_tache":3,"couverture":33,"provisoire":true},"ecriture":{"score":77.2,"bas":69,"haut":85.4,"mesures":1,"benchmarks_tache":1,"couverture":100,"provisoire":false,"rang":80},"web":{"score":78.5,"bas":73.6,"haut":83.3,"mesures":1,"benchmarks_tache":1,"couverture":100,"provisoire":false,"rang":64}},"reflexions_mesurees":["elevee","faible","moyenne"],"harnais_mesures":["Codex CLI","OpenHands","Terminus 2","mini-SWE-agent"],"mesures":[{"benchmark":"math_level_5","tache":"maths","etat":"archive","score_publie":0.9813066465256798,"score_0_1":0.9813,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2025-10-29","source":"https://epoch.ai/benchmarks","niveau_suggere":80.6},{"benchmark":"math_level_5","tache":"maths","etat":"archive","score_publie":0.9792296072507553,"score_0_1":0.9792,"reflexion":"moyenne","harnais":null,"provenance":"independant","date":"2025-08-20","source":"https://epoch.ai/benchmarks","niveau_suggere":79.7},{"benchmark":"euroeval_allocine","tache":"francais","etat":"sature","score_publie":97.33,"score_0_1":0.9733,"reflexion":"elevee","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":89.2},{"benchmark":"fiction_livebench","tache":"donnees","etat":"archive","score_publie":0.972,"score_0_1":0.972,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":100.9},{"benchmark":"euroeval_allocine","tache":"francais","etat":"sature","score_publie":97.1,"score_0_1":0.971,"reflexion":"faible","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":85.1},{"benchmark":"euroeval_allocine","tache":"francais","etat":"sature","score_publie":97.1,"score_0_1":0.971,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":85.1},{"benchmark":"otis_mock_aime_2024_2025","tache":"maths","etat":"sature","score_publie":0.9138888888888888,"score_0_1":0.9138,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2025-10-29","source":"https://epoch.ai/benchmarks","niveau_suggere":78.5},{"benchmark":"aider_polyglot","tache":"code","etat":"archive","score_publie":88,"score_0_1":0.88,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://aider.chat/docs/leaderboards/","niveau_suggere":81.1},{"benchmark":"otis_mock_aime_2024_2025","tache":"maths","etat":"sature","score_publie":0.8722222222222222,"score_0_1":0.8721,"reflexion":"moyenne","harnais":null,"provenance":"independant","date":"2025-08-07","source":"https://epoch.ai/benchmarks","niveau_suggere":75.5},{"benchmark":"aider_polyglot","tache":"code","etat":"archive","score_publie":86.7,"score_0_1":0.867,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://aider.chat/docs/leaderboards/","niveau_suggere":80.1},{"benchmark":"lech_mazur_writing","tache":"ecriture","etat":"archive","score_publie":8.6,"score_0_1":0.86,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":87.6},{"benchmark":"dtbench","tache":"raisonnement","etat":"sature","score_publie":0.9067,"score_0_1":0.8445,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/dtbench","niveau_suggere":86.1},{"benchmark":"gpqa_diamond","tache":"sciences","etat":"actif","score_publie":0.8617424242424242,"score_0_1":0.8157,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2025-10-29","source":"https://epoch.ai/benchmarks","niveau_suggere":78.3},{"benchmark":"aider_polyglot","tache":"code","etat":"archive","score_publie":81.3,"score_0_1":0.813,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://aider.chat/docs/leaderboards/","niveau_suggere":76.8},{"benchmark":"geobench","tache":"vision","etat":"archive","score_publie":0.81,"score_0_1":0.81,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":93.6},{"benchmark":"gpqa_diamond","tache":"sciences","etat":"actif","score_publie":0.8535353535353535,"score_0_1":0.8047,"reflexion":"moyenne","harnais":null,"provenance":"independant","date":"2025-08-07","source":"https://epoch.ai/benchmarks","niveau_suggere":77.4},{"benchmark":"euroeval_hellaswag_fr","tache":"francais","etat":"actif","score_publie":76.43,"score_0_1":0.7643,"reflexion":"elevee","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":76.5},{"benchmark":"euroeval_hellaswag_fr","tache":"francais","etat":"actif","score_publie":75.02,"score_0_1":0.7502,"reflexion":"faible","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":74},{"benchmark":"swe_bench_verified","tache":"code","etat":"actif","score_publie":0.7355371900826446,"score_0_1":0.7355,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-02-06","source":"https://epoch.ai/benchmarks","niveau_suggere":81.3},{"benchmark":"euroeval_hellaswag_fr","tache":"francais","etat":"actif","score_publie":73.34,"score_0_1":0.7334,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":71.1},{"benchmark":"swe_bench_verified","tache":"code","etat":"actif","score_publie":0.7148760330578512,"score_0_1":0.7149,"reflexion":"moyenne","harnais":null,"provenance":"independant","date":"2026-02-05","source":"https://epoch.ai/benchmarks","niveau_suggere":79.4},{"benchmark":"euroeval_eltec","tache":"francais","etat":"actif","score_publie":71.04,"score_0_1":0.7104,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":83.3},{"benchmark":"euroeval_eltec","tache":"francais","etat":"actif","score_publie":70.5,"score_0_1":0.705,"reflexion":"elevee","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":81.2},{"benchmark":"metr_time_horizons","tache":"agents","etat":"actif","score_publie":0.696053,"score_0_1":0.6961,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":80.5},{"benchmark":"metr_time_horizons","tache":"agents","etat":"actif","score_publie":0.693697,"score_0_1":0.6937,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":80.3},{"benchmark":"euroeval_fquad","tache":"francais","etat":"actif","score_publie":66.3,"score_0_1":0.663,"reflexion":"faible","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":49.7},{"benchmark":"arc_agi","tache":"raisonnement","etat":"sature","score_publie":0.6567000000000001,"score_0_1":0.6567,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://arcprize.org/leaderboard","niveau_suggere":77.8},{"benchmark":"euroeval_fquad","tache":"francais","etat":"actif","score_publie":63.98,"score_0_1":0.6398,"reflexion":"elevee","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":37.3},{"benchmark":"euroeval_fquad","tache":"francais","etat":"actif","score_publie":63.08,"score_0_1":0.6308,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":32.6},{"benchmark":"euroeval_eltec","tache":"francais","etat":"actif","score_publie":62.89,"score_0_1":0.6289,"reflexion":"faible","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":54.5},{"benchmark":"gpqa_diamond","tache":"sciences","etat":"actif","score_publie":0.7171717171717171,"score_0_1":0.6229,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-07-20","source":"https://epoch.ai/benchmarks","niveau_suggere":66.7},{"benchmark":"weirdml","tache":"code","etat":"actif","score_publie":0.6070000000000001,"score_0_1":0.607,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://htihle.github.io/weirdml.html","niveau_suggere":81.9},{"benchmark":"frontiermath","tache":"maths","etat":"actif","score_publie":0.3241379310344827,"score_0_1":0.5687,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2025-11-13","source":"https://epoch.ai/benchmarks","niveau_suggere":81.9},{"benchmark":"arc_agi","tache":"raisonnement","etat":"sature","score_publie":0.5617,"score_0_1":0.5617,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://arcprize.org/leaderboard","niveau_suggere":75.4},{"benchmark":"frontiermath_tiers_1_3_v2","tache":"maths","etat":"actif","score_publie":0.5543859649122806,"score_0_1":0.5544,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-06-10","source":"https://epoch.ai/benchmarks","niveau_suggere":83.4},{"benchmark":"arena_expert","tache":"sciences","etat":"actif","score_publie":1459.5,"score_0_1":0.553,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":77.6},{"benchmark":"arena_texte","tache":"usage","etat":"actif","score_publie":1434.4,"score_0_1":0.5465,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":77.4},{"benchmark":"arena_maths","tache":"maths","etat":"actif","score_publie":1434,"score_0_1":0.5435,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":76.4},{"benchmark":"arena_texte","tache":"usage","etat":"actif","score_publie":1426.8,"score_0_1":0.5356,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":75.6},{"benchmark":"arena_code","tache":"code","etat":"actif","score_publie":1470.2,"score_0_1":0.5331,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":75},{"benchmark":"arena_expert","tache":"sciences","etat":"actif","score_publie":1443.7,"score_0_1":0.5305,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":74.6},{"benchmark":"arena_ecriture","tache":"ecriture","etat":"actif","score_publie":1389.8,"score_0_1":0.527,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":74.3},{"benchmark":"arena_francais","tache":"francais","etat":"actif","score_publie":1444.8,"score_0_1":0.527,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":74.9},{"benchmark":"arena_code","tache":"code","etat":"actif","score_publie":1462.1,"score_0_1":0.5214,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":73.3},{"benchmark":"arena_francais","tache":"francais","etat":"actif","score_publie":1440,"score_0_1":0.5201,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":73.9},{"benchmark":"arena_maths","tache":"maths","etat":"actif","score_publie":1408.9,"score_0_1":0.5075,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":71.3},{"benchmark":"comparia","tache":"francais","etat":"actif","score_publie":1030,"score_0_1":0.5072,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arene.comparia.beta.gouv.fr/ranking","niveau_suggere":75.7},{"benchmark":"arena_ecriture","tache":"ecriture","etat":"actif","score_publie":1372.5,"score_0_1":0.5022,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":70.4},{"benchmark":"simpleqa_verified","tache":"donnees","etat":"actif","score_publie":0.501,"score_0_1":0.501,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-08-27","source":"https://epoch.ai/benchmarks","niveau_suggere":87.5},{"benchmark":"arena_vision","tache":"vision","etat":"actif","score_publie":1225.5,"score_0_1":0.4993,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":"2026-09-28","source":"https://arena.ai/leaderboard","niveau_suggere":75.3},{"benchmark":"terminal_bench","tache":"code","etat":"actif","score_publie":0.49606741573,"score_0_1":0.4961,"reflexion":"inconnue","harnais":"Codex CLI","provenance":"externe","date":"2025-08-07","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","niveau_suggere":78},{"benchmark":"deepresearch_bench","tache":"agents","etat":"actif","score_publie":0.496,"score_0_1":0.496,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://evals.futuresearch.ai/#drb","niveau_suggere":91.2},{"benchmark":"terminal_bench","tache":"code","etat":"actif","score_publie":0.496,"score_0_1":0.496,"reflexion":"moyenne","harnais":"Codex CLI","provenance":"externe","date":"2025-11-04","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","niveau_suggere":78},{"benchmark":"vpct","tache":"vision","etat":"archive","score_publie":0.66,"score_0_1":0.49,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":81.2},{"benchmark":"deepresearch_bench","tache":"agents","etat":"actif","score_publie":0.489,"score_0_1":0.489,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://evals.futuresearch.ai/#drb","niveau_suggere":88.7},{"benchmark":"deepresearch_bench","tache":"agents","etat":"actif","score_publie":0.486,"score_0_1":0.486,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://evals.futuresearch.ai/#drb","niveau_suggere":87.6},{"benchmark":"deepresearch_bench","tache":"agents","etat":"actif","score_publie":0.481,"score_0_1":0.481,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://evals.futuresearch.ai/#drb","niveau_suggere":85.9},{"benchmark":"simplebench","tache":"raisonnement","etat":"actif","score_publie":0.5670000000000001,"score_0_1":0.4804,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://lmcouncil.ai/benchmarks","niveau_suggere":81.1},{"benchmark":"frontiermath","tache":"maths","etat":"actif","score_publie":0.2724137931034482,"score_0_1":0.4779,"reflexion":"moyenne","harnais":null,"provenance":"independant","date":"2025-11-13","source":"https://epoch.ai/benchmarks","niveau_suggere":79.7},{"benchmark":"arena_vision","tache":"vision","etat":"actif","score_publie":1210,"score_0_1":0.477,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-09-28","source":"https://arena.ai/leaderboard","niveau_suggere":71.7},{"benchmark":"lmca","tache":"raisonnement","etat":"actif","score_publie":39.99,"score_0_1":0.4705,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/lmca","niveau_suggere":80.1},{"benchmark":"arena_webdev","tache":"web","etat":"actif","score_publie":1417.1,"score_0_1":0.4675,"reflexion":"moyenne","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":78.4},{"benchmark":"otis_mock_aime_2024_2025","tache":"maths","etat":"sature","score_publie":0.4666666666666667,"score_0_1":0.4661,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-07-20","source":"https://epoch.ai/benchmarks","niveau_suggere":61.4},{"benchmark":"vpct","tache":"vision","etat":"archive","score_publie":0.632,"score_0_1":0.448,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":80.5},{"benchmark":"arc_agi","tache":"raisonnement","etat":"sature","score_publie":0.44,"score_0_1":0.44,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":72.6},{"benchmark":"terminal_bench","tache":"code","etat":"actif","score_publie":0.438202247191,"score_0_1":0.4382,"reflexion":"inconnue","harnais":"OpenHands","provenance":"externe","date":"2025-08-07","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","niveau_suggere":76.1},{"benchmark":"terminal_bench","tache":"code","etat":"actif","score_publie":0.438,"score_0_1":0.438,"reflexion":"moyenne","harnais":"OpenHands","provenance":"externe","date":"2025-11-02","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","niveau_suggere":76.1},{"benchmark":"scicode","tache":"code","etat":"actif","score_publie":0.429398148148148,"score_0_1":0.4294,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://artificialanalysis.ai/evaluations/scicode","niveau_suggere":74.9},{"benchmark":"euroeval_scala_fr","tache":"francais","etat":"actif","score_publie":42.46,"score_0_1":0.4246,"reflexion":"faible","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":50.9},{"benchmark":"weirdml","tache":"code","etat":"actif","score_publie":0.3977,"score_0_1":0.3977,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://htihle.github.io/weirdml.html","niveau_suggere":67.6},{"benchmark":"frontiermath_tiers_1_3_v2","tache":"maths","etat":"actif","score_publie":0.3719298245614035,"score_0_1":0.3719,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-08-27","source":"https://epoch.ai/benchmarks","niveau_suggere":77.8},{"benchmark":"euroeval_scala_fr","tache":"francais","etat":"actif","score_publie":36.68,"score_0_1":0.3668,"reflexion":"elevee","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":38.1},{"benchmark":"terminal_bench","tache":"code","etat":"actif","score_publie":0.352,"score_0_1":0.352,"reflexion":"moyenne","harnais":"Terminus 2","provenance":"externe","date":"2025-10-31","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","niveau_suggere":73.2},{"benchmark":"terminal_bench","tache":"code","etat":"actif","score_publie":0.3516853932579999,"score_0_1":0.3517,"reflexion":"inconnue","harnais":"Terminus 2","provenance":"externe","date":"2025-08-07","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","niveau_suggere":73.2},{"benchmark":"gdpval","tache":"agents","etat":"archive","score_publie":0.348,"score_0_1":0.348,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":77.5},{"benchmark":"terminal_bench","tache":"code","etat":"actif","score_publie":0.339325842697,"score_0_1":0.3393,"reflexion":"inconnue","harnais":"mini-SWE-agent","provenance":"externe","date":"2025-08-07","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","niveau_suggere":72.7},{"benchmark":"terminal_bench","tache":"code","etat":"actif","score_publie":0.339,"score_0_1":0.339,"reflexion":"moyenne","harnais":"mini-SWE-agent","provenance":"externe","date":"2025-11-03","source":"https://www.tbench.ai/leaderboard/terminal-bench/2.0","niveau_suggere":72.7},{"benchmark":"chess_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.37,"score_0_1":0.3371,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2025-12-08","source":"https://epoch.ai/benchmarks","niveau_suggere":87.6},{"benchmark":"euroeval_scala_fr","tache":"francais","etat":"actif","score_publie":33.5,"score_0_1":0.335,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":30.8},{"benchmark":"balrog","tache":"agents","etat":"actif","score_publie":0.3279999999999999,"score_0_1":0.328,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://balrogai.com/","niveau_suggere":65.8},{"benchmark":"chess_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.29,"score_0_1":0.2529,"reflexion":"moyenne","harnais":null,"provenance":"independant","date":"2026-07-15","source":"https://epoch.ai/benchmarks","niveau_suggere":83.5},{"benchmark":"forecastbench","tache":"raisonnement","etat":"actif","score_publie":61.4,"score_0_1":0.228,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":90.4},{"benchmark":"frontiermath_tier_4_v2","tache":"maths","etat":"sature","score_publie":0.2195121951219512,"score_0_1":0.2195,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-06-11","source":"https://epoch.ai/benchmarks","niveau_suggere":84.8},{"benchmark":"hle","tache":"sciences","etat":"actif","score_publie":0.2532,"score_0_1":0.2155,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":81.2},{"benchmark":"hle","tache":"sciences","etat":"actif","score_publie":0.2532,"score_0_1":0.2155,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":81.2},{"benchmark":"frontiermath_tier_4","tache":"maths","etat":"actif","score_publie":0.125,"score_0_1":0.2083,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2025-10-30","source":"https://epoch.ai/benchmarks","niveau_suggere":83.1},{"benchmark":"chess_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.24,"score_0_1":0.2003,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-07-15","source":"https://epoch.ai/benchmarks","niveau_suggere":80.4},{"benchmark":"frontiermath_tiers_1_3_v2","tache":"maths","etat":"actif","score_publie":0.1824561403508772,"score_0_1":0.1825,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-08-27","source":"https://epoch.ai/benchmarks","niveau_suggere":70.3},{"benchmark":"proofbench","tache":"maths","etat":"sature","score_publie":0.18,"score_0_1":0.18,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://www.vals.ai/benchmarks/proof_bench","niveau_suggere":82},{"benchmark":"mystery_game_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.23,"score_0_1":0.1518,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-08-05","source":"https://epoch.ai/benchmarks","niveau_suggere":84},{"benchmark":"ebr_bench","tache":"agents","etat":"actif","score_publie":0.126984,"score_0_1":0.127,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-06-29","source":"https://epoch.ai/benchmarks","niveau_suggere":85.1},{"benchmark":"critpt","tache":"sciences","etat":"actif","score_publie":0.126,"score_0_1":0.126,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":85.5},{"benchmark":"chess_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.16,"score_0_1":0.1162,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-07-15","source":"https://epoch.ai/benchmarks","niveau_suggere":73.8},{"benchmark":"enigmaeval","tache":"raisonnement","etat":"actif","score_publie":0.1047,"score_0_1":0.1047,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://labs.scale.com/leaderboard/enigma_eval","niveau_suggere":79.3},{"benchmark":"frontiermath_tier_4","tache":"maths","etat":"actif","score_publie":0.0625,"score_0_1":0.1042,"reflexion":"moyenne","harnais":null,"provenance":"independant","date":"2025-08-07","source":"https://epoch.ai/benchmarks","niveau_suggere":78.8},{"benchmark":"arc_agi_2","tache":"raisonnement","etat":"sature","score_publie":0.0986,"score_0_1":0.0986,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":75.3},{"benchmark":"arc_agi_2","tache":"raisonnement","etat":"sature","score_publie":0.0749,"score_0_1":0.0749,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":73.9},{"benchmark":"mystery_game_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.16,"score_0_1":0.0747,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-08-27","source":"https://epoch.ai/benchmarks","niveau_suggere":78.9},{"benchmark":"gso_bench","tache":"code","etat":"actif","score_publie":0.0686,"score_0_1":0.0686,"reflexion":"elevee","harnais":"OpenHands","provenance":"externe","date":null,"source":"https://gso-bench.github.io/index.html","niveau_suggere":74.3},{"benchmark":"mystery_game_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.15,"score_0_1":0.0637,"reflexion":"moyenne","harnais":null,"provenance":"independant","date":"2026-08-27","source":"https://epoch.ai/benchmarks","niveau_suggere":77.8},{"benchmark":"arc_agi","tache":"raisonnement","etat":"sature","score_publie":0.06,"score_0_1":0.06,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":57.8},{"benchmark":"mystery_game_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.14,"score_0_1":0.0527,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-08-27","source":"https://epoch.ai/benchmarks","niveau_suggere":76.6},{"benchmark":"arc_agi_2","tache":"raisonnement","etat":"sature","score_publie":0.0194,"score_0_1":0.0194,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":67.7},{"benchmark":"arc_agi_2","tache":"raisonnement","etat":"sature","score_publie":0.0194,"score_0_1":0.0194,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":67.7},{"benchmark":"remote_labor_index","tache":"agents","etat":"actif","score_publie":0.0167,"score_0_1":0.0167,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":80.3},{"benchmark":"arc_agi_2","tache":"raisonnement","etat":"sature","score_publie":0,"score_0_1":0,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":64.7},{"benchmark":"critpt","tache":"sciences","etat":"actif","score_publie":0,"score_0_1":0,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":61.2}],"qualite_prix":{"prix_mixte_eur":2.981,"score_attendu":84.8,"avantage":-5,"avantage_bas":-6.9,"avantage_haut":-3.2,"meilleur_compromis":false,"rang":89}}}