{"source":"Quelle IA, le classement des modèles de langage","page":"https://quelleia.com/modeles/gpt-5-6-sol/","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":"Essayer sur ChatGPT","url":"https://chatgpt.com"},{"type":"openrouter","libelle":"Utiliser par API sur OpenRouter","url":"https://openrouter.ai/openai/gpt-5.6-sol"},{"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-5-6-sol","nom":"GPT-5.6 Sol","editeur":"OpenAI","pays":"États-Unis","date_sortie":"2026-07-09","nouveau":false,"poids_ouverts":false,"acces":"API access","licence":null,"local":null,"prix_eur_par_million":{"entree":3.51,"sortie":17.56},"hebergeable_ue":null,"classe_energie":null,"contexte_jetons":1050000,"entrees":["text","image","pdf"],"niveaux_reflexion":["none","low","medium","high","xhigh","max"],"connaissances_jusqu_a":"2026-02-16","general":{"score":93.9,"bas":92.5,"haut":95.2,"mesures":49,"poids_couvert":100,"sources":35,"provisoire":false,"historique":false,"rang":8,"groupe":3},"taches":{"raisonnement":{"score":96.2,"bas":93.8,"haut":98.6,"mesures":8,"benchmarks_tache":9,"couverture":89,"provisoire":false,"rang":3},"code":{"score":91.3,"bas":89.3,"haut":93.2,"mesures":10,"benchmarks_tache":13,"couverture":77,"provisoire":false,"rang":10},"agents":{"score":93.6,"bas":91.1,"haut":96.1,"mesures":6,"benchmarks_tache":9,"couverture":67,"provisoire":false,"rang":5},"usage":{"score":91.8,"bas":83.7,"haut":99.9,"mesures":1,"benchmarks_tache":1,"couverture":100,"provisoire":false,"rang":7},"maths":{"score":96,"bas":93.1,"haut":98.8,"mesures":6,"benchmarks_tache":8,"couverture":75,"provisoire":false,"rang":7},"sciences":{"score":97,"bas":92.2,"haut":101.8,"mesures":4,"benchmarks_tache":5,"couverture":80,"provisoire":false,"rang":1},"francais":{"score":94.1,"bas":83,"haut":105.2,"mesures":9,"benchmarks_tache":10,"couverture":75,"provisoire":false,"rang":6},"vision":{"score":94.9,"bas":92.7,"haut":97.1,"mesures":3,"benchmarks_tache":3,"couverture":100,"provisoire":false,"rang":4},"ecriture":{"score":93.1,"bas":85,"haut":101.2,"mesures":1,"benchmarks_tache":1,"couverture":100,"provisoire":false,"rang":8},"web":{"score":92.6,"bas":86.6,"haut":98.5,"mesures":1,"benchmarks_tache":1,"couverture":100,"provisoire":false,"rang":15}},"reflexions_mesurees":["elevee","faible","maximale","moyenne","sans"],"harnais_mesures":["Codex CLI","mini-SWE-agent","proximus"],"mesures":[{"benchmark":"otis_mock_aime_2024_2025","tache":"maths","etat":"sature","score_publie":1,"score_0_1":1,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-07-09","source":"https://epoch.ai/benchmarks","niveau_suggere":93.8},{"benchmark":"arc_agi","tache":"raisonnement","etat":"sature","score_publie":0.975,"score_0_1":0.975,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://arcprize.org/leaderboard","niveau_suggere":95.5},{"benchmark":"arc_agi","tache":"raisonnement","etat":"sature","score_publie":0.975,"score_0_1":0.975,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://arcprize.org/leaderboard","niveau_suggere":95.5},{"benchmark":"arc_agi","tache":"raisonnement","etat":"sature","score_publie":0.97,"score_0_1":0.97,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://arcprize.org/leaderboard","niveau_suggere":94.4},{"benchmark":"euroeval_allocine","tache":"francais","etat":"sature","score_publie":96.7,"score_0_1":0.967,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":78.7},{"benchmark":"arc_agi","tache":"raisonnement","etat":"sature","score_publie":0.965,"score_0_1":0.965,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://arcprize.org/leaderboard","niveau_suggere":93.5},{"benchmark":"otis_mock_aime_2024_2025","tache":"maths","etat":"sature","score_publie":0.9555555555555556,"score_0_1":0.9555,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-08-07","source":"https://epoch.ai/benchmarks","niveau_suggere":83.3},{"benchmark":"dtbench","tache":"raisonnement","etat":"sature","score_publie":0.96,"score_0_1":0.9333,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/dtbench","niveau_suggere":99.5},{"benchmark":"surface_evolver_bench","tache":"sciences","etat":"sature","score_publie":0.93125,"score_0_1":0.9313,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://yhenon.github.io/surface-evolver-llm-eval/","niveau_suggere":103.2},{"benchmark":"dtbench","tache":"raisonnement","etat":"sature","score_publie":0.9573,"score_0_1":0.9288,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/dtbench","niveau_suggere":98.5},{"benchmark":"arc_agi_2","tache":"raisonnement","etat":"sature","score_publie":0.925,"score_0_1":0.925,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":96.1},{"benchmark":"arc_agi","tache":"raisonnement","etat":"sature","score_publie":0.925,"score_0_1":0.925,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://arcprize.org/leaderboard","niveau_suggere":88.8},{"benchmark":"dtbench","tache":"raisonnement","etat":"sature","score_publie":0.9547,"score_0_1":0.9245,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/dtbench","niveau_suggere":97.6},{"benchmark":"dtbench","tache":"raisonnement","etat":"sature","score_publie":0.9547,"score_0_1":0.9245,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/dtbench","niveau_suggere":97.6},{"benchmark":"dtbench","tache":"raisonnement","etat":"sature","score_publie":0.952,"score_0_1":0.92,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/dtbench","niveau_suggere":96.7},{"benchmark":"gpqa_diamond","tache":"sciences","etat":"actif","score_publie":0.9349747474747476,"score_0_1":0.9133,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-07-09","source":"https://epoch.ai/benchmarks","niveau_suggere":88.4},{"benchmark":"arc_agi_2","tache":"raisonnement","etat":"sature","score_publie":0.9,"score_0_1":0.9,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":94.8},{"benchmark":"arc_agi_2","tache":"raisonnement","etat":"sature","score_publie":0.9,"score_0_1":0.9,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":94.8},{"benchmark":"dtbench","tache":"raisonnement","etat":"sature","score_publie":0.9387,"score_0_1":0.8978,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/dtbench","niveau_suggere":92.9},{"benchmark":"weirdml","tache":"code","etat":"actif","score_publie":0.8943000000000001,"score_0_1":0.8943,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://htihle.github.io/weirdml.html","niveau_suggere":110.7},{"benchmark":"frontiermath_tiers_1_3_v2","tache":"maths","etat":"actif","score_publie":0.8912280701754386,"score_0_1":0.8912,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-07-09","source":"https://epoch.ai/benchmarks","niveau_suggere":97.8},{"benchmark":"weirdml","tache":"code","etat":"actif","score_publie":0.8876000000000001,"score_0_1":0.8876,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://htihle.github.io/weirdml.html","niveau_suggere":109.5},{"benchmark":"weirdml","tache":"code","etat":"actif","score_publie":0.8697,"score_0_1":0.8697,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://htihle.github.io/weirdml.html","niveau_suggere":106.7},{"benchmark":"gpqa_diamond","tache":"sciences","etat":"actif","score_publie":0.898989898989899,"score_0_1":0.8653,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-08-07","source":"https://epoch.ai/benchmarks","niveau_suggere":82.6},{"benchmark":"arc_agi_2","tache":"raisonnement","etat":"sature","score_publie":0.8542000000000001,"score_0_1":0.8542,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":92.9},{"benchmark":"euroeval_include_fr","tache":"francais","etat":"actif","score_publie":84.14,"score_0_1":0.8414,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":101.3},{"benchmark":"euroeval_multiloko_fr","tache":"francais","etat":"actif","score_publie":83.28,"score_0_1":0.8328,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":107.6},{"benchmark":"proofbench","tache":"maths","etat":"sature","score_publie":0.8300000000000001,"score_0_1":0.83,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://www.vals.ai/benchmarks/proof_bench","niveau_suggere":94.1},{"benchmark":"frontiermath_tier_4_v2","tache":"maths","etat":"sature","score_publie":0.8292682926829268,"score_0_1":0.8293,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-07-09","source":"https://epoch.ai/benchmarks","niveau_suggere":97.1},{"benchmark":"euroeval_hellaswag_fr","tache":"francais","etat":"actif","score_publie":80.85,"score_0_1":0.8085,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":85.2},{"benchmark":"frontiermath_tier_4_v2","tache":"maths","etat":"sature","score_publie":0.8048780487804879,"score_0_1":0.8049,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-07-09","source":"https://epoch.ai/benchmarks","niveau_suggere":96.4},{"benchmark":"euroeval_eltec","tache":"francais","etat":"actif","score_publie":80.39,"score_0_1":0.8039,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":123.3},{"benchmark":"gpqa_diamond","tache":"sciences","etat":"actif","score_publie":0.8282828282828283,"score_0_1":0.771,"reflexion":"sans","harnais":null,"provenance":"independant","date":"2026-08-07","source":"https://epoch.ai/benchmarks","niveau_suggere":75.1},{"benchmark":"arc_agi","tache":"raisonnement","etat":"sature","score_publie":0.745,"score_0_1":0.745,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://arcprize.org/leaderboard","niveau_suggere":80.3},{"benchmark":"arena_webdev","tache":"web","etat":"actif","score_publie":1619.3,"score_0_1":0.7377,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":92.2},{"benchmark":"dtbench","tache":"raisonnement","etat":"sature","score_publie":0.8373,"score_0_1":0.7288,"reflexion":"sans","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/dtbench","niveau_suggere":76.1},{"benchmark":"deepswe","tache":"code","etat":"actif","score_publie":0.7266666666666667,"score_0_1":0.7267,"reflexion":"maximale","harnais":"mini-SWE-agent","provenance":"externe","date":null,"source":"https://deepswe.datacurve.ai/","niveau_suggere":94},{"benchmark":"deepswe","tache":"code","etat":"actif","score_publie":0.7073170731707318,"score_0_1":0.7073,"reflexion":"maximale","harnais":"mini-SWE-agent","provenance":"externe","date":null,"source":"https://deepswe.datacurve.ai/","niveau_suggere":93.2},{"benchmark":"simpleqa_verified","tache":"donnees","etat":"actif","score_publie":0.697,"score_0_1":0.697,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-08-10","source":"https://epoch.ai/benchmarks","niveau_suggere":100.9},{"benchmark":"lmca","tache":"raisonnement","etat":"actif","score_publie":59.21,"score_0_1":0.6966,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/lmca","niveau_suggere":95.9},{"benchmark":"deepswe","tache":"code","etat":"actif","score_publie":0.6940133037694013,"score_0_1":0.694,"reflexion":"elevee","harnais":"mini-SWE-agent","provenance":"externe","date":null,"source":"https://deepswe.datacurve.ai/","niveau_suggere":92.7},{"benchmark":"otis_mock_aime_2024_2025","tache":"maths","etat":"sature","score_publie":0.6888888888888889,"score_0_1":0.6886,"reflexion":"sans","harnais":null,"provenance":"independant","date":"2026-08-07","source":"https://epoch.ai/benchmarks","niveau_suggere":67.8},{"benchmark":"lmca","tache":"raisonnement","etat":"actif","score_publie":58.49,"score_0_1":0.6881,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/lmca","niveau_suggere":95.2},{"benchmark":"lmca","tache":"raisonnement","etat":"actif","score_publie":58.43,"score_0_1":0.6874,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/lmca","niveau_suggere":95.2},{"benchmark":"euroeval_fquad","tache":"francais","etat":"actif","score_publie":67.84,"score_0_1":0.6784,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":58.1},{"benchmark":"arc_agi_2","tache":"raisonnement","etat":"sature","score_publie":0.6708,"score_0_1":0.6708,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":88.2},{"benchmark":"lmca","tache":"raisonnement","etat":"actif","score_publie":56.94,"score_0_1":0.6699,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/lmca","niveau_suggere":93.8},{"benchmark":"lmca","tache":"raisonnement","etat":"actif","score_publie":56.4,"score_0_1":0.6635,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/lmca","niveau_suggere":93.3},{"benchmark":"simplebench","tache":"raisonnement","etat":"actif","score_publie":0.7170000000000001,"score_0_1":0.6604,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://lmcouncil.ai/benchmarks","niveau_suggere":91.5},{"benchmark":"simplebench","tache":"raisonnement","etat":"actif","score_publie":0.717,"score_0_1":0.6604,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":91.5},{"benchmark":"lmca","tache":"raisonnement","etat":"actif","score_publie":55.89,"score_0_1":0.6575,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/lmca","niveau_suggere":92.9},{"benchmark":"arena_expert","tache":"sciences","etat":"actif","score_publie":1534.5,"score_0_1":0.6558,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":91.9},{"benchmark":"arena_ecriture","tache":"ecriture","etat":"actif","score_publie":1468.9,"score_0_1":0.6373,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":92.1},{"benchmark":"arena_maths","tache":"maths","etat":"actif","score_publie":1493.1,"score_0_1":0.6259,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":88.6},{"benchmark":"arena_code","tache":"code","etat":"actif","score_publie":1533.7,"score_0_1":0.622,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":88.9},{"benchmark":"chess_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.64,"score_0_1":0.6212,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-07-10","source":"https://epoch.ai/benchmarks","niveau_suggere":99.6},{"benchmark":"lmca","tache":"raisonnement","etat":"actif","score_publie":52.75,"score_0_1":0.6206,"reflexion":"sans","harnais":null,"provenance":"externe","date":null,"source":"https://conceptualreasoning.ai/lmca","niveau_suggere":90.2},{"benchmark":"arena_francais","tache":"francais","etat":"actif","score_publie":1509.1,"score_0_1":0.6174,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":88.7},{"benchmark":"arena_texte","tache":"usage","etat":"actif","score_publie":1483.8,"score_0_1":0.6156,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-09-30","source":"https://arena.ai/leaderboard","niveau_suggere":88.8},{"benchmark":"deepswe","tache":"code","etat":"actif","score_publie":0.6106194690265486,"score_0_1":0.6106,"reflexion":"moyenne","harnais":"mini-SWE-agent","provenance":"externe","date":null,"source":"https://deepswe.datacurve.ai/","niveau_suggere":89.9},{"benchmark":"balrog","tache":"agents","etat":"actif","score_publie":0.6,"score_0_1":0.6,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://balrogai.com/","niveau_suggere":96},{"benchmark":"arena_vision","tache":"vision","etat":"actif","score_publie":1286.8,"score_0_1":0.5866,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-09-28","source":"https://arena.ai/leaderboard","niveau_suggere":89.7},{"benchmark":"simplebench","tache":"raisonnement","etat":"actif","score_publie":0.648,"score_0_1":0.5776,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":86.6},{"benchmark":"simplebench","tache":"raisonnement","etat":"actif","score_publie":0.648,"score_0_1":0.5776,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://lmcouncil.ai/benchmarks","niveau_suggere":86.6},{"benchmark":"scicode","tache":"code","etat":"actif","score_publie":0.570601851851852,"score_0_1":0.5706,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://artificialanalysis.ai/evaluations/scicode","niveau_suggere":91.6},{"benchmark":"scicode","tache":"code","etat":"actif","score_publie":0.569444444444444,"score_0_1":0.5694,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://artificialanalysis.ai/evaluations/scicode","niveau_suggere":91.4},{"benchmark":"scicode","tache":"code","etat":"actif","score_publie":0.564814814814815,"score_0_1":0.5648,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://artificialanalysis.ai/evaluations/scicode","niveau_suggere":90.9},{"benchmark":"scicode","tache":"code","etat":"actif","score_publie":0.560185185185185,"score_0_1":0.5602,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://artificialanalysis.ai/evaluations/scicode","niveau_suggere":90.3},{"benchmark":"scicode","tache":"code","etat":"actif","score_publie":0.554398148148148,"score_0_1":0.5544,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://artificialanalysis.ai/evaluations/scicode","niveau_suggere":89.6},{"benchmark":"mystery_game_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.58,"score_0_1":0.5373,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-07-28","source":"https://epoch.ai/benchmarks","niveau_suggere":95.8},{"benchmark":"chess_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.55,"score_0_1":0.5265,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-07-09","source":"https://epoch.ai/benchmarks","niveau_suggere":95.6},{"benchmark":"vending_bench_2","tache":"agents","etat":"actif","score_publie":9619.368,"score_0_1":0.5263,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":90.2},{"benchmark":"gbaeval","tache":"code","etat":"actif","score_publie":0.5259227864005247,"score_0_1":0.5259,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://gbaeval.com/model/codex-gpt-5-6-sol","niveau_suggere":90.3},{"benchmark":"apex_agents","tache":"agents","etat":"actif","score_publie":0.514,"score_0_1":0.514,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":88.6},{"benchmark":"frontiercode","tache":"code","etat":"actif","score_publie":0.4749,"score_0_1":0.4749,"reflexion":"inconnue","harnais":"Codex CLI","provenance":"externe","date":null,"source":"https://cognition.com/frontiercode","niveau_suggere":93.6},{"benchmark":"scicode","tache":"code","etat":"actif","score_publie":0.471064814814815,"score_0_1":0.4711,"reflexion":"sans","harnais":null,"provenance":"externe","date":null,"source":"https://artificialanalysis.ai/evaluations/scicode","niveau_suggere":79.8},{"benchmark":"deepswe","tache":"code","etat":"actif","score_publie":0.4535398230088495,"score_0_1":0.4535,"reflexion":"faible","harnais":"mini-SWE-agent","provenance":"externe","date":null,"source":"https://deepswe.datacurve.ai/","niveau_suggere":85.1},{"benchmark":"euroeval_scala_fr","tache":"francais","etat":"actif","score_publie":45.35,"score_0_1":0.4535,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":57.1},{"benchmark":"ebr_bench","tache":"agents","etat":"actif","score_publie":0.4476190476190475,"score_0_1":0.4476,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-09-04","source":"https://epoch.ai/benchmarks","niveau_suggere":94.2},{"benchmark":"arc_agi_2","tache":"raisonnement","etat":"sature","score_publie":0.425,"score_0_1":0.425,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":83.7},{"benchmark":"cursorbench","tache":"code","etat":"actif","score_publie":0.417,"score_0_1":0.417,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://cursor.com/cursorbench","niveau_suggere":90.8},{"benchmark":"furniture_assembly","tache":"vision","etat":"actif","score_publie":0.5666666666666667,"score_0_1":0.381,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-09-10","source":"https://epoch.ai/benchmarks","niveau_suggere":95},{"benchmark":"cursorbench","tache":"code","etat":"actif","score_publie":0.377,"score_0_1":0.377,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://cursor.com/cursorbench","niveau_suggere":88},{"benchmark":"euroeval_orange_sum","tache":"francais","etat":"actif","score_publie":37.3,"score_0_1":0.373,"reflexion":"inconnue","harnais":null,"provenance":"independant","date":null,"source":"https://euroeval.com/leaderboards/Monolingual/french/","niveau_suggere":58.2},{"benchmark":"enigmaeval","tache":"raisonnement","etat":"actif","score_publie":0.3712,"score_0_1":0.3712,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://labs.scale.com/leaderboard/enigma_eval","niveau_suggere":95.7},{"benchmark":"posttrainbench","tache":"agents","etat":"actif","score_publie":0.3622999999999999,"score_0_1":0.3623,"reflexion":"maximale","harnais":"Codex CLI","provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":95.1},{"benchmark":"cursorbench","tache":"code","etat":"actif","score_publie":0.357,"score_0_1":0.357,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://cursor.com/cursorbench","niveau_suggere":86.6},{"benchmark":"blueprint_bench_2","tache":"vision","etat":"actif","score_publie":0.336225596529284,"score_0_1":0.3362,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://andonlabs.com/evals/blueprint-bench-2","niveau_suggere":93.1},{"benchmark":"critpt","tache":"sciences","etat":"actif","score_publie":0.322857142857143,"score_0_1":0.3229,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":96.4},{"benchmark":"frontierswe","tache":"code","etat":"actif","score_publie":0.3220246705882353,"score_0_1":0.322,"reflexion":"maximale","harnais":"proximus","provenance":"externe","date":null,"source":"https://www.frontierswe.com/","niveau_suggere":91.7},{"benchmark":"cursorbench","tache":"code","etat":"actif","score_publie":0.311,"score_0_1":0.311,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://cursor.com/cursorbench","niveau_suggere":83.2},{"benchmark":"gdp_pdf","tache":"donnees","etat":"actif","score_publie":0.307,"score_0_1":0.307,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://surgehq.ai/benchmarks/gdp-pdf","niveau_suggere":97.1},{"benchmark":"gdp_pdf","tache":"donnees","etat":"actif","score_publie":0.307,"score_0_1":0.307,"reflexion":"inconnue","harnais":null,"provenance":"externe","date":null,"source":"https://surgehq.ai/benchmarks/gdp-pdf","niveau_suggere":97.1},{"benchmark":"critpt","tache":"sciences","etat":"actif","score_publie":0.286,"score_0_1":0.286,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":94.8},{"benchmark":"osworld_2","tache":"agents","etat":"actif","score_publie":0.2734,"score_0_1":0.2734,"reflexion":"maximale","harnais":null,"provenance":"externe","date":null,"source":"https://osworld-v2.xlang.ai/","niveau_suggere":94.3},{"benchmark":"mystery_game_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.33,"score_0_1":0.262,"reflexion":"sans","harnais":null,"provenance":"independant","date":"2026-08-27","source":"https://epoch.ai/benchmarks","niveau_suggere":88.3},{"benchmark":"critpt","tache":"sciences","etat":"actif","score_publie":0.257142857142857,"score_0_1":0.2571,"reflexion":"elevee","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":93.4},{"benchmark":"cursorbench","tache":"code","etat":"actif","score_publie":0.246,"score_0_1":0.246,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://cursor.com/cursorbench","niveau_suggere":77.9},{"benchmark":"chess_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.27,"score_0_1":0.2319,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-08-07","source":"https://epoch.ai/benchmarks","niveau_suggere":82.3},{"benchmark":"critpt","tache":"sciences","etat":"actif","score_publie":0.228571428571429,"score_0_1":0.2286,"reflexion":"moyenne","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":92},{"benchmark":"mirrorcode","tache":"code","etat":"actif","score_publie":0.2,"score_0_1":0.2,"reflexion":"elevee","harnais":null,"provenance":"independant","date":"2026-08-10","source":"https://epoch.ai/benchmarks","niveau_suggere":89.8},{"benchmark":"mystery_game_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.26,"score_0_1":0.1848,"reflexion":"faible","harnais":null,"provenance":"independant","date":"2026-08-27","source":"https://epoch.ai/benchmarks","niveau_suggere":85.5},{"benchmark":"weirdml_v3","tache":"code","etat":"actif","score_publie":0.1499222454545454,"score_0_1":0.1499,"reflexion":"maximale","harnais":"Codex CLI","provenance":"externe","date":null,"source":"https://htihle.github.io/weirdml.html","niveau_suggere":93.7},{"benchmark":"critpt","tache":"sciences","etat":"actif","score_publie":0.148571428571429,"score_0_1":0.1486,"reflexion":"faible","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":87.2},{"benchmark":"critpt","tache":"sciences","etat":"actif","score_publie":0.0514285714285714,"score_0_1":0.0514,"reflexion":"sans","harnais":null,"provenance":"externe","date":null,"source":"https://epoch.ai/benchmarks","niveau_suggere":76.5},{"benchmark":"chess_puzzles","tache":"raisonnement","etat":"actif","score_publie":0.07,"score_0_1":0.0215,"reflexion":"sans","harnais":null,"provenance":"independant","date":"2026-08-07","source":"https://epoch.ai/benchmarks","niveau_suggere":55.5},{"benchmark":"frontiermath_erdos","tache":"maths","etat":"actif","score_publie":0,"score_0_1":0,"reflexion":"maximale","harnais":null,"provenance":"independant","date":"2026-08-28","source":"https://epoch.ai/benchmarks","niveau_suggere":99.6}],"qualite_prix":{"prix_mixte_eur":7.022,"score_attendu":88.8,"avantage":5.1,"avantage_bas":3.7,"avantage_haut":6.4,"meilleur_compromis":false,"rang":20}}}