{"benchmark_id":"mmlu-prox","name":"MMLU-ProX","parent_benchmark":null,"categories":["math","reasoning","language","legal","finance","general","healthcare"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"Extended version of MMLU-Pro providing additional challenging multiple-choice questions for evaluating language models across diverse academic and professional domains. Built on the foundation of the Massive Multitask Language Understanding benchmark framework.","paper_link":"https://arxiv.org/abs/2406.01574","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:24.829132+00:00","updated_at":"2026-07-05T18:27:54.780699+00:00","statistics":{"total_models":32,"average_score":0.6662687499999999,"min_score":0.081,"max_score":0.87,"score_stddev":0.23025220735518587,"verified_count":0,"self_reported_count":32},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"qwen3.7-max","model_name":"Qwen3.7 Max","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.87,"normalized_score":0.87,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.7","analysis_method":"Average accuracy across 29 languages","verification_date":null,"provider_id":"novita","input_cost_per_million":1.25,"output_cost_per_million":3.75,"context_window":1000000,"announcement_date":"2026-05-19","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":2,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.854,"normalized_score":0.854,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.7-plus","analysis_method":null,"verification_date":null,"provider_id":"together","input_cost_per_million":0.32,"output_cost_per_million":1.28,"context_window":1000000,"announcement_date":"2026-05-31","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Together","best_throughput":null,"throughput_provider":"Together","context_provider":"Together"},{"rank":3,"model_id":"qwen3.6-plus","model_name":"Qwen3.6 Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.847,"normalized_score":0.847,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6","analysis_method":null,"verification_date":null,"provider_id":"together","input_cost_per_million":0.5,"output_cost_per_million":3.0,"context_window":1000000,"announcement_date":"2026-04-02","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Together","best_throughput":null,"throughput_provider":"Together","context_provider":"Together"},{"rank":3,"model_id":"qwen3.5-397b-a17b","model_name":"Qwen3.5-397B-A17B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.847,"normalized_score":0.847,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen3.5/","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-16","param_count":397000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"nemotron-3-ultra-550b-a55b","model_name":"Nemotron 3 Ultra (550B A55B)","organization_id":"nvidia","organization_name":"NVIDIA","organization_country":"US","score":0.83,"normalized_score":0.83,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","analysis_method":"Average over languages","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-06-04","param_count":550000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":6,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.822,"normalized_score":0.822,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":"novita","input_cost_per_million":0.3,"output_cost_per_million":2.4,"context_window":262144,"announcement_date":"2026-02-24","param_count":27000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":6,"model_id":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.822,"normalized_score":0.822,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-24","param_count":122000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":8,"model_id":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3-235B-A22B-Thinking-2507","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.81,"normalized_score":0.81,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen3-thinking/","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-07-25","param_count":235000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":8,"model_id":"qwen3.5-35b-a3b","model_name":"Qwen3.5-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.81,"normalized_score":0.81,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-24","param_count":35000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":10,"model_id":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 235B A22B Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.806,"normalized_score":0.806,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-22","param_count":236000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":11,"model_id":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3-235B-A22B-Instruct-2507","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.794,"normalized_score":0.794,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-07-22","param_count":235000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":12,"model_id":"nemotron-3-super-120b-a12b","model_name":"Nemotron 3 Super (120B A12B)","organization_id":"nvidia","organization_name":"NVIDIA","organization_country":"US","score":0.7936,"normalized_score":0.7936,"verified":false,"self_reported":true,"self_reported_source":"https://build.nvidia.com/nvidia/nemotron-3-super-120b-a12b/modelcard","analysis_method":"Average over languages","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-03-11","param_count":120000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":13,"model_id":"qwen3-next-80b-a3b-thinking","model_name":"Qwen3-Next-80B-A3B-Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.787,"normalized_score":0.787,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen3-next/","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-10","param_count":80000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":14,"model_id":"qwen3-vl-235b-a22b-instruct","model_name":"Qwen3 VL 235B A22B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.778,"normalized_score":0.778,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-22","param_count":236000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":15,"model_id":"qwen3-vl-32b-thinking","model_name":"Qwen3 VL 32B Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.772,"normalized_score":0.772,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-22","param_count":33000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":16,"model_id":"qwen3-next-80b-a3b-instruct","model_name":"Qwen3-Next-80B-A3B-Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.767,"normalized_score":0.767,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen3-next/","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-10","param_count":80000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":17,"model_id":"qwen3.5-9b","model_name":"Qwen3.5-9B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.763,"normalized_score":0.763,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen3.5-9B","analysis_method":"Thinking mode","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-03-02","param_count":9000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":18,"model_id":"qwen3-vl-30b-a3b-thinking","model_name":"Qwen3 VL 30B A3B Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.761,"normalized_score":0.761,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-22","param_count":31000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":19,"model_id":"qwen3-vl-32b-instruct","model_name":"Qwen3 VL 32B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.734,"normalized_score":0.734,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-22","param_count":33000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":20,"model_id":"qwen3.5-4b","model_name":"Qwen3.5-4B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.715,"normalized_score":0.715,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen3.5-4B","analysis_method":"Thinking mode","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-03-02","param_count":4000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":21,"model_id":"qwen3-vl-30b-a3b-instruct","model_name":"Qwen3 VL 30B A3B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.709,"normalized_score":0.709,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-22","param_count":31000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":22,"model_id":"qwen3-vl-8b-thinking","model_name":"Qwen3 VL 8B Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.707,"normalized_score":0.707,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.18,"output_cost_per_million":2.09,"context_window":262144,"announcement_date":"2025-09-22","param_count":9000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"},{"rank":23,"model_id":"qwen3-vl-8b-instruct","model_name":"Qwen3 VL 8B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.654,"normalized_score":0.654,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-22","param_count":9000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":24,"model_id":"qwen3-vl-4b-thinking","model_name":"Qwen3 VL 4B Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.65,"normalized_score":0.65,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":1.0,"context_window":262144,"announcement_date":"2025-09-22","param_count":4000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"},{"rank":25,"model_id":"nemotron-3-nano-30b-a3b","model_name":"Nemotron 3 Nano (30B A3B)","organization_id":"nvidia","organization_name":"NVIDIA","organization_country":"US","score":0.595,"normalized_score":0.595,"verified":false,"self_reported":true,"self_reported_source":"https://build.nvidia.com/nvidia/nemotron-3-nano-30b-a3b/modelcard","analysis_method":"Average over languages","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.06,"output_cost_per_million":0.24,"context_window":262144,"announcement_date":"2025-12-15","param_count":32000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"},{"rank":26,"model_id":"qwen3-vl-4b-instruct","model_name":"Qwen3 VL 4B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.594,"normalized_score":0.594,"verified":false,"self_reported":true,"self_reported_source":null,"analysis_method":null,"verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.1,"output_cost_per_million":0.6,"context_window":262144,"announcement_date":"2025-09-22","param_count":4000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"},{"rank":27,"model_id":"qwen3.5-2b","model_name":"Qwen3.5-2B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.523,"normalized_score":0.523,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen3.5-2B","analysis_method":"Thinking mode","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-03-02","param_count":2000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":28,"model_id":"qwen3.5-0.8b","model_name":"Qwen3.5-0.8B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.346,"normalized_score":0.346,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen3.5-0.8B","analysis_method":"Thinking mode","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-03-02","param_count":800000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":29,"model_id":"gemma-3n-e4b-it","model_name":"Gemma 3n E4B Instructed","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.199,"normalized_score":0.199,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E4B-it","analysis_method":"0-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-26","param_count":8000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":29,"model_id":"gemma-3n-e4b-it-litert-preview","model_name":"Gemma 3n E4B Instructed LiteRT Preview","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.199,"normalized_score":0.199,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E4B-it-litert-preview","analysis_method":"0-shot Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-05-20","param_count":1910000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":31,"model_id":"gemma-3n-e2b-it","model_name":"Gemma 3n E2B Instructed","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.081,"normalized_score":0.081,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E2B-it","analysis_method":"0-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-26","param_count":8000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":31,"model_id":"gemma-3n-e2b-it-litert-preview","model_name":"Gemma 3n E2B Instructed LiteRT (Preview)","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.081,"normalized_score":0.081,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E2B-it-litert-preview","analysis_method":"0-shot Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-05-20","param_count":1910000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}