{"benchmark_id":"mmlu-redux","name":"MMLU-Redux","parent_benchmark":null,"categories":["math","reasoning","language","general"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"An improved version of the MMLU benchmark featuring manually re-annotated questions to identify and correct errors in the original dataset. Provides more reliable evaluation metrics for language models by addressing dataset quality issues found in the original MMLU.","paper_link":"https://arxiv.org/abs/2406.04127","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:24.850303+00:00","updated_at":"2026-07-05T18:27:54.858943+00:00","statistics":{"total_models":48,"average_score":0.8642499999999996,"min_score":0.432,"max_score":0.95,"score_stddev":0.10257088882349882,"verified_count":0,"self_reported_count":48},"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":0.95,"normalized_score":0.95,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.7","analysis_method":null,"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":"qwen3.5-397b-a17b","model_name":"Qwen3.5-397B-A17B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.949,"normalized_score":0.949,"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":3,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.945,"normalized_score":0.945,"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":0.945,"normalized_score":0.945,"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":5,"model_id":"kimi-k2-thinking-0905","model_name":"Kimi K2-Thinking-0905","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.944,"normalized_score":0.944,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/thinking.html","analysis_method":"no tools","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-05","param_count":1000000000000,"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":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.94,"normalized_score":0.94,"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":7,"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":0.938,"normalized_score":0.938,"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-vl-235b-a22b-thinking","model_name":"Qwen3 VL 235B A22B Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.937,"normalized_score":0.937,"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":9,"model_id":"qwen3.6-27b","model_name":"Qwen3.6-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.935,"normalized_score":0.935,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-27b","analysis_method":null,"verification_date":null,"provider_id":"novita","input_cost_per_million":0.6,"output_cost_per_million":3.6,"context_window":262144,"announcement_date":"2026-04-21","param_count":27781427952,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":10,"model_id":"deepseek-r1-0528","model_name":"DeepSeek-R1-0528","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.934,"normalized_score":0.934,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1","analysis_method":"Thinking mode","verification_date":null,"provider_id":"deepseek","input_cost_per_million":0.55,"output_cost_per_million":2.19,"context_window":131072,"announcement_date":"2025-05-28","param_count":671000000000,"is_open_source":true,"is_new":false,"best_latency":0.3,"latency_provider":"DeepSeek","best_throughput":37.96,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":11,"model_id":"qwen3.6-35b-a3b","model_name":"Qwen3.6-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.933,"normalized_score":0.933,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-35b-a3b","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-16","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":11,"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":0.933,"normalized_score":0.933,"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":13,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.932,"normalized_score":0.932,"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":14,"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":0.931,"normalized_score":0.931,"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":15,"model_id":"mimo-v2.5-pro","model_name":"MiMo-V2.5-Pro","organization_id":"xiaomi","organization_name":"Xiaomi","organization_country":"CN","score":0.928,"normalized_score":0.928,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","analysis_method":"Base model, 5-shot","verification_date":null,"provider_id":"xiaomi","input_cost_per_million":0.435,"output_cost_per_million":0.87,"context_window":1048576,"announcement_date":"2026-04-27","param_count":1023244718976,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Xiaomi","best_throughput":null,"throughput_provider":"Xiaomi","context_provider":"DeepInfra"},{"rank":16,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.927,"normalized_score":0.927,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/","analysis_method":"EM","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-05","param_count":1000000000000,"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":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.927,"normalized_score":0.927,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/","analysis_method":"EM","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-07-11","param_count":1000000000000,"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-next-80b-a3b-thinking","model_name":"Qwen3-Next-80B-A3B-Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.925,"normalized_score":0.925,"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":19,"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":0.922,"normalized_score":0.922,"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":20,"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":0.919,"normalized_score":0.919,"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":21,"model_id":"deepseek-v3.1","model_name":"DeepSeek-V3.1","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.918,"normalized_score":0.918,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1","analysis_method":"Non-Thinking mode","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-01-10","param_count":671000000000,"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":"qwen3.5-9b","model_name":"Qwen3.5-9B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.911,"normalized_score":0.911,"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":23,"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":0.909,"normalized_score":0.909,"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":23,"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":0.909,"normalized_score":0.909,"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":25,"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":0.898,"normalized_score":0.898,"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":26,"model_id":"longcat-flash-thinking","model_name":"LongCat-Flash-Thinking","organization_id":"meituan","organization_name":"Meituan","organization_country":"CN","score":0.893,"normalized_score":0.893,"verified":false,"self_reported":true,"self_reported_source":"https://github.com/meituan-longcat/LongCat-Flash-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":"2025-09-22","param_count":560000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":27,"model_id":"deepseek-v3","model_name":"DeepSeek-V3","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.891,"normalized_score":0.891,"verified":false,"self_reported":true,"self_reported_source":"https://github.com/deepseek-ai/DeepSeek-V3","analysis_method":"Exact Match","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-12-25","param_count":671000000000,"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-vl-8b-thinking","model_name":"Qwen3 VL 8B Thinking","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.888,"normalized_score":0.888,"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":28,"model_id":"qwen3.5-4b","model_name":"Qwen3.5-4B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.888,"normalized_score":0.888,"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":30,"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":0.884,"normalized_score":0.884,"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":31,"model_id":"qwen3-235b-a22b","model_name":"Qwen3 235B A22B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.874,"normalized_score":0.874,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen3/","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-04-29","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":32,"model_id":"qwen-2.5-72b-instruct","model_name":"Qwen2.5 72B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.868,"normalized_score":0.868,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen2.5/","analysis_method":"MMLU-redux benchmark evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":72700000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":33,"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":0.86,"normalized_score":0.86,"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":34,"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":0.849,"normalized_score":0.849,"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":35,"model_id":"qwen-2.5-32b-instruct","model_name":"Qwen2.5 32B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.839,"normalized_score":0.839,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen2.5-llm/","analysis_method":"MMLU-redux benchmark evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":32500000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":36,"model_id":"ministral-3-14b-base-2512","model_name":"Ministral 3 (14B Base 2512)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.82,"normalized_score":0.82,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/mistral-3","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-04","param_count":14000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":36,"model_id":"mistral-large-3-2509","model_name":"Mistral Large 3","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.82,"normalized_score":0.82,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/ministral-14b-8b-3b/","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-01","param_count":675000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":38,"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":0.815,"normalized_score":0.815,"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":39,"model_id":"qwen-2.5-14b-instruct","model_name":"Qwen2.5 14B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.8,"normalized_score":0.8,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen2.5-llm/","analysis_method":"MMLU-redux benchmark evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":14700000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":40,"model_id":"qwen3.5-2b","model_name":"Qwen3.5-2B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.796,"normalized_score":0.796,"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":41,"model_id":"ministral-3-8b-base-2512","model_name":"Ministral 3 (8B Base 2512)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.793,"normalized_score":0.793,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/mistral-3","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-04","param_count":8000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":42,"model_id":"qwen-2.5-coder-32b-instruct","model_name":"Qwen2.5-Coder 32B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.775,"normalized_score":0.775,"verified":false,"self_reported":true,"self_reported_source":"https://arxiv.org/abs/2409.12186","analysis_method":"accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":32000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":43,"model_id":"qwen-2.5-7b-instruct","model_name":"Qwen2.5 7B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.754,"normalized_score":0.754,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen2.5-llm/","analysis_method":"MMLU-redux benchmark evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":7610000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":44,"model_id":"ministral-3-3b-base-2512","model_name":"Ministral 3 (3B Base 2512)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.735,"normalized_score":0.735,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/mistral-3","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-04","param_count":3000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":45,"model_id":"qwen2.5-omni-7b","model_name":"Qwen2.5-Omni-7B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.71,"normalized_score":0.71,"verified":false,"self_reported":true,"self_reported_source":"https://github.com/QwenLM/Qwen2.5-Omni","analysis_method":"Score","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-27","param_count":7000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":46,"model_id":"qwen-2.5-coder-7b-instruct","model_name":"Qwen2.5-Coder 7B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.666,"normalized_score":0.666,"verified":false,"self_reported":true,"self_reported_source":"https://arxiv.org/abs/2409.12186","analysis_method":"accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":7000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":47,"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":0.595,"normalized_score":0.595,"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":48,"model_id":"ernie-4.5","model_name":"ERNIE 4.5","organization_id":"baidu","organization_name":"Baidu","organization_country":"CN","score":0.432,"normalized_score":0.432,"verified":false,"self_reported":true,"self_reported_source":"https://cloud.baidu.com/doc/WENXINWORKSHOP/s/clntwmv7t","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-25","param_count":21000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}