{"benchmark_id":"hmmt-2025","name":"HMMT 2025","parent_benchmark":null,"categories":["math"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds","paper_link":"http://web.mit.edu/HMMT/www/","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:23.832234+00:00","updated_at":"2026-07-05T18:27:49.820790+00:00","statistics":{"total_models":33,"average_score":0.8157969696969698,"min_score":0.289,"max_score":1.0,"score_stddev":0.21196302225395422,"verified_count":0,"self_reported_count":33},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"gpt-5.2-pro-2025-12-11","model_name":"GPT-5.2 Pro","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":1.0,"normalized_score":1.0,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-2/","analysis_method":"GPT-5.2 Pro - HMMT Feb 2025 (no tools).","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-11","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"gpt-5.2-2025-12-11","model_name":"GPT-5.2","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.994,"normalized_score":0.994,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-2/","analysis_method":"GPT-5.2 Thinking - HMMT Feb 2025 (no tools).","verification_date":null,"provider_id":"openai","input_cost_per_million":1.75,"output_cost_per_million":14.0,"context_window":400000,"announcement_date":"2025-12-11","param_count":null,"is_open_source":false,"is_new":false,"best_latency":2.0,"latency_provider":"OpenAI","best_throughput":100.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":3,"model_id":"deepseek-v3.2-speciale","model_name":"DeepSeek-V3.2-Speciale","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.992,"normalized_score":0.992,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2/resolve/main/assets/paper.pdf","analysis_method":"Pass@1","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-01","param_count":685000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":4,"model_id":"kimi-k2-thinking-0905","model_name":"Kimi K2-Thinking-0905","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.975,"normalized_score":0.975,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/thinking.html","analysis_method":"heavy","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":5,"model_id":"qwen3.6-plus","model_name":"Qwen3.6 Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.967,"normalized_score":0.967,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6","analysis_method":"February 2025","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":6,"model_id":"kimi-k2.5","model_name":"Kimi K2.5","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.954,"normalized_score":0.954,"verified":false,"self_reported":true,"self_reported_source":"https://www.kimi.com/blog/kimi-k2-5.html","analysis_method":"Full","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-01-27","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":7,"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":0.948,"normalized_score":0.948,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen3.5/","analysis_method":"February 2025","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":8,"model_id":"nemotron-3-super-120b-a12b","model_name":"Nemotron 3 Super (120B A12B)","organization_id":"nvidia","organization_name":"NVIDIA","organization_country":"US","score":0.9473,"normalized_score":0.9473,"verified":false,"self_reported":true,"self_reported_source":"https://build.nvidia.com/nvidia/nemotron-3-super-120b-a12b/modelcard","analysis_method":"With tools","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":9,"model_id":"glm-5.2","model_name":"GLM-5.2","organization_id":"zai-org","organization_name":"Zhipu AI","organization_country":"CN","score":0.944,"normalized_score":0.944,"verified":false,"self_reported":true,"self_reported_source":"https://z.ai/blog/glm-5.2","analysis_method":null,"verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.95,"output_cost_per_million":3.0,"context_window":1048576,"announcement_date":"2026-06-16","param_count":753000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Fireworks","best_throughput":null,"throughput_provider":"Fireworks","context_provider":"DeepInfra"},{"rank":10,"model_id":"glm-5.1","model_name":"GLM-5.1","organization_id":"zai-org","organization_name":"Zhipu AI","organization_country":"CN","score":0.94,"normalized_score":0.94,"verified":false,"self_reported":true,"self_reported_source":"https://z.ai/blog/glm-5.1","analysis_method":null,"verification_date":null,"provider_id":"friendli","input_cost_per_million":1.4,"output_cost_per_million":4.4,"context_window":200000,"announcement_date":"2026-04-07","param_count":754000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"FriendliAI","best_throughput":null,"throughput_provider":"FriendliAI","context_provider":"ZAI"},{"rank":11,"model_id":"qwen3.6-27b","model_name":"Qwen3.6-27B","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://qwen.ai/blog?id=qwen3.6-27b","analysis_method":"February 2025","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":12,"model_id":"grok-4-fast","model_name":"Grok 4 Fast","organization_id":"xai","organization_name":"xAI","organization_country":"US","score":0.933,"normalized_score":0.933,"verified":false,"self_reported":true,"self_reported_source":"https://x.ai/news/grok-4-fast","analysis_method":"accuracy","verification_date":null,"provider_id":"xai","input_cost_per_million":0.2,"output_cost_per_million":0.5,"context_window":2000000,"announcement_date":"2025-08-28","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"xAI","best_throughput":90,"throughput_provider":"xAI","context_provider":"xAI"},{"rank":12,"model_id":"gpt-5-2025-08-07","model_name":"GPT-5","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.933,"normalized_score":0.933,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-5/","analysis_method":"GPT-5 standard with thinking mode enabled (no tools) - Harvard-MIT Mathematics Tournament.","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-08-07","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":14,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.92,"normalized_score":0.92,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"February 2025","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":15,"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":0.914,"normalized_score":0.914,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"February 2025","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":16,"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":0.907,"normalized_score":0.907,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-35b-a3b","analysis_method":"February 2025","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":17,"model_id":"deepseek-v3.2","model_name":"DeepSeek-V3.2","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.902,"normalized_score":0.902,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2/resolve/main/assets/paper.pdf","analysis_method":"Nov 2025 (Pass@1)","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-01","param_count":685000000000,"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":"deepseek-reasoner","model_name":"DeepSeek-V3.2 (Thinking)","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.902,"normalized_score":0.902,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2/resolve/main/assets/paper.pdf","analysis_method":"Pass@1","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-01","param_count":685000000000,"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":"qwen3.5-35b-a3b","model_name":"Qwen3.5-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.89,"normalized_score":0.89,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"February 2025","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":20,"model_id":"gpt-5-mini-2025-08-07","model_name":"GPT-5 mini","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.878,"normalized_score":0.878,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-5/","analysis_method":"GPT-5 mini with thinking mode enabled (no tools) - Harvard-MIT Mathematics Tournament.","verification_date":null,"provider_id":"openai","input_cost_per_million":0.25,"output_cost_per_million":2.0,"context_window":400000,"announcement_date":"2025-08-07","param_count":null,"is_open_source":false,"is_new":false,"best_latency":1.0,"latency_provider":"OpenAI","best_throughput":200.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":21,"model_id":"sarvam-105b","model_name":"Sarvam-105B","organization_id":"sarvamai","organization_name":"Sarvam AI","organization_country":"IN","score":0.858,"normalized_score":0.858,"verified":false,"self_reported":true,"self_reported_source":"https://www.sarvam.ai/blogs/sarvam-30b-105b","analysis_method":"February 2025","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-03-06","param_count":105000000000,"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":"mimo-v2-flash","model_name":"MiMo-V2-Flash","organization_id":"xiaomi","organization_name":"Xiaomi","organization_country":"CN","score":0.844,"normalized_score":0.844,"verified":false,"self_reported":true,"self_reported_source":"https://mimo.xiaomi.com/blog/mimo-v2-flash","analysis_method":"Feb 2025","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-16","param_count":309000000000,"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":"deepseek-v3.2-exp","model_name":"DeepSeek-V3.2-Exp","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.836,"normalized_score":0.836,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp","analysis_method":"Pass@1 (Reasoning Mode w/o Tool Use)","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-29","param_count":685000000000,"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":"qwen3.5-9b","model_name":"Qwen3.5-9B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.832,"normalized_score":0.832,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen3.5-9B","analysis_method":"February 2025","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":25,"model_id":"deepseek-r1-0528","model_name":"DeepSeek-R1-0528","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.794,"normalized_score":0.794,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1","analysis_method":"Pass@1, 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":26,"model_id":"gpt-5-nano-2025-08-07","model_name":"GPT-5 nano","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.756,"normalized_score":0.756,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-5/","analysis_method":"GPT-5 nano with thinking mode enabled (no tools) - Harvard-MIT Mathematics Tournament.","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-08-07","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":27,"model_id":"qwen3.5-4b","model_name":"Qwen3.5-4B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.74,"normalized_score":0.74,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen3.5-4B","analysis_method":"February 2025","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":28,"model_id":"sarvam-30b","model_name":"Sarvam-30B","organization_id":"sarvamai","organization_name":"Sarvam AI","organization_country":"IN","score":0.733,"normalized_score":0.733,"verified":false,"self_reported":true,"self_reported_source":"https://www.sarvam.ai/blogs/sarvam-30b-105b","analysis_method":"February 2025","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-03-06","param_count":30000000000,"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":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.388,"normalized_score":0.388,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/","analysis_method":"Avg@32","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":29,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.388,"normalized_score":0.388,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/","analysis_method":"Avg@32","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":31,"model_id":"gpt-4.1-mini-2025-04-14","model_name":"GPT-4.1 mini","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.35,"normalized_score":0.35,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-for-developers/","analysis_method":"GPT-4.1 mini with no tools - Harvard-MIT Mathematics Tournament.","verification_date":null,"provider_id":"openai","input_cost_per_million":0.4,"output_cost_per_million":1.6,"context_window":1047576,"announcement_date":"2025-04-14","param_count":null,"is_open_source":false,"is_new":false,"best_latency":5.0,"latency_provider":"OpenAI","best_throughput":150.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":32,"model_id":"deepseek-v3.1","model_name":"DeepSeek-V3.1","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.335,"normalized_score":0.335,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1","analysis_method":"Pass@1, 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":33,"model_id":"gpt-4.1-2025-04-14","model_name":"GPT-4.1","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.289,"normalized_score":0.289,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-for-developers/","analysis_method":"GPT-4.1 with no tools - Harvard-MIT Mathematics Tournament.","verification_date":null,"provider_id":"openai","input_cost_per_million":2.0,"output_cost_per_million":8.0,"context_window":1047576,"announcement_date":"2025-04-14","param_count":null,"is_open_source":false,"is_new":false,"best_latency":10.0,"latency_provider":"OpenAI","best_throughput":100.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"}]}