Wikibench

HMMT Feb 26

math

Multilingual: no

HMMT February 2026 is a math competition benchmark based on problems from the Harvard-MIT Mathematics Tournament, testing advanced mathematical problem-solving and reasoning.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: math, reasoning. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 8 of 8 results

  1. Qwen3.7 Max self-reported llm-stats
    97.1%
  2. DeepSeek-V4-Pro-Max self-reported llm-stats
    95.2%
  3. DeepSeek-V4-Flash-Max self-reported llm-stats
    94.8%
  4. Kimi K2.6 self-reported llm-stats
    92.7%
  5. Qwen3.6 Plus self-reported llm-stats
    87.8%
  6. MAI-Thinking-1 self-reported llm-stats
    84.9%
  7. Qwen3.6-27B self-reported llm-stats
    84.3%
  8. GLM-5.1 self-reported llm-stats
    82.6%