Benchmark

HMMT

A dated competition, not a fixed set: each sitting is a different instrument and contamination rises once problems are published.

Released
2025-02-15
Categories
math
Openness
unknown
Source
model_reports
Reported scores
7

Reported scores

model_reports

ModelOrganizationReported valueReportedEvidence
DeepSeek-V4-FlashDeepSeek94.82026-06-25evidence
DeepSeek-V4-ProDeepSeek95.22026-04-22evidence
GLM-5Z.ai96.92026-02-11evidence
GLM-5.1Z.ai94.02026-04-03evidence
GLM-5.2Z.ai94.42026-06-16evidence
Qwen3.5-397B-A17BQwen94.82026-02-16evidence
Qwen3.5-397B-A17BQwen92.72026-02-16evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.