evals.report
BenchmarksLabsCompareRun guidesIn the wild
BenchmarksReasoning

MathArena HMMT February 2026

Contamination-free evaluation of large language models on the 33 problems of the HMMT February 2026 mathematics competition, scoring final-answer accuracy (pass@1 estimated from 4 samples per problem) on problems released after model training.

ReasoningaccuracyHigher is better

What this benchmark measures

Contamination-free evaluation of large language models on the 33 problems of the HMMT February 2026 mathematics competition, scoring final-answer accuracy (pass@1 estimated from 4 samples per problem) on problems released after model training.

Rows on this page are sourced from public benchmark artifacts, leaderboard exports, or source-linked model reports. Each row keeps benchmark version, source model name, and available run details attached to the score.

The metric shown here is accuracy. It should be interpreted within MathArena HMMT February 2026, not compared as part of a site-wide ranking.

No composite ranking
evals.report never combines benchmarks. accuracy on MathArena HMMT February 2026 is its own number — don’t average it with other metrics.

Frequently asked

What is MathArena HMMT February 2026?

Contamination-free evaluation of large language models on the 33 problems of the HMMT February 2026 mathematics competition, scoring final-answer accuracy (pass@1 estimated from 4 samples per problem) on problems released after model training. It is a reasoning benchmark measured by accuracy.

What does accuracy mean on MathArena HMMT February 2026?

MathArena HMMT February 2026 reports accuracy (%); higher is better. Scores are shown only within MathArena HMMT February 2026 and are never averaged with other benchmarks.

What is the top reported MathArena HMMT February 2026 score?

GPT-5.4 has the top reported score on MathArena HMMT February 2026: 97.73% (accuracy).

Why do MathArena HMMT February 2026 scores differ across runs?

Harness, scaffold, reasoning effort, and prompt setup change results, so two runs of the same model can differ. evals.report keeps each score with its run context so the differences stay visible.

Does evals.report rank models across benchmarks?

No. MathArena HMMT February 2026 scores are shown within their own metric; evals.report never combines benchmarks into a composite ranking or a single "best model".