Benchmark

OmniMath

A Universal Olympiad Level Mathematic Benchmark for Large Language Models containing 4,428 competition-level problems with rigorous human annotation…

Modality
text
Categories
math, reasoning
Openness
unknown
Source
llm_stats
Reported scores
2

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Phi 4 ReasoningMicrosoft0.7662025-04-30evidence
Phi 4 Reasoning PlusMicrosoft0.8192025-04-30evidence

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.