Benchmark category
Math evaluations, model coverage and rankings. Each benchmark keeps its original scale and methodology.
Data as of 2026-08-17
Select a benchmark to inspect model results, evidence fields and scoring direction.
Benchmark | Family | Modality | Metric | Coverage | Coverage tier | Evidence | Score eligible |
|---|
| BenchmarkMMLU-Pro | FamilyMMLU-Pro | Modalitytext | MetricScore | Coverage134 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkAIME 2025 | FamilyAIME 2025 | Modalitytext | MetricScore | Coverage115 | Coverage tierfeatured | EvidenceC | Score eligibleYes |
| BenchmarkMMLU | FamilyMMLU | Modalitytext | MetricScore | Coverage101 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkHumanity's Last Exam | FamilyHumanity's Last Exam | Modalitymultimodal | MetricScore | Coverage99 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkMATH | FamilyMATH | Modalitytext | MetricScore | Coverage71 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkAIME 2024 | FamilyAIME 2024 | Modalitytext | MetricScore | Coverage53 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkMMMLU | FamilyMMMLU | Modalitytext | MetricScore | Coverage49 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkGSM8k | FamilyGSM8k | Modalitytext | MetricScore | Coverage48 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkMMLU-Redux | FamilyMMLU-Redux | Modalitytext | MetricScore | Coverage48 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkMathVista | FamilyMathVista | Modalitymultimodal | MetricScore | Coverage39 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkLiveBench | FamilyLiveBench | Modalitytext | MetricScore | Coverage38 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkSuperGPQA | FamilySuperGPQA | Modalitytext | MetricScore | Coverage34 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkHMMT 2025 | FamilyHMMT 2025 | Modalitytext | MetricScore | Coverage33 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkMathVision | FamilyMathVision | Modalitymultimodal | MetricScore | Coverage33 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkMATH-500 | FamilyMATH-500 | Modalitytext | MetricScore | Coverage32 | Coverage tierfeatured | EvidenceC | Score eligibleYes |
| BenchmarkMMLU-ProX | FamilyMMLU-ProX | Modalitytext | MetricScore | Coverage32 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkMGSM | FamilyMGSM | Modalitytext | MetricScore | Coverage31 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkDROP | FamilyDROP | Modalitytext | MetricScore | Coverage30 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkHMMT25 | FamilyHMMT25 | Modalitytext | MetricScore | Coverage25 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkMathVista-Mini | FamilyMathVista-Mini | Modalitymultimodal | MetricScore | Coverage24 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkPolyMATH | FamilyPolyMATH | Modalitymultimodal | MetricScore | Coverage23 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkAIME 2026 | FamilyAIME 2026 | Modalitytext | MetricScore | Coverage21 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkBIG-Bench Hard | FamilyBIG-Bench Hard | Modalitytext | MetricScore | Coverage21 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkSciCode | FamilySciCode | Modalitytext | MetricScore | Coverage21 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkIMO-AnswerBench | FamilyIMO-AnswerBench | Modalitytext | MetricScore | Coverage20 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkCodeForces | FamilyCodeForces | Modalitytext | MetricNormalized rating | Coverage17 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkFrontierMath | FamilyFrontierMath | Modalitytext | MetricScore | Coverage17 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkLiveBench 20241125 | FamilyLiveBench 20241125 | Modalitytext | MetricScore | Coverage14 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkHiddenMath | FamilyHiddenMath | Modalitytext | MetricScore | Coverage13 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkBBH | FamilyBBH | Modalitytext | MetricScore | Coverage12 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkHMMT Feb 26 | FamilyHMMT Feb 26 | Modalitytext | MetricScore | Coverage12 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkAGIEval | FamilyAGIEval | Modalitytext | MetricScore | Coverage10 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
Leading results from high-coverage benchmarks with at least two models.
How this category is assembled on llmboard.ai.
This page groups benchmarks whose primary or display category matches math. It does not average incompatible metrics into a new category score.
Open an individual benchmark to inspect score direction, evidence level, participant count and model results.
Benchmarks are grouped by their primary and display categories.