Benchmark category
Agents 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 |
|---|
| BenchmarkBrowseComp | FamilyBrowseComp | Modalitytext | MetricScore | Coverage62 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkTerminal-Bench 2.0 | FamilyTerminal-Bench 2.0 | Modalitytext | MetricScore | Coverage51 | Coverage tierfeatured | EvidenceC | Score eligibleYes |
| BenchmarkSWE-Bench Pro | FamilySWE-Bench Pro | Modalitytext | MetricScore | Coverage50 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkToolathlon | FamilyToolathlon | Modalitytext | MetricScore | Coverage37 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkMCP Atlas | FamilyMCP Atlas | Modalitytext | MetricScore | Coverage33 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkTerminal-Bench 2.1 | FamilyTerminal-Bench 2.1 | Modalitytext | MetricScore | Coverage28 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkFinance Agent v2 | FamilyFinance Agent v2 | Modalitytext | MetricScore | Coverage26 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkDeepSWE 1.1 | FamilyDeepSWE 1.1 | Modalitytext | MetricScore | Coverage25 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkTerminal-Bench | FamilyTerminal-Bench | Modalitytext | MetricScore | Coverage25 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkOSWorld-Verified | FamilyOSWorld-Verified | Modalitymultimodal | MetricScore | Coverage24 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| Benchmarkt2-bench | Familyt2-bench | Modalitytext | MetricScore | Coverage23 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkOSWorld | FamilyOSWorld | Modalitymultimodal | MetricScore | Coverage20 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkBFCL-v3 | FamilyBFCL-v3 | Modalitytext | MetricScore | Coverage19 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkNL2Repo | FamilyNL2Repo | Modalitytext | MetricScore | Coverage17 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkFrontierCode 1.1 | FamilyFrontierCode 1.1 | Modalitytext | MetricScore | Coverage16 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkFrontierSWE | FamilyFrontierSWE | Modalitytext | MetricScore | Coverage16 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkBFCL-V4 | FamilyBFCL-V4 | Modalitytext | MetricScore | Coverage15 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkClaw-Eval | FamilyClaw-Eval | Modalitytext | MetricScore | Coverage14 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkCyberGym | FamilyCyberGym | Modalitytext | MetricScore | Coverage13 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkLegal Agent Benchmark | FamilyLegal Agent Benchmark | Modalitytext | MetricScore | Coverage13 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkAutomationBench | FamilyAutomationBench | Modalitytext | MetricScore | Coverage12 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkDeepSWE | FamilyDeepSWE | Modalitytext | MetricScore | Coverage11 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkAgents' Last Exam | FamilyAgents' Last Exam | Modalitytext | MetricScore | Coverage10 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkVITA-Bench | FamilyVITA-Bench | Modalitytext | MetricScore | Coverage10 | Coverage tierfeatured | EvidenceB | Score eligibleYes |
| BenchmarkWideSearch | FamilyWideSearch | 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 agents. 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.