Overall score
60.5
Rank #23 · A confidence
MiniMax · stable
MiniMax's current long-context multimodal API model for coding and agentic workloads.
Overall score
60.5
Rank #23 · A confidence
Capability
55.8
27 eligible benchmark families
Coverage
81%
Confidence A
Benchmarks scored
31
34 raw result rows
Model specification
Identity, configuration and price are preserved as dated source records.
Category profile
A category remains Not evaluated until an eligible source-qualified result is attached.
Benchmark scores
Best published score per benchmark. Open any row for the full per-benchmark leaderboard.
| Benchmark | Category | Score | Date |
|---|---|---|---|
| GPQA DiamondRanking weighted | reasoning | 92.93% | 2026-07-15 |
| τ-benchRanking weighted | agents | 88.9% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 88.8889% | 2026-07-15 |
| USAMO 2026Ranking weighted | mathematics | 85.71% | 2026-07-15 |
| BrowseCompRanking weighted | agents | 83.52% | 2026-07-15 |
| IFBench | instruction following | 82.9% | 2026-07-15 |
| IFEval | instruction following | 82.9% | 2026-07-15 |
| SWE-bench VerifiedRanking weighted | coding | 80.5% | 2026-07-15 |
| MMMU-ProRanking weighted | multimodal | 78.55% | 2026-07-15 |
| MCP AtlasRanking weighted | agents | 74.2% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 74% | 2026-07-15 |
| OSWorld-VerifiedRanking weighted | agents | 70.06% | 2026-07-15 |
| LiveBenchRanking weighted | reasoning | 70.02% | 2026-07-15 |
| BenchLM Math priorRanking weighted | mathematics | 68.8% | 2026-07-15 |
| Terminal-BenchRanking weighted | agents | 66% | 2026-07-15 |
| SWE-Bench ProRanking weighted | coding | 59% | 2026-07-15 |
| BenchLM Coding priorRanking weighted | coding | 58.06% | 2026-07-15 |
| PaperBenchRanking weighted | research | 52.6% | 2026-07-15 |
| BenchLM Agentic priorRanking weighted | agents | 49.75% | 2026-07-15 |
| BenchLM Multimodal priorRanking weighted | multimodal | 49.6% | 2026-07-15 |
| SciCodeRanking weighted | coding | 45.4% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 44.7415% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 42.4242% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 42.4% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 37.12% | 2026-07-15 |
| EnterpriseOps-Gym-AARanking weighted | agents | 32.1098% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 12.9897% | 2026-07-15 |
| Harvey LAB-AARanking weighted | agents | 6.6667% | 2026-07-15 |
| OSWorldRanking weighted | agents | 4.6% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 3.7143% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | 1.3667 index | 2026-07-15 |
Showing the best of 34 raw result rows across 31 benchmark families.
Price and efficiency
Operational values are shown only when the source publishes a comparable measurement or a valid derivation.
Verification summary
News and X posts are structurally excluded from this model's evidence graph.
Missing publication dimensions: value. The last source check for this exact model was 2026-07-15.
Related models
Exact variants remain separate even when they share a provider or family.