Overall score
51.6
Rank #53 · A confidence
Moonshot AI · stable
Moonshot AI's officially documented multimodal Kimi model; unverified K3 reports are excluded from this registry.
Overall score
51.6
Rank #53 · A confidence
Capability
60.0
33 eligible benchmark families
Coverage
86%
Confidence A
Benchmarks scored
33
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 |
|---|---|---|---|
| AIME 2025 | mathematics | 96.1% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 95.9064% | 2026-07-15 |
| τ-benchRanking weighted | agents | 95.9% | 2026-07-15 |
| AIME 2026Ranking weighted | mathematics | 95.8% | 2026-07-15 |
| IFEval | instruction following | 93.9% | 2026-07-15 |
| GPQA DiamondRanking weighted | reasoning | 87.6% | 2026-07-15 |
| HMMT Feb 2026Ranking weighted | mathematics | 87.1% | 2026-07-15 |
| MMLU-ProRanking weighted | research | 87.1% | 2026-07-15 |
| LiveCodeBenchRanking weighted | coding | 85% | 2026-07-15 |
| MMMU-ProRanking weighted | multimodal | 78.5% | 2026-07-15 |
| SWE-bench VerifiedRanking weighted | coding | 76.8% | 2026-07-15 |
| IFBench | instruction following | 70.2% | 2026-07-15 |
| SuperGPQARanking weighted | reasoning | 69.2% | 2026-07-15 |
| LiveBenchRanking weighted | reasoning | 69.07% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 65.3333% | 2026-07-15 |
| PaperBenchRanking weighted | research | 63.5% | 2026-07-15 |
| LongBench v2 | long context | 61% | 2026-07-15 |
| BrowseCompRanking weighted | agents | 60.6% | 2026-07-15 |
| SWE-RebenchRanking weighted | coding | 58.5% | 2026-07-15 |
| SWE-Bench ProRanking weighted | coding | 50.7% | 2026-07-15 |
| SciCodeRanking weighted | coding | 48.7% | 2026-07-15 |
| GAIARanking weighted | agents | 36.5% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 34.8485% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 34.8% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 30.1% | 2026-07-15 |
| MCP AtlasRanking weighted | agents | 29.5% | 2026-07-15 |
| FrontierMathRanking weighted | mathematics | 27.9% | 2026-07-15 |
| ToolathlonRanking weighted | agents | 27.8% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 25.4265% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 14.2268% | 2026-07-15 |
| APEX-Agents-AARanking weighted | agents | 11.5044% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 3.1429% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | -8.1167 index | 2026-07-15 |
Showing the best of 34 raw result rows across 33 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 2026-07-16.
Related models
Exact variants remain separate even when they share a provider or family.