True Index: Domain Rankings
Head-to-Head: Clean Evals vs. Legacy Benchmarks
| Capability Domain | Clean Evals (Tiers S & A) | Legacy Benchmarks (Tiers C & D) | Public Lift (Boost) |
|---|---|---|---|
| Agentic & Enterprise | 69.4p | 95.9p | +26.5p |
| Coding & SWE | 57.2p | 100.0p | +42.8p |
| General Knowledge & QA | 64.2p | 61.3p | -3.0p |
| Math & Scientific Reasoning | 70.2p | 71.2p | +1.0p |
Audited Benchmark Performance of Kimi K3.1 Pro
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (11)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #5/46 | 91.3p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #7/50 | 87.8p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #7/50 | 87.8p |
| MKA (Multimodal Knowledge Agent) | Private / Fresh | Agentic & Enterprise | #11/23 | 66.9p |
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #14/27 | 61.5p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #24/46 | 50.4p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #15/47 | 71.0p |
| AA-3D | Private / Fresh | Coding & SWE | #11/22 | 64.0p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #15/40 | 57.9p |
| LiveBench | Private / Fresh | General Knowledge & QA | #16/28 | 57.5p |
| AA-AnalystAgent | Private / Fresh | Agentic & Enterprise | #18/24 | 35.1p |
Mid-Tier Evaluations (Tier B) (2)
Partially exposed or transitional evaluations with moderate leakage risk.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| HLE-Diamond | Semi-Exposed | General Knowledge & QA | #18/49 | 64.6p |
| VIALS-AA | Semi-Exposed | Math & Scientific Reasoning | #13/23 | 45.5p |
Legacy & Vulnerable Benchmarks (Tiers C & D) (6)
Public or aging benchmarks prone to overfitting and training-data leaks.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #1/50 | 100.0p |
| GDP.pdf | Public / Aging | Agentic & Enterprise | #2/50 | 98.0p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #2/43 | 93.8p |
| BioMysteryBench | Public / Aging | Math & Scientific Reasoning | #9/23 | 72.6p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #15/41 | 69.8p |
| MMMU-Pro | Public / Aging | General Knowledge & QA | #8/22 | 61.3p |