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 | 70.1p | 76.5p | +6.5p |
| Coding & SWE | 67.8p | 85.2p | +17.4p |
| Math & Scientific Reasoning | 59.9p | 74.9p | +15.0p |
Audited Benchmark Performance of Claude Fable 5.1
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (14)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #8/50 | 85.7p |
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #9/27 | 75.7p |
| Code2Video-AA | Private / Fresh | Coding & SWE | #5/23 | 73.9p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #15/46 | 70.7p |
| Harvey LAB-AA v1.1 | Private / Fresh | Agentic & Enterprise | #11/21 | 67.4p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #31/50 | 38.8p |
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #35/46 | 29.4p |
| LiveBench | Private / Fresh | General Knowledge & QA | #5/28 | 94.5p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #6/47 | 89.6p |
| AA-AnalystAgent | Private / Fresh | Agentic & Enterprise | #3/24 | 88.3p |
| AA-3D | Private / Fresh | Coding & SWE | #8/22 | 75.6p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #8/40 | 74.6p |
| ARC-AGI-2 | Private / Fresh | General Knowledge & QA | #9/22 | 71.3p |
| CyberBench v1.1 | Private / Fresh | Coding & SWE | #14/25 | 50.9p |
Mid-Tier Evaluations (Tier B) (1)
Partially exposed or transitional evaluations with moderate leakage risk.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| HLE-Diamond | Semi-Exposed | General Knowledge & QA | #8/49 | 85.4p |
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 |
|---|---|---|---|---|
| SWE Atlas - Codebase QnA | Public / Aging | Coding & SWE | #2/15 | 100.0p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #8/43 | 79.6p |
| HealthBench | Public / Aging | Math & Scientific Reasoning | #7/16 | 74.9p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #13/41 | 74.9p |
| GDP.pdf | Public / Aging | Agentic & Enterprise | #13/50 | 73.5p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #15/50 | 70.4p |