True Index: Domain Rankings
Agentic & Enterprise81.2p
#8
5 Top-Tier private testsCoding & SWE79.0p
#9
5 Top-Tier private testsMath & Scientific Reasoning82.6p
#6
3 Top-Tier private testsHead-to-Head: Clean Evals vs. Legacy Benchmarks
| Capability Domain | Clean Evals (Tiers S & A) | Legacy Benchmarks (Tiers C & D) | Public Lift (Boost) |
|---|---|---|---|
| Agentic & Enterprise | 81.2p | 79.2p | -1.9p |
| Coding & SWE | 79.0p | 75.1p | -3.9p |
| Math & Scientific Reasoning | 82.6p | 94.1p | +11.5p |
Clean Evals Avg (Tiers S & A)
78.3p
15 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
82.8p
8 public or aging tests
Matched Public Lift (Boost)
+1.6p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of Claude Sonnet 5.5
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (15)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #1/50 | 100.0p |
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #2/46 | 97.6p |
| MKA (Multimodal Knowledge Agent) | Private / Fresh | Agentic & Enterprise | #6/23 | 87.4p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #8/46 | 86.4p |
| Code2Video-AA | Private / Fresh | Coding & SWE | #2/23 | 84.9p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #10/50 | 81.6p |
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #11/27 | 70.9p |
| Harvey LAB-AA v1.1 | Private / Fresh | Agentic & Enterprise | #16/21 | 48.5p |
| Code Migration v1.1 | Private / Fresh | Coding & SWE | #1/24 | 96.6p |
| AA-3D | Private / Fresh | Coding & SWE | #4/22 | 91.1p |
| AA-AnalystAgent | Private / Fresh | Agentic & Enterprise | #3/24 | 88.3p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #6/40 | 79.3p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #14/47 | 73.2p |
| LiveBench | Private / Fresh | General Knowledge & QA | #13/28 | 67.7p |
| CyberBench v1.1 | Private / Fresh | Coding & SWE | #19/25 | 36.0p |
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 | #12/49 | 77.1p |
| VIALS-AA | Semi-Exposed | Math & Scientific Reasoning | #8/23 | 65.9p |
Legacy & Vulnerable Benchmarks (Tiers C & D) (8)
Public or aging benchmarks prone to overfitting and training-data leaks.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| BioMysteryBench | Public / Aging | Math & Scientific Reasoning | #2/23 | 100.0p |
| HealthBench | Public / Aging | Math & Scientific Reasoning | #1/16 | 100.0p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #4/50 | 92.9p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #4/43 | 89.1p |
| SWE Atlas - Codebase QnA | Public / Aging | Coding & SWE | #4/15 | 88.1p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #10/41 | 82.4p |
| GDP.pdf | Public / Aging | Agentic & Enterprise | #16/50 | 69.4p |
| SWE-bench Pro V2 | Public / Aging | Coding & SWE | #6/8 | 44.4p |