True Index: Domain Rankings
Agentic & Enterprise83.2p
#6
5 Top-Tier private testsCoding & SWE79.1p
#8
6 Top-Tier private testsMath & Scientific Reasoning81.4p
#8
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 | 83.2p | 84.8p | +1.6p |
| Coding & SWE | 79.1p | 92.1p | +13.0p |
| General Knowledge & QA | 88.2p | 87.1p | -1.1p |
| Math & Scientific Reasoning | 81.4p | 82.2p | +0.8p |
Clean Evals Avg (Tiers S & A)
83.0p
17 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
86.6p
8 public or aging tests
Matched Public Lift (Boost)
+11.2p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of Claude Opus 5.5
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (17)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #2/46 | 100.0p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #2/50 | 98.0p |
| MKA (Multimodal Knowledge Agent) | Private / Fresh | Agentic & Enterprise | #4/23 | 95.6p |
| Code2Video-AA | Private / Fresh | Coding & SWE | #1/23 | 88.5p |
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #6/27 | 86.8p |
| Vibe Code Bench 1-100 v1.1 | Private / Fresh | Coding & SWE | #4/10 | 77.2p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #13/50 | 75.5p |
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #14/46 | 73.4p |
| Harvey LAB-AA v1.1 | Private / Fresh | Agentic & Enterprise | #12/21 | 63.7p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #5/47 | 92.9p |
| LiveBench | Private / Fresh | General Knowledge & QA | #6/28 | 91.2p |
| Code Migration v1.1 | Private / Fresh | Coding & SWE | #3/24 | 88.5p |
| AA-3D | Private / Fresh | Coding & SWE | #5/22 | 87.2p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #3/40 | 84.0p |
| AA-AnalystAgent | Private / Fresh | Agentic & Enterprise | #5/24 | 83.0p |
| ARC-AGI-2 | Private / Fresh | General Knowledge & QA | #7/22 | 80.5p |
| CyberBench v1.1 | Private / Fresh | Coding & SWE | #20/25 | 33.0p |
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 | #5/49 | 91.7p |
| VIALS-AA | Semi-Exposed | Math & Scientific Reasoning | #6/23 | 77.3p |
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 |
|---|---|---|---|---|
| SWE Atlas - Codebase QnA | Public / Aging | Coding & SWE | #3/15 | 97.5p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #1/43 | 96.1p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #7/41 | 89.9p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #7/50 | 86.7p |
| BioMysteryBench | Public / Aging | Math & Scientific Reasoning | #5/23 | 86.6p |
| GDP.pdf | Public / Aging | Agentic & Enterprise | #13/50 | 73.5p |
| HealthBench | Public / Aging | Math & Scientific Reasoning | #8/16 | 70.2p |
| MMMU-Pro | Public / Aging | General Knowledge & QA | #2/22 | 87.1p |