True Index: Domain Rankings
Agentic & Enterprise47.3p
#27
3 Top-Tier private testsCoding & SWE77.8p
#10
3 Top-Tier private testsMath & Scientific Reasoning80.4p
#9
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 | 47.3p | 47.1p | -0.1p |
| Coding & SWE | 77.8p | 65.3p | -12.5p |
| General Knowledge & QA | 60.1p | 57.0p | -3.1p |
| Math & Scientific Reasoning | 80.4p | 62.6p | -17.9p |
Clean Evals Avg (Tiers S & A)
66.4p
11 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
58.0p
7 public or aging tests
Matched Public Lift (Boost)
-6.6p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of GPT-6 Sol
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 | #9/46 | 83.9p |
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #8/27 | 80.5p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #13/46 | 75.1p |
| Harvey LAB-AA v1.1 | Private / Fresh | Agentic & Enterprise | #14/21 | 56.1p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #27/50 | 46.9p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #31/50 | 38.8p |
| CyberBench v1.1 | Private / Fresh | Coding & SWE | #2/25 | 86.6p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #7/40 | 76.9p |
| AA-3D | Private / Fresh | Coding & SWE | #9/22 | 71.7p |
| ARC-AGI-2 | Private / Fresh | General Knowledge & QA | #10/22 | 66.7p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #23/47 | 53.5p |
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 | #15/49 | 70.8p |
Legacy & Vulnerable Benchmarks (Tiers C & D) (7)
Public or aging benchmarks prone to overfitting and training-data leaks.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| BioMysteryBench | Public / Aging | Math & Scientific Reasoning | #10/23 | 68.7p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #16/41 | 67.3p |
| GDP.pdf | Public / Aging | Agentic & Enterprise | #17/50 | 66.3p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #18/50 | 65.3p |
| HealthBench | Public / Aging | Math & Scientific Reasoning | #12/16 | 51.7p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #30/43 | 28.0p |
| MMMU-Pro | Public / Aging | General Knowledge & QA | #9/22 | 57.0p |