True Index: Domain Rankings
Agentic & Enterprise64.5p
#17
5 Top-Tier private testsCoding & SWE66.2p
#15
5 Top-Tier private testsMath & Scientific Reasoning91.6p
#3
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 | 64.5p | 67.3p | +2.9p |
| Coding & SWE | 66.2p | 70.1p | +3.9p |
| General Knowledge & QA | 88.4p | 78.5p | -9.9p |
| Math & Scientific Reasoning | 91.6p | 89.6p | -2.0p |
Clean Evals Avg (Tiers S & A)
77.7p
16 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
76.4p
9 public or aging tests
Matched Public Lift (Boost)
+1.9p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of GPT-6.1 Sol
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (16)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #1/27 | 99.5p |
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #5/46 | 91.3p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #9/46 | 84.2p |
| Code2Video-AA | Private / Fresh | Coding & SWE | #4/23 | 77.6p |
| MKA (Multimodal Knowledge Agent) | Private / Fresh | Agentic & Enterprise | #9/23 | 75.1p |
| Harvey LAB-AA v1.1 | Private / Fresh | Agentic & Enterprise | #10/21 | 71.2p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #21/50 | 59.2p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #23/50 | 55.1p |
| ARC-AGI-2 | Private / Fresh | General Knowledge & QA | #3/22 | 98.9p |
| LiveBench | Private / Fresh | General Knowledge & QA | #8/28 | 84.5p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #3/40 | 84.0p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #10/47 | 81.9p |
| Code Migration v1.1 | Private / Fresh | Coding & SWE | #5/24 | 80.4p |
| AA-3D | Private / Fresh | Coding & SWE | #10/22 | 67.8p |
| AA-AnalystAgent | Private / Fresh | Agentic & Enterprise | #11/24 | 61.7p |
| CyberBench v1.1 | Private / Fresh | Coding & SWE | #24/25 | 21.2p |
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 | #9/49 | 82.3p |
| VIALS-AA | Semi-Exposed | Math & Scientific Reasoning | #10/23 | 59.1p |
Legacy & Vulnerable Benchmarks (Tiers C & D) (9)
Public or aging benchmarks prone to overfitting and training-data leaks.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| GDP.pdf | Public / Aging | Agentic & Enterprise | #3/50 | 94.9p |
| BioMysteryBench | Public / Aging | Math & Scientific Reasoning | #4/23 | 92.6p |
| HealthBench | Public / Aging | Math & Scientific Reasoning | #4/16 | 88.9p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #8/41 | 87.4p |
| SWE Atlas - Codebase QnA | Public / Aging | Coding & SWE | #6/15 | 78.7p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #12/50 | 77.6p |
| SWE-bench Pro V2 | Public / Aging | Coding & SWE | #5/8 | 54.0p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #25/43 | 39.8p |
| MMMU-Pro | Public / Aging | General Knowledge & QA | #4/22 | 78.5p |