True Index: Domain Rankings
Agentic & Enterprise43.4p
#31
3 Top-Tier private testsCoding & SWE88.8p
#6
1 Top-Tier private testMath & Scientific Reasoning76.7p
#11
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 | 43.4p | 55.7p | +12.3p |
| Coding & SWE | 88.8p | 55.2p | -33.5p |
| General Knowledge & QA | 73.3p | 65.5p | -7.8p |
| Math & Scientific Reasoning | 76.7p | 84.9p | +8.2p |
Clean Evals Avg (Tiers S & A)
70.5p
9 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
65.3p
6 public or aging tests
Matched Public Lift (Boost)
-5.3p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of GPT-6.1 Terra
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (9)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #7/46 | 88.8p |
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #7/27 | 83.6p |
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #12/46 | 76.6p |
| MKA (Multimodal Knowledge Agent) | Private / Fresh | Agentic & Enterprise | #12/23 | 62.8p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #29/50 | 42.9p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #38/50 | 24.5p |
| LiveBench | Private / Fresh | General Knowledge & QA | #10/28 | 77.8p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #10/40 | 69.8p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #16/47 | 68.8p |
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 | #14/49 | 72.9p |
| VIALS-AA | Semi-Exposed | Math & Scientific Reasoning | #7/23 | 72.7p |
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 |
|---|---|---|---|---|
| GDP.pdf | Public / Aging | Agentic & Enterprise | #8/50 | 85.7p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #9/41 | 84.9p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #13/50 | 75.5p |
| SWE Atlas - Codebase QnA | Public / Aging | Coding & SWE | #13/15 | 35.0p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #31/43 | 25.7p |
| MMMU-Pro | Public / Aging | General Knowledge & QA | #7/22 | 65.5p |