True Index: Domain Rankings
Agentic & Enterprise75.5p
#11
2 Top-Tier private testsCoding & SWE79.7p
#7
1 Top-Tier private testMath & Scientific Reasoning67.2p
#15
2 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 | 75.5p | 79.6p | +4.1p |
| Coding & SWE | 79.7p | 73.5p | -6.2p |
| Math & Scientific Reasoning | 67.2p | 69.2p | +2.0p |
Clean Evals Avg (Tiers S & A)
76.7p
8 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
74.1p
4 public or aging tests
Matched Public Lift (Boost)
-0.4p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of Gemini 4 Hydrogen
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (8)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #6/50 | 89.8p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #11/46 | 79.7p |
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #9/27 | 75.7p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #20/50 | 61.2p |
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #21/46 | 58.8p |
| ARC-AGI-2 | Private / Fresh | General Knowledge & QA | #4/22 | 91.9p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #6/47 | 89.6p |
| LiveBench | Private / Fresh | General Knowledge & QA | #12/28 | 71.1p |
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 | #9/49 | 82.3p |
Legacy & Vulnerable Benchmarks (Tiers C & D) (4)
Public or aging benchmarks prone to overfitting and training-data leaks.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| GDP.pdf | Public / Aging | Agentic & Enterprise | #11/50 | 79.6p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #12/41 | 77.4p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #14/50 | 73.5p |
| Autoform-Hard | Public / Aging | Math & Scientific Reasoning | #5/8 | 61.0p |