True Index: Domain Rankings
Head-to-Head: Clean Evals vs. Legacy Benchmarks
| Capability Domain | Clean Evals (Tiers S & A) | Legacy Benchmarks (Tiers C & D) | Public Lift (Boost) |
|---|---|---|---|
| Agentic & Enterprise | 31.9p | 32.6p | +0.7p |
| Coding & SWE | 25.6p | 28.6p | +3.0p |
| General Knowledge & QA | 49.1p | 74.2p | +25.1p |
| Math & Scientific Reasoning | 23.9p | 33.4p | +9.5p |
Audited Benchmark Performance of Gemini 3.8 Flash
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 |
|---|---|---|---|---|
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #30/50 | 40.8p |
| MKA (Multimodal Knowledge Agent) | Private / Fresh | Agentic & Enterprise | #20/23 | 30.0p |
| Harvey LAB-AA v1.1 | Private / Fresh | Agentic & Enterprise | #21/21 | 29.6p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #34/46 | 27.8p |
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #25/27 | 26.7p |
| Code2Video-AA | Private / Fresh | Coding & SWE | #20/23 | 18.9p |
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #45/46 | 8.4p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #46/50 | 8.2p |
| ARC-AGI-2 | Private / Fresh | General Knowledge & QA | #11/22 | 62.1p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #21/47 | 57.9p |
| AA-AnalystAgent | Private / Fresh | Agentic & Enterprise | #13/24 | 51.1p |
| AA-3D | Private / Fresh | Coding & SWE | #18/22 | 36.9p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #24/40 | 36.6p |
| CyberBench v1.1 | Private / Fresh | Coding & SWE | #21/25 | 28.6p |
| LiveBench | Private / Fresh | General Knowledge & QA | #25/28 | 27.3p |
| Code Migration v1.1 | Private / Fresh | Coding & SWE | #21/24 | 15.7p |
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 | #20/49 | 60.4p |
| VIALS-AA | Semi-Exposed | Math & Scientific Reasoning | #16/23 | 31.8p |
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 |
|---|---|---|---|---|
| GDP.pdf | Public / Aging | Agentic & Enterprise | #26/50 | 49.0p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #26/41 | 42.2p |
| HealthBench | Public / Aging | Math & Scientific Reasoning | #16/16 | 33.1p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #36/50 | 28.6p |
| BioMysteryBench | Public / Aging | Math & Scientific Reasoning | #21/23 | 24.9p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #35/43 | 16.2p |
| MMMU-Pro | Public / Aging | General Knowledge & QA | #5/22 | 74.2p |