True Index: Domain Rankings
Agentic & Enterprise91.0p
#4
3 Top-Tier private testsCoding & SWE88.8p
#5
2 Top-Tier private testsMath & Scientific Reasoning68.6p
#14
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 | 91.0p | 79.3p | -11.7p |
| Coding & SWE | 88.8p | 98.0p | +9.2p |
| Math & Scientific Reasoning | 68.6p | 84.8p | +16.2p |
Clean Evals Avg (Tiers S & A)
84.6p
10 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
87.4p
5 public or aging tests
Matched Public Lift (Boost)
+3.9p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of Gemini 4 Carbon
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (10)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| MKA (Multimodal Knowledge Agent) | Private / Fresh | Agentic & Enterprise | #3/23 | 99.6p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #2/50 | 98.0p |
| Vibe Code Bench 1-100 v1.1 | Private / Fresh | Coding & SWE | #2/10 | 95.6p |
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #5/27 | 89.9p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #10/46 | 81.9p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #13/50 | 75.5p |
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #26/46 | 47.2p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #3/47 | 97.3p |
| LiveBench | Private / Fresh | General Knowledge & QA | #7/28 | 87.8p |
| ARC-AGI-2 | Private / Fresh | General Knowledge & QA | #6/22 | 85.1p |
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 | #4/49 | 93.8p |
| VIALS-AA | Semi-Exposed | Math & Scientific Reasoning | #3/23 | 90.9p |
Legacy & Vulnerable Benchmarks (Tiers C & D) (5)
Public or aging benchmarks prone to overfitting and training-data leaks.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #2/50 | 98.0p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #5/41 | 95.0p |
| GDP.pdf | Public / Aging | Agentic & Enterprise | #9/50 | 83.7p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #10/43 | 75.0p |
| Autoform-Hard | Public / Aging | Math & Scientific Reasoning | #4/8 | 74.5p |