True Index: Domain Rankings
Agentic & Enterprise68.0p
#16
5 Top-Tier private testsCoding & SWE71.7p
#12
5 Top-Tier private testsMath & Scientific Reasoning53.2p
#22
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 | 68.0p | 52.3p | -15.7p |
| Coding & SWE | 71.7p | 86.5p | +14.9p |
| Math & Scientific Reasoning | 53.2p | 60.4p | +7.3p |
Clean Evals Avg (Tiers S & A)
67.9p
16 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
66.4p
8 public or aging tests
Matched Public Lift (Boost)
+5.2p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of Gemini 4 Argon
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 | #3/50 | 95.9p |
| MKA (Multimodal Knowledge Agent) | Private / Fresh | Agentic & Enterprise | #7/23 | 83.3p |
| Code2Video-AA | Private / Fresh | Coding & SWE | #6/23 | 70.2p |
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #12/27 | 67.8p |
| Harvey LAB-AA v1.1 | Private / Fresh | Agentic & Enterprise | #13/21 | 59.9p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #23/46 | 52.6p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #29/50 | 42.9p |
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #37/46 | 24.2p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #8/47 | 86.3p |
| CyberBench v1.1 | Private / Fresh | Coding & SWE | #3/25 | 83.7p |
| AA-3D | Private / Fresh | Coding & SWE | #7/22 | 79.4p |
| ARC-AGI-2 | Private / Fresh | General Knowledge & QA | #8/22 | 75.9p |
| LiveBench | Private / Fresh | General Knowledge & QA | #11/28 | 74.4p |
| Code Migration v1.1 | Private / Fresh | Coding & SWE | #7/24 | 72.4p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #11/40 | 67.5p |
| AA-AnalystAgent | Private / Fresh | Agentic & Enterprise | #12/24 | 58.2p |
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 | #11/49 | 79.2p |
| VIALS-AA | Semi-Exposed | Math & Scientific Reasoning | #8/23 | 65.9p |
Legacy & Vulnerable Benchmarks (Tiers C & D) (8)
Public or aging benchmarks prone to overfitting and training-data leaks.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| SWE-bench Pro V2 | Public / Aging | Coding & SWE | #1/8 | 92.5p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #10/50 | 80.6p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #11/41 | 79.9p |
| BioMysteryBench | Public / Aging | Math & Scientific Reasoning | #8/23 | 76.7p |
| GDP.pdf | Public / Aging | Agentic & Enterprise | #24/50 | 53.1p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #20/43 | 51.5p |
| Autoform-Hard | Public / Aging | Math & Scientific Reasoning | #6/8 | 47.4p |
| HealthBench | Public / Aging | Math & Scientific Reasoning | #15/16 | 37.8p |