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 | 3.0p | 4.7p | +1.6p |
| Coding & SWE | 5.1p | 1.0p | -4.1p |
| General Knowledge & QA | 1.0p | 31.1p | +30.1p |
| Math & Scientific Reasoning | 0.0p | 10.7p | +10.7p |
Audited Benchmark Performance of Apodex 1.1
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (5)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #44/46 | 5.1p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #48/50 | 4.1p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #49/50 | 2.0p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #47/47 | 1.0p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #39/40 | 0.0p |
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 | #47/49 | 4.2p |
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-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #38/41 | 10.7p |
| GDP.pdf | Public / Aging | Agentic & Enterprise | #46/50 | 7.1p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #41/43 | 2.2p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #49/50 | 1.0p |
| MMMU-Pro | Public / Aging | General Knowledge & QA | #15/22 | 31.1p |