True Index: Domain Rankings
Agentic & Enterprise91.2p
#3
3 Top-Tier private testsCoding & SWE70.2p
#13
3 Top-Tier private testsMath & Scientific Reasoning75.3p
#12
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 | 91.2p | 95.7p | +4.5p |
| Coding & SWE | 70.2p | 80.6p | +10.4p |
| Math & Scientific Reasoning | 75.3p | 68.5p | -6.8p |
Clean Evals Avg (Tiers S & A)
78.0p
9 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
81.6p
5 public or aging tests
Matched Public Lift (Boost)
+1.1p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of Muse Wonder Full
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (9)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| Harvey LAB-AA v1.1 | Private / Fresh | Agentic & Enterprise | #2/21 | 100.0p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #4/50 | 93.9p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #11/50 | 79.6p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #12/46 | 77.5p |
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #19/46 | 61.9p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #2/40 | 88.7p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #13/47 | 75.4p |
| CyberBench v1.1 | Private / Fresh | Coding & SWE | #8/25 | 68.7p |
| Code Migration v1.1 | Private / Fresh | Coding & SWE | #9/24 | 64.3p |
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 | #13/49 | 75.0p |
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 |
|---|---|---|---|---|
| GDP.pdf | Public / Aging | Agentic & Enterprise | #1/50 | 100.0p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #3/43 | 91.4p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #10/50 | 80.6p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #14/41 | 72.3p |
| BioMysteryBench | Public / Aging | Math & Scientific Reasoning | #11/23 | 64.7p |