True Index: Domain Rankings
Agentic & Enterprise8.2p
#42
2 Top-Tier private testsCoding & SWE5.4p
#42
3 Top-Tier private testsMath & Scientific Reasoning28.2p
#36
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 | 8.2p | 6.1p | -2.1p |
| Coding & SWE | 5.4p | 6.1p | +0.7p |
| Math & Scientific Reasoning | 28.2p | 18.2p | -10.0p |
Clean Evals Avg (Tiers S & A)
18.3p
8 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
10.1p
6 public or aging tests
Matched Public Lift (Boost)
-3.7p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of Beam 1.0
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (8)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #30/46 | 38.8p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #42/50 | 16.3p |
| Code2Video-AA | Private / Fresh | Coding & SWE | #23/23 | 8.0p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #46/46 | 0.7p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #50/50 | 0.0p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #33/47 | 31.6p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #32/40 | 17.6p |
| Code Migration v1.1 | Private / Fresh | Coding & SWE | #23/24 | 7.6p |
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 | #46/49 | 6.2p |
Legacy & Vulnerable Benchmarks (Tiers C & D) (6)
Public or aging benchmarks prone to overfitting and training-data leaks.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| Autoform-Hard | Public / Aging | Math & Scientific Reasoning | #7/8 | 27.0p |
| BioMysteryBench | Public / Aging | Math & Scientific Reasoning | #23/23 | 16.9p |
| GDP.pdf | Public / Aging | Agentic & Enterprise | #44/50 | 12.2p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #38/41 | 10.7p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #47/50 | 6.1p |
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #42/43 | 0.0p |