True Index: Domain Rankings
Agentic & Enterprise26.4p
#37
3 Top-Tier private testsCoding & SWE16.5p
#39
1 Top-Tier private testMath & Scientific Reasoning22.3p
#40
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 | 26.4p | 36.7p | +10.3p |
| Coding & SWE | 16.5p | 32.7p | +16.2p |
| Math & Scientific Reasoning | 22.3p | 29.0p | +6.7p |
Clean Evals Avg (Tiers S & A)
24.7p
7 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
32.8p
4 public or aging tests
Matched Public Lift (Boost)
+10.4p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of Mistral Large 4
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (7)
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 | #34/50 | 32.7p |
| MKA (Multimodal Knowledge Agent) | Private / Fresh | Agentic & Enterprise | #21/23 | 26.0p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #40/50 | 20.4p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #39/46 | 16.5p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #32/47 | 33.8p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #37/40 | 5.8p |
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 | #39/49 | 20.8p |
| VIALS-AA | Semi-Exposed | Math & Scientific Reasoning | #23/23 | 0.0p |
Legacy & Vulnerable Benchmarks (Tiers C & D) (4)
Public or aging benchmarks prone to overfitting and training-data leaks.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| GDP.pdf | Public / Aging | Agentic & Enterprise | #32/50 | 36.7p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #34/50 | 32.7p |
| BioMysteryBench | Public / Aging | Math & Scientific Reasoning | #19/23 | 30.8p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #31/41 | 27.1p |