# Mistral Large 4 - BenchAudit True Index Profile

**Contamination Sensitivity: Elevated**

> The Verdict: Strong on Public Leaderboards, Vulnerable to Fresh Evals. Mistral Large 4 (evaluated at high effort) shows a noticeable divergence between public benchmark claims (32.8p) and private evaluation performance (24.7p), posting a +10.4p Low-Tier Boost across 3 matched domains, especially in Coding & SWE (+16.2p boost) and Agentic & Enterprise (+10.3p boost). Private tests reveal meaningful headroom beneath its legacy scores.

- **Canonical URL:** https://benchaudit.org/models/mistral-large-4__high/
- **True Index Rank:** #38 of 44
- **Creator:** Mistral
- **Weights:** Open Weights
- **Clean Evals Avg (Tiers S & A):** 24.7p (7 evals)
- **Legacy Benchmarks Avg (Tiers C & D):** 32.8p (4 evals)
- **Low-Tier Boost (Matched Delta):** +10.4p
- **Updated:** 2026-11-22

## True Index: Domain Rankings

| Capability Domain | Sub-Rank | Clean Evals (S/A) Avg | Top-Tier Evals |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | #37 | 26.4p | 3 |
| Coding & SWE | #39 | 16.5p | 1 |
| Math & Scientific Reasoning | #40 | 22.3p | 2 |

## 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 (26.4p) | 1 (36.7p) | +10.3p |
| Coding & SWE | 1 (16.5p) | 1 (32.7p) | +16.2p |
| Math & Scientific Reasoning | 2 (22.3p) | 2 (29.0p) | +6.7p |

## Audited Benchmark Performance of Mistral Large 4

| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
| --- | --- | --- | ---: | ---: |
| [MLCR-AA](https://benchaudit.org/benchmarks/mlcr-aa/) | Private / Fresh | Math & Scientific Reasoning | #30/46 | 38.8p |
| [GDP.pdf](https://benchaudit.org/benchmarks/gdp-pdf/) | Public / Aging | Agentic & Enterprise | #32/50 | 36.7p |
| [AA-Omniscience v1.1](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/) | Private / Fresh | General Knowledge & QA | #32/47 | 33.8p |
| [AutomationBench-AA](https://benchaudit.org/benchmarks/automationbench-aa/) | Private / Fresh | Agentic & Enterprise | #34/50 | 32.7p |
| [Terminal-Bench 4.0](https://benchaudit.org/benchmarks/terminal-bench-4-0/) | Public / Aging | Coding & SWE | #34/50 | 32.7p |
| [BioMysteryBench](https://benchaudit.org/benchmarks/biomysterybench/) | Public / Aging | Math & Scientific Reasoning | #19/23 | 30.8p |
| [Terminal-Bench-Science 0.1](https://benchaudit.org/benchmarks/terminal-bench-science-0-1/) | Public / Aging | Math & Scientific Reasoning | #31/41 | 27.1p |
| [MKA (Multimodal Knowledge Agent)](https://benchaudit.org/benchmarks/mka/) | Private / Fresh | Agentic & Enterprise | #21/23 | 26.0p |
| [HLE-Diamond](https://benchaudit.org/benchmarks/hle-diamond/) | Semi-Exposed | General Knowledge & QA | #39/49 | 20.8p |
| [AA-Briefcase v1.1](https://benchaudit.org/benchmarks/aa-briefcase-v1-1/) | Private / Fresh | Agentic & Enterprise | #40/50 | 20.4p |
| [FrontierCode-AA 2.0](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/) | Private / Fresh | Coding & SWE | #39/46 | 16.5p |
| [CritPt v2](https://benchaudit.org/benchmarks/critpt-v2/) | Private / Fresh | Math & Scientific Reasoning | #37/40 | 5.8p |
| [VIALS-AA](https://benchaudit.org/benchmarks/vials-aa/) | Semi-Exposed | Math & Scientific Reasoning | #23/23 | 0.0p |
