mistral-large-4-oss: benchmark results
The open-weight release of Mistral Large 4 on October 29, 2026, which Mistral describes as an improved model after further reinforcement learning on the October 6 public preview. Natively multimodal MoE with about 1T total and 52B active parameters; Mistral publishes FP8 weights, with an NVFP4 quantization in a separate repository. Provider: Mistral. Released 2026-10-29. Access: Open.
Aggregate Rating 1803 ± 25, rank #69 of 1647 rated models, from 75 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA GDP.pdf - Legal - Criterion Pass Rate | 88.25 | Criterion Pass Rate (%) | 99.6 |
| AA-Briefcase - DOCX - Rubric Pass Rate | 57.4 | Rubric Pass Rate (%) | 94.7 |
| AA-Omniscience Hallucination Rate | 24.82 | Hallucination Rate (%) | 90.2 |
| AutomationBench-AA - Marketing - Raw Objective Completion | 85.91 | Raw Objective Completion (%) | 87.1 |
| AA-Briefcase - PDF - Rubric Pass Rate | 51.72 | Rubric Pass Rate (%) | 82.3 |
| AutomationBench-AA - Sales - Raw Objective Completion | 83.6 | Raw Objective Completion (%) | 82.3 |
| AA GDP.pdf - HR - Criterion Pass Rate | 78.08 | Criterion Pass Rate (%) | 82.2 |
| AutomationBench-AA - Support - Raw Objective Completion | 88.27 | Raw Objective Completion (%) | 80.6 |
| AA-Briefcase | 48.37 | Rubric Pass Rate (%) | 80.2 |
| AutomationBench-AA - HR - Raw Objective Completion | 72.73 | Raw Objective Completion (%) | 79.3 |
| Vals AI Vibe Code Bench | 81.56 | Accuracy (%) | 78.5 |
| AA GDP.pdf - Insurance - Criterion Pass Rate | 76.93 | Criterion Pass Rate (%) | 78.4 |
Interactive version: theaggregate.ai/model?slug=mistral-large-4-oss · How It Works · Data refreshed daily, snapshot 2026-10-30.