Mistral-Small-4-119B-2603-NVFP4: benchmark results
Provider: Mistral. Access: Open.
Aggregate Rating 1577 ± 48, rank #1298 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BenCzechMark - Czech Language Understanding | 75.21 | Duel Win Score (%) | 91 |
| BenCzechMark - Czech Math Reasoning | 80.45 | Duel Win Score (%) | 91 |
| BenCzechMark - Factual Knowledge | 69.78 | Duel Win Score (%) | 89.7 |
| BenCzechMark - Sentiment | 75.64 | Duel Win Score (%) | 89.7 |
| BenCzechMark | 70.03 | Average Duel Win Score (%) | 83.3 |
| BenCzechMark - NER | 70.51 | Duel Win Score (%) | 71.2 |
| BenCzechMark - Reading Comprehension | 63.25 | Duel Win Score (%) | 69.9 |
| BenCzechMark - NLI | 55.37 | Duel Win Score (%) | 61.5 |
| Coding Agent Leaderboard - SWE-Bench Pro -- Ansible (OpenCode) | 38.5 | Score (%) | 37.5 |
| Coding Agent Leaderboard - Shellbench (OpenClaw) | 0.9 | Score (%) | 33.3 |
| Coding Agent Leaderboard - SWE-Bench Pro -- Ansible (Claude Code) | 26 | Score (%) | 0 |
| Coding Agent Leaderboard - SWE-Bench Verified (Claude Code) | 11.8 | Score (%) | 0 |
Interactive version: theaggregate.ai/model?slug=mistral-small-4-119b-2603-nvfp4 · How It Works · Data refreshed daily, snapshot 2026-11-08.