Pricing source: Mistral announcement, December 2025.
Devstral 2 powers Mistral Vibe 2.0 with support for custom subagents, multi-choice clarifications, and slash-command skills. API access moved from free to paid pricing.
| Benchmark | Score | Rank | Source |
|---|---|---|---|
| GPQA | 59.4% | 145 of 159 | Artificial Analysis, Jul 2026 ↗ |
| Speed (tok/s) | 148 tok/s | 37 of 126 | Artificial Analysis, Sep 2026 ↗ |
| Hallucination Rate (lower is better) | 85.3% | 81 of 109 | Artificial Analysis, Aug 2026 ↗ |
| MMLU-Pro | 76.2% | 56 of 73 | Artificial Analysis, Jul 2026 ↗ |
| LiveCodeBench | 44.8% | 43 of 47 | Artificial Analysis, Jul 2026 ↗ |
Rank is against every model in our database with a sourced score on that benchmark, each counted once with its best score.
Mistral AI released Vibe 2.0, a terminal-native coding agent powered by Devstral 2, adding custom subagents, multi-choice clarifications, and slash-command skills. Devstral 2 API pricing is now $0.40/M input tokens and $2.00/M output tokens, with a smaller variant at $0.10/$0.30 per million tokens.