LLM
Magistral Small 1.2
Mistral AI
Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error
Specifications
- Type
- LLM
- Released
- September 17, 2025
- Output speed
- 106 tok/s
- Latency (TTFT)
- 0.38s
- API pricing
- $0.50 in · $1.50 out / 1M tokens
Benchmarks
Reasoning
| GPQA Diamond | 66.3 |
Coding
| LiveCodeBench | 72.3 |
Math
| AIME 2025 | 80.3 |
General
| MMLU-Pro | 76.8 |
| Humanity’s Last Exam | 6.1 |