Mistral
Magistral Medium 1.2
Magistral Medium 1.2 by Mistral — compare inference API pricing across providers.
Contact providers for pricing
API Pricing
No pricing data available for this model at the moment.
Prices updated daily. Last check: Jul 16, 2026
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
17.9 / 100
Coding
21.3 / 100
Math
82.0 / 100
Output Speed
41.6 t/s
Latency (TTFT)
584ms
Reasoning & Knowledge
- MMLU-Pro81.5%
- GPQA Diamond73.9%
- Humanity's Last Exam9.6%
Coding
- LiveCodeBench75.0%
- SciCode39.2%
Math
- AIME 202582.0%
Agentic & Tool Use
- Terminal-Bench Hard12.9%
- Terminal-Bench v2.112.4%
- τ²-bench52.0%
- τ-bench Banking5.6%
Instruction & Long Context
- IFBench43.0%
- Long-Context Reasoning51.3%
Benchmarks measured Jul 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- Mistral
- Modalities
- Text
Capabilities
- Tool Calling
- No
- Open Source
- No