Mistral
Devstral Small 2
Devstral Small 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: Aug 27, 2026
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
17.7 / 100
Coding
29.3 / 100
Math
34.3 / 100
Output Speed
141 t/s
Latency (TTFT)
629ms
Reasoning & Knowledge
- MMLU-Pro67.8%
- GPQA Diamond53.2%
- Humanity's Last Exam3.5%
Coding
- LiveCodeBench34.8%
- SciCode28.8%
Math
- AIME 202534.3%
Agentic & Tool Use
- Terminal-Bench Hard16.7%
- Terminal-Bench v2.129.6%
- τ²-bench23.4%
- τ-bench Banking10.7%
Instruction & Long Context
- IFBench31.2%
- Long-Context Reasoning27.0%
Benchmarks measured Aug 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- Mistral
- Modalities
- Text
Capabilities
- Tool Calling
- No
- Open Source
- No