Analysis of Mistral's Devstral Small 2 and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.
Devstral Small 2
Mistral
Vision ModelApache 2.0
Analysis of Mistral's Devstral Small 2 and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.
Context
- Release Date
- Dec 09, 2025
- Window
- 256k
PricingPer 1M tokens
- Input
- $
- Output
- $
- Blended 3:1
- $
Capabilities
- Speed
- 67 t/s
- Input
- Output
- Reasoning tokens
Latency
- TTFT
- 1.18 ms
- 500 token response
- 8.63 s
Benchmarks
- Intelligence
- ●○○○○
- Math
- ●●○○○
- Coding
- ●○○○○
- MMLU Pro
- 67.8%
- GPQA
- 53.2%
- HLE
- 3.4%
- SciCode
- 28.8%
- AIME
- 34.3%
- LiveCodeBench
- 34.8%