Analysis of Mistral's Ministral 3 3B and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.
Ministral 3 3B
Mistral
Vision ModelApache 2.0
Analysis of Mistral's Ministral 3 3B 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 02, 2025
- Window
- 256k
PricingPer 1M tokens
- Input
- $0.1
- Output
- $0.1
- Blended 3:1
- $0.1
Capabilities
- Speed
- 168 t/s
- Input
- Output
- Reasoning tokens
Latency
- TTFT
- 0.55 ms
- 500 token response
- 3.52 s
Benchmarks
- Intelligence
- ●○○○○
- Math
- ●○○○○
- Coding
- ○○○○○
- MMLU Pro
- 52.4%
- GPQA
- 35.8%
- HLE
- 5.3%
- SciCode
- 14.4%
- AIME
- 22.0%
- LiveCodeBench
- 24.7%