Analysis of Mistral's Ministral 3 14B 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 14B
Mistral
Vision ModelApache 2.0
Analysis of Mistral's Ministral 3 14B 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
- $0.2
- Output
- $0.2
- Blended 3:1
- $0.2
Capabilities
- Speed
- 98 t/s
- Input
- Output
- Reasoning tokens
Latency
- TTFT
- 0.77 ms
- 500 token response
- 5.88 s
Benchmarks
- Intelligence
- ●○○○○
- Math
- ●●○○○
- Coding
- ●○○○○
- MMLU Pro
- 69.3%
- GPQA
- 57.2%
- HLE
- 4.6%
- SciCode
- 23.6%
- AIME
- 30.0%
- LiveCodeBench
- 35.1%