Mistral
Ministral 3 8B
Ministral 3 8B 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
9.0 / 100
Coding
9.7 / 100
Math
31.7 / 100
Output Speed
128 t/s
Latency (TTFT)
521ms
Reasoning & Knowledge
- MMLU-Pro64.2%
- GPQA Diamond47.1%
- Humanity's Last Exam4.3%
Coding
- LiveCodeBench30.3%
- SciCode20.8%
Math
- AIME 202531.7%
Agentic & Tool Use
- Terminal-Bench Hard4.5%
- Terminal-Bench v2.14.1%
- τ²-bench26.6%
- τ-bench Banking3.7%
Instruction & Long Context
- IFBench29.1%
- Long-Context Reasoning25.3%
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