Mistral AI model product
Ministral 8B
The Ministral-8B-Instruct-2410 is an instruct fine-tuned model for local intelligence, on-device computing, and at-the-edge use cases, significantly outperforming existing models of similar size.
Updated Aug 12, 2026. Default version: Ministral 8B Instruct
LLMBoard score0.0Ministral 8B Instruct
Coverage100%9 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable
Ministral 8B Specifications
Technical details for the model's default version.
- Version
- Ministral 8B Instruct
- Released
- Oct 16, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 8B
- Context window
- 131.1K
- Max output
- 8.2K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Mistral Research License
Ministral 8B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Ministral 8B Benchmark Results
Benchmark scores for Ministral 8B Instruct.
| French MMLU | 57.5% | 01 | 1 | 100.0% | C | |
| MBPP pass@1 | 70.0% | 01 | 1 | 100.0% | C | |
| AGIEval | 48.3% | 09 | 10 | 11.1% | C | |
| MT-Bench | 83.0% | 09 | 12 | 27.3% | C | |
| Arena Hard | 70.9% | 11 | 26 | 60.0% | C | |
| Winogrande | 75.3% | 13 | 22 | 42.9% | C | |
| TriviaQA | 65.5% | 15 | 18 | 17.6% | C | |
| ARC-C | 71.9% | 18 | 34 | 48.5% | C | |
| MATH | 54.5% | 52 | 71 | 27.1% | C | |
| HumanEval | 34.8% | 66 | 66 | 0.0% | C | |
| MMLU | 65.0% | 92 | 100 | 8.1% | C |
Ministral 8B Arena Results
Preference and agent-evaluation results for the default version.
| text | overall | 294 | 1191.0 | 4,781 | N/A | |
| text style control | overall | 296 | 1237.5 | 4,781 | N/A |
Ministral 8B Runtime Performance
Provider-specific output speed and catalog latency for Ministral 8B Instruct. Runtime does not affect the capability score.
| Mistral AI | 0.1 tok/s | 0.18 s | 128K | 128K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Ministral 8B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.15 input, $0.15 output per 1M via Pioneer
- Tracked offerings
- 1
| Pioneer | mistralai/Ministral-8B-Instruct-2410 | global | $0.15 | $0.15 | 128K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Ministral 8B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Ministral 8B Instruct | 0.0 | 8B | 131.1K | 8.2K | Yes | Mistral Research License |
What is Ministral 8B?
Key information about Ministral 8B and its available data.
The Ministral-8B-Instruct-2410 is an instruct fine-tuned model for local intelligence, on-device computing, and at-the-edge use cases, significantly outperforming existing models of similar size.
Data as of 2026-08-11.
Ministral 8B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Ministral 8B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Mistral NeMo
Mistral AI
MA
Pixtral 12B
Mistral AI
MA
Codestral 22B
Mistral AI
MA
Mistral Large 2
Mistral AI
MA
Mistral Small 3 24B
Mistral AI
MA
Mistral Small 3.1 24B
Mistral AI
FAQ
Common questions about Ministral 8B.
When was Ministral 8B released?
Ministral 8B's default version was released on Oct 16, 2024.
How much does Ministral 8B cost?
No official standard PAYG price is currently available for Ministral 8B. The lowest tracked third-party offer starts at $0.15 input and $0.15 output via Pioneer.
Who created Ministral 8B?
Ministral 8B was created by Mistral AI.
What is the context window for Ministral 8B?
The default version has a 131.1K token context window.
Is Ministral 8B open weight?
Yes. The default version is marked as open weight under Mistral Research License.
How many API providers offer Ministral 8B?
1 provider offerings are linked to the default version.
What models should I compare Ministral 8B with?
Nearby ranked alternatives include GPT-5.1-Codex-Mini, Gemma 3n E2B LiteRT, MedGemma 4B IT.