Mistral AI, open weights
Ministral 3 8B 2512 (batch)
Ministral 3 8B 2512 (batch) by Mistral AI has 1 published benchmark result on Noometry, not yet enough to be ranked. API pricing starts at $0.075 per million input tokens and $0.075 per million output tokens, with a 128K-token context window.
Last verified
Specifications
- Noometry rank
- Unranked
- Index score
- Not ranked
- Evidence
- Sparse 1 results
- Provider
Mistral AI- Released
- December 2, 2025
- Weights
- Open weights
- Reasoning
- No
- Context window
- 128K
- Max output
- 4K
- Input price
- $0.075 / M
- Output price
- $0.075 / M
- Blended price
- $0.075 / M
- Output speed
- Not measured
- Value
- Not ranked
- Knowledge cutoff
- Unknown
- Input
- text, image
- Hugging Face
- mistralai/Ministral-3-8B-Instruct-2512
Category scores
Each category score combines every public result we have in that category.
- Knowledge 27.1
| Category | Score | Rank | Results |
|---|---|---|---|
| Knowledge | 27.1 | — | 1 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Vectara Hallucination Rate (lower is better) | 21.7% | #93 of 96, top 97% | Vectara Hallucination Leaderboard |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| bedrock | $0.15 | $0.15 | — | 2026-10-10 |
| openrouter | $0.075 | $0.075 | $0.0075 | 2026-10-10 |
Compare Ministral 3 8B 2512 (batch)
- Ministral 3 8B 2512 (batch) vs GPT-6 Astra
- Ministral 3 8B 2512 (batch) vs Claude Fable 5.1
- Ministral 3 8B 2512 (batch) vs Claude Opus 5.5
- Ministral 3 8B 2512 (batch) vs Claude Opus 5
- Ministral 3 8B 2512 (batch) vs Claude Fable 5
- Ministral 3 8B 2512 (batch) vs GPT-6.1 Sol
- Ministral 3 8B 2512 (batch) vs Gemini 3.8 Flash
- Ministral 3 8B 2512 (batch) vs Kimi K3
- Ministral 3 8B 2512 (batch) vs Grok 4.6
- Ministral 3 8B 2512 (batch) vs Qwen3.8 Max
- Ministral 3 8B 2512 (batch) vs GLM-5.3
- Ministral 3 8B 2512 (batch) vs Muse Spark 1.3
- Ministral 3 8B 2512 (batch) vs DeepSeek V4 Pro
- Ministral 3 8B 2512 (batch) vs MiMo-V2.6-Pro
Other Mistral AI models
- Mistral Large 443.1
- Mistral Medium 3.540.2
- Mistral Large 339.1
- Mistral Medium36.3
- Magistral Medium35.2
- Devstral Small 250534.3
- Mistral Small33.4
- Pixtral Large32.2
Frequently asked questions
How good is Ministral 3 8B 2512 (batch)?
Ministral 3 8B 2512 (batch) by Mistral AI has 1 published benchmark result on Noometry, not yet enough to be ranked. API pricing starts at $0.075 per million input tokens and $0.075 per million output tokens, with a 128K-token context window.
How much does Ministral 3 8B 2512 (batch) cost?
Ministral 3 8B 2512 (batch) costs $0.075 per million input tokens and $0.075 per million output tokens on openrouter, with cached input at $0.0075.
What is Ministral 3 8B 2512 (batch)'s context window?
Ministral 3 8B 2512 (batch) accepts up to 128K tokens of input and can write up to 4K tokens in one response.
Is Ministral 3 8B 2512 (batch) open source?
Yes. Ministral 3 8B 2512 (batch)'s weights are downloadable from Hugging Face (mistralai/Ministral-3-8B-Instruct-2512); check the license for commercial terms.