Ministral 8B Instruct
Unavailable in this round
Language model
Ministral 8B Instruct
Mistral AI
- Released
- October 16, 2024
- Data date
- September 26, 2026
- Input
- Text
- Output
- Text
Ministral 8B Instruct is the earlier 8B instruction-tuned checkpoint with 131,000 tokens of context and function calls. It uses the Mistral Research License and targets local and edge applications without automatically authorizing commercial use.
Ministral 8B names the same model family.
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
MT-Bench (Show measurement, test conditions, and source)
- Source value
- 8.3
- Score
- 8.3
- Metric
- GPT-4o judge score; scale not stated
- Unit
- No unit provided
- Category
- chat
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Mistral AI Ministral 8B Instruct model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact Ministral 8B Instruct row in the Instruct Models table; benchmark comparison used the publisher's internal framework. Prompt and sample details are not stated.
Arena Hard (Show measurement, test conditions, and source)
- Source value
- 70.9
- Score
- 70.9
- Metric
- score as published; scale not stated
- Unit
- No unit provided
- Category
- chat
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Mistral AI Ministral 8B Instruct model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact Ministral 8B Instruct row in the Instruct Models table; benchmark comparison used the publisher's internal framework. Prompt and sample details are not stated.
WildBench (Show measurement, test conditions, and source)
- Source value
- 41.3
- Score
- 41.3
- Metric
- score as published; scale not stated
- Unit
- No unit provided
- Category
- chat
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Mistral AI Ministral 8B Instruct model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact Ministral 8B Instruct row in the Instruct Models table; benchmark comparison used the publisher's internal framework. Prompt and sample details are not stated.
MBPP (Show measurement, test conditions, and source)
- Source value
- 70
- Score
- 70
- Metric
- pass@1; unit/scale not stated
- Unit
- No unit provided
- Category
- coding
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Mistral AI Ministral 8B Instruct model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact Ministral 8B Instruct row in the Instruct Models table; benchmark comparison used the publisher's internal framework. Prompt and sample details are not stated.
HumanEval (Show measurement, test conditions, and source)
- Source value
- 76.8
- Score
- 76.8
- Metric
- pass@1; unit/scale not stated
- Unit
- No unit provided
- Category
- coding
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Mistral AI Ministral 8B Instruct model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact Ministral 8B Instruct row in the Instruct Models table; benchmark comparison used the publisher's internal framework. Prompt and sample details are not stated.
Math (Show measurement, test conditions, and source)
- Source value
- 54.5
- Score
- 54.5
- Metric
- maj@1; unit/scale not stated
- Unit
- No unit provided
- Category
- reasoning
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Mistral AI Ministral 8B Instruct model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact Ministral 8B Instruct row in the Instruct Models table; benchmark comparison used the publisher's internal framework. Prompt and sample details are not stated.
Our tests
SVG short test
One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.
Popularity
19.3 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Input | Documented modalities. Retrieved September 26, 2026. |
| Output | Documented modalities. Retrieved September 26, 2026. |
| Research status | Research date October 15, 2026. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not published | score-units-and-run-details Note The card names several benchmark metrics and the comparison framework but does not state scales for most scores or detailed prompts, task dates and sampling. |
| Additional source | Hugging Face (retrieved October 15, 2026) · Ministral 8B Instruct model card · Editorial description reviewed October 2, 2026 |
| Additional source | Ministral announcement · Editorial description reviewed October 2, 2026 |
| Additional source | Mistral model overview · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |