Mistral AIMinistral 8B
Ministral 8B is a Mistral AI open-weights model, released 16 Oct 2024. Its best configuration ranks #724 of 785 on the BenchLeader Index at 37.9 ±4.5, in the lower half. The ± is the point: 208 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in coding (38) and lowest in agents & tools (25). At $0.150 per million tokens blended it is among the cheapest fifth of ranked models. Last measured 22 Oct 2026.
- Blended price
- $0.150/M
- $0.150 in · $0.150 out
- Output speed
- –
- First answer
- –
- Context
- 262k
- Full answer
- –
- Cost per run
- –
- Released
- 16 Oct 2024
- Overall index38
- Reasoning28
- Coding38
- Agents & tools25
- Maths35
- Human preference38
Versions
Mistral AI has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Ministral 3 8B | 2 Dec 2025 | 38.4 | #714 |
| Ministral 8Bthis page | 16 Oct 2024 | 37.9 | #724 |
How its index has moved
8 Sept 2026 to 19 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond | 27.1%#279 | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | 1251#291 | Arena (LMArena) | |
| DTBenchnot in index | 45.7%#225 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1274#293 | Arena (LMArena) |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| BFCL Overall | 11.1%#79 | Berkeley Function Calling Leaderboard | |
| BrowseCompnot in index | 0.3%#36 | OpenAI |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MATH Level 5 | 14.9%#83 | Epoch AI Benchmarking Hub | |
| Arena Maths | 1214#286 | Arena (LMArena) |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Instruction Followingnot in index | 1211#297 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1238#293 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1222#281 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1208#293 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1259#287 | Arena (LMArena) |
Price history
The price above, per 1M tokens, every day it changed.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.015 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | $0.0001 | – |
| Summarize a 30-page report | 12,000 / 600 | $0.0019 | $0.0007 | – |
| Code edit | 6,000 / 1,500 | $0.0011 | $0.0005 | – |
| Agentic coding session | 60,000 / 4,000 | $0.0096 | $0.0035 | – |
| Structured extraction | 2,000 / 200 | $0.0003 | $0.0001 | – |
More from Mistral AI
See also
Questions people ask
- What are Ministral 8B's benchmark scores?
- As of 25 Oct 2026, Ministral 8B scores 37.9 ±4.5 on the BenchLeader Index, strongest in coding (38) and weakest in agents & tools (25). That rests on 7 independent benchmark results, and every score on this page links to its publisher.
- How does Ministral 8B rank?
- Ministral 8B is #724 of 785 ranked configurations on 25 Oct 2026. 208 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Ministral 8B cost per 1M tokens?
- As of 25 Oct 2026, Ministral 8B costs $0.150 per 1M input tokens and $0.150 per 1M output tokens, $0.150 blended (three input tokens per output token). The list price last changed on 20 Oct 2026.
- When was Ministral 8B released?
- Mistral AI released Ministral 8B on 16 Oct 2024.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Ministral 8B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/ministral-8b.