Mistral AIMinistral 8B (latest)
Best configuration ranks #552 of 610 on the BenchLeader Index at 38.2 ±5.4. Last measured 2 Sept 2026. Released 16 Oct 2024.
- Blended price
- $0.100/M
- $0.100 in · $0.100 out
- Output speed
- 42 tok/s
- First answer
- 0.30 s
- Context
- 128k
- Overall index38
- Reasoning28
- Coding39
- Agents & tools25
- Maths30
- Human preference39
Benchmark results
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 | default | Source |
|---|---|---|
| GPQA Diamond | 27.1%#258 | Epoch AI Benchmarking Hub |
| LMArena Hard Prompts | 1251#267 | LMArena |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1275#268 | LMArena |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| BFCL Overall | 11.1%#79 | Berkeley Function Calling Leaderboard |
Maths
| Benchmark | default | Source |
|---|---|---|
| MATH Level 5 | 14.9%#77 | Epoch AI Benchmarking Hub |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1237#269 | LMArena |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Mistral (ZDR) | 45 tok/s | 0.31 s | $0.150 | $0.150 | 262k | – |
| Mistral | 39 tok/s | 0.29 s | $0.150 | $0.150 | 262k | – |
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. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | – | 7.4 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0013 | – | 14.6 s |
| Code edit | 6,000 / 1,500 | $0.0008 | – | 36.0 s |
| Agentic coding session | 60,000 / 4,000 | $0.0064 | – | 1.6 min |
| Structured extraction | 2,000 / 200 | $0.0002 | – | 5.1 s |
See also
Data as of 9 Sept 2026. Compare with another model.