Mistral AIMixtral 8x22B
Best configuration ranks #536 of 610 on the BenchLeader Index at 39.0 ±5.4. Last measured 2 Sept 2026. Released 17 Apr 2024.
- Blended price
- $3.00/M
- $2.00 in · $6.00 out
- Output speed
- 61 tok/s
- First answer
- 0.54 s
- Context
- 66k
- Overall index39
- Reasoning39
- Coding29
- Agents & tools37
- Knowledge28
- Human preference38
- Composite36
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 |
|---|---|---|
| LMArena Hard Prompts | 1243#270 | LMArena |
| GPQA Diamond (AA)not in index | 33.2%#475 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 4.0%#466 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| WeirdML | 3.2%#149 | WeirdML |
| LMArena Coding | 1277#265 | LMArena |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1229#274 | LMArena |
Composite
| Benchmark | default | Source |
|---|---|---|
| Epoch Capabilities Indexnot in index | 122#157 | Epoch AI Benchmarking Hub |
| AA Intelligence Index | 5.7#474 | Artificial Analysis |
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 | 62 tok/s | 0.55 s | $2.00 | $6.00 | 66k | – |
| Mistral (ZDR) | 61 tok/s | 0.53 s | $2.00 | $6.00 | 66k | – |
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 | $0.0026 | – | 5.4 s |
| Summarise a 30-page report | 12,000 / 600 | $0.028 | – | 10.3 s |
| Code edit | 6,000 / 1,500 | $0.021 | – | 25.0 s |
| Agentic coding session | 60,000 / 4,000 | $0.144 | – | 1.1 min |
| Structured extraction | 2,000 / 200 | $0.0052 | – | 3.8 s |
See also
Data as of 9 Sept 2026. Compare with another model.