# Mistral Mixtral 8x22B Instruct

As of October 21, 2026, Mistral Mixtral 8x22B Instruct ranks #204 of 213 models overall with 5.7 on the Artificial Analysis Intelligence Index. Its strongest category is knowledge, where it ranks #140 of 147. Mistral Mixtral 8x22B Instruct costs $2.00 per million input tokens and $6.00 per million output tokens. It was released on April 17, 2024.

Page: https://llmbenchmark.ai/models/mixtral-8x22b-instruct
Data from October 21, 2026. Every figure below names the board it was read from and the day.

- Maker: Mistral AI
- Released: April 17, 2024
- Price per million input tokens: $2.00
- Price per million output tokens: $6.00
- Context window: 66K tokens
- Overall rank: 204 of 213, by the Artificial Analysis Intelligence Index
- Artificial Analysis Intelligence Index: 5.7

Benchmark results (7 of 190):

- AA Intelligence Index: 5.7 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- GPQA Diamond (Artificial Analysis run): 33.2% (source: Artificial Analysis, read October 21, 2026)
- Humanity's Last Exam (Artificial Analysis run): 4.0% (source: Artificial Analysis, read October 21, 2026)
- MMLU Pro (Artificial Analysis run): 53.7% (source: Artificial Analysis, read October 21, 2026)
- LiveCodeBench (Artificial Analysis run): 14.8% (source: Artificial Analysis, read October 21, 2026)
- DTBench: 55.1% (source: Epoch AI benchmarking hub, read October 21, 2026)
- Epoch Capabilities Index: 122.0 (source: Epoch AI benchmarking hub, read October 21, 2026)