Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
Tested on 6 benchmarks · BenchGecko score 24.3. Top scores: MMLU (70.4%), Dtbench (25.2%), MATH level 5 (24.2%).
Mistral Small 3.2 24B scores 23.8 (98% as good) at $0.09/1M input · 95% cheaper
Capture-the-flag cybersecurity challenges. Tests vulnerability analysis, reverse engineering, cryptography, and exploitation skills.
Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.
Massive Multitask Language Understanding. 57 subjects from STEM, humanities, and social sciences. The most widely-cited knowledge benchmark.
Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.
- Typetext
- Context66K tokens (~33 books)
- ReleasedApr 2024
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.010
Frequently Asked Questions
Key facts · as of 2026-10-05
- Mixtral 8x22B Instruct by Mistral AI. BenchGecko score 24.3, rank 268 of 312 scored models (normalized average of public benchmark scores).
- List price $2.00 input · $6.00 output per 1M tokens (as of 2026-10-05).
- Sold by 3 providers (as of 2026-10-05): Mistral $2.00 in / $6.00 out · Mistral $2.00 in / $6.00 out · Mistral $2.20 in / $6.60 out. Every provider
How to cite · data as of 2026-10-05
Mixtral 8x22B Instruct · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/mixtral-8x22b-instruct
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP