Mixtral 8x22B: benchmark scores, price and ranking

Mixtral 8x22B from Mistral AI is a recent or sparsely tested model with 1 benchmark result on record; it has not been measured on enough benchmarks shared with other models to receive an aggregate rank. This page lists every score we have, based on 1 benchmark results captured up to 2026-10-14.

Organisation: Mistral AI
Type: Open-weight / local model
Open weights: Yes
Released: 2024-04-17 (source: epoch)
Aggregate rank: Not ranked yet (too few shared benchmarks)

Across the 1 benchmark where at least ten models are scored, Mixtral 8x22B is in the top 10% on 0 and in the top half on 0.

Mixtral 8x22B benchmark results

Mixtral 8x22B benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
Epoch ECI	122	#121 of 204	Epoch AI Benchmarking Hub	2026-10-14

About Mixtral 8x22B

Mixtral 8x22B is an open-weight model that can run on your own hardware from Mistral AI. It was released on 2024-04-17, according to Epoch AI. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where Mixtral 8x22B stands

Mixtral 8x22B has 1 result so far and shares too few benchmarks with other models to get an aggregate rank. The rank will appear on its own once more scores are published.

Mixtral 8x22B, benchmark by benchmark

Mixtral 8x22B lands below the middle on Epoch ECI: 122, #121 of 204, with 59% of the field scoring higher. Qwen 3.8 Max leads at 156; the closest result above is gemma-2-27b at 122. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Mixtral 8x22B is 5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.

Release history

The Mistral AI model released before it was mistral-small-2402 on 2024-02-26, which scores 46.7. The next one was Mixtral-8x22B-Instruct-v0.1 on 2024-04-17, at 43.5.

Reading these numbers

The 1 score on this page comes from 1 source: Epoch AI Benchmarking Hub (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.