The Model Index
Up to four models

Mistral Large vs Mixtral 8x22B

On the index (GPT-4 = 100), Mistral Large scores 100 and Mixtral 8x22B 99. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Mistral Large
Presets
Mistral Large
10084–117
WeightsClosed
ReleasedFeb 2024
Price in / out$2.0 / $6.0
Context128K
Core tests taken1 of 9
Mixtral 8x22B
9983–116
WeightsOpen
ReleasedApr 2024
Price in / out$2.0 / $6.0
Context66K
Core tests taken1 of 9

Mistral Large and Mixtral 8x22B are too close to call (1 point apart, within the uncertainty), ahead on 1 of 1 shared core tests, at a similar price.

Test by testthird-party results

Mistral LargeMixtral 8x22B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)MATHSMATH (level 5)MATH (level 5)AGENTSDTBenchDTBench
Every result as a table
TestMistral LargeMixtral 8x22B
Reasoning & knowledge
GPQA Diamond (Epoch AI)38.8%34.1%
MMLU (HELM runs)68.8%77.8%
Maths
MATH (level 5)24.5%24.2%
Agents
DTBench55.9%55.1%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG