The Model Index
Up to four models

Mixtral 8x22B vs Claude 3 Sonnet

On the index (GPT-4 = 100), Mixtral 8x22B scores 99 and Claude 3 Sonnet 98. 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 Mixtral 8x22B
Presets
Mixtral 8x22B
9983–116
WeightsOpen
ReleasedApr 2024
Price in / out$2.0 / $6.0
Context66K
Core tests taken1 of 9
Claude 3 Sonnet
9881–115
WeightsClosed
ReleasedMar 2024
Price in / out–
Context–
Core tests taken1 of 9

Mixtral 8x22B and Claude 3 Sonnet are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

Mixtral 8x22BClaude 3 Sonnet
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)CODINGWeirdMLWeirdMLAGENTSDTBenchDTBench
Every result as a table
TestMixtral 8x22BClaude 3 Sonnet
Reasoning & knowledge
GPQA Diamond (Epoch AI)34.1%40.6%
MMLU (HELM runs)77.8%75.9%
Maths
MATH (level 5)24.2%18.2%
Coding
WeirdML3.2%10.2%
Agents
DTBench55.1%53.6%

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

This page as a chartDownload PNG