The Model Index
Up to four models

Qwen2.5 vs Qwen2

On the index (GPT-4 = 100), Qwen2.5 scores 112 and Qwen2 106. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Qwen2.5Qwen2
Next to Qwen2.5
Presets
Qwen2.5
11296–128
WeightsOpen
ReleasedSep 2024
Price in / out$0.36 / $0.40
Context33K
Core tests taken2 of 9
Qwen2
10690–122
WeightsOpen
ReleasedJun 2024
Price in / out–
Context–
Core tests taken2 of 9

Qwen2.5 leads Qwen2 by 6 points, ahead on 2 of 2 shared core tests.

Test by testthird-party results

Qwen2.5Qwen2
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)CODINGWeirdMLWeirdML
Every result as a table
TestQwen2.5Qwen2
Reasoning & knowledge
GPQA Diamond (Epoch AI)49.1%40.8%
MMLU (HELM runs)83.4%82.4%
Maths
MATH (level 5)63.2%39.1%
Coding
WeirdML16.0%11.3%
Task length · METR21 sec18 sec

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

This page as a chartDownload PNG