The Model Index
Up to four models

Qwen3-Max vs Qwen2.5-Max

On the index (GPT-4 = 100), Qwen3-Max scores 135 and Qwen2.5-Max 118. 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 Qwen3-Max
Presets
Qwen3-Max
135119–151
WeightsClosed
ReleasedSep 2025
Price in / out–
Context–
Core tests taken2 of 9
Qwen2.5-Max
118102–134
WeightsClosed
ReleasedJan 2025
Price in / out–
Context–
Core tests taken1 of 9

Qwen3-Max leads Qwen2.5-Max by 17 points, ahead on 1 of 1 shared core tests.

Test by testthird-party results

Qwen3-MaxQwen2.5-Max
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)Fiction.LiveBenchFiction.LiveBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)
Every result as a table
TestQwen3-MaxQwen2.5-Max
Reasoning & knowledge
GPQA Diamond (Epoch AI)72.6%56.1%
Fiction.LiveBench66.7%66.7%
Maths
AIME-style maths (OTIS mock)73.3%16.1%
MATH (level 5)97.1%67.2%

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

This page as a chartDownload PNG