The Model Index
Up to four models

Qwen3.6-Max-Preview vs Qwen3-Max

On the index (GPT-4 = 100), Qwen3.6-Max-Preview scores 155 and Qwen3-Max 135. 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 Qwen3.6-Max-Preview
Presets
Qwen3.6-Max-Preview
155138–172
WeightsClosed
ReleasedApr 2026
Price in / out–
Context–
Core tests taken2 of 9
Qwen3-Max
135119–151
WeightsClosed
ReleasedSep 2025
Price in / out–
Context–
Core tests taken2 of 9

Qwen3.6-Max-Preview leads Qwen3-Max by 20 points, ahead on 1 of 1 shared core tests.

Test by testthird-party results

Qwen3.6-Max-PreviewQwen3-Max
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)SimpleQA VerifiedSimpleQA VerifiedMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)AGENTSDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKCorpFin v2CorpFin v2
Every result as a table
TestQwen3.6-Max-PreviewQwen3-Max
Reasoning & knowledge
GPQA Diamond (Epoch AI)87.4%72.6%
SimpleQA Verified52.0%48.8%
Maths
AIME-style maths (OTIS mock)91.1%73.3%
Agents
DTBench87.2%82.1%
LMCA42.5%28.3%
Mystery game puzzles19.0%5.0%
Professional work
CorpFin v266.5%68.0%

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

This page as a chartDownload PNG