The Model Index
Up to four models

Qwen3.7-Max vs Qwen3.6-Max-Preview

On the index (GPT-4 = 100), Qwen3.7-Max scores 160 and Qwen3.6-Max-Preview 155. 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 Qwen3.7-Max
Presets
Qwen3.7-Max
160144–177
WeightsClosed
ReleasedMay 2026
Price in / out$1.48 / $4.42
Context1M
Core tests taken4 of 9
Qwen3.6-Max-Preview
155138–172
WeightsClosed
ReleasedApr 2026
Price in / out–
Context–
Core tests taken2 of 9

Qwen3.7-Max and Qwen3.6-Max-Preview are too close to call (5 points apart, within the uncertainty), ahead on 2 of 2 shared core tests.

Test by testthird-party results

Qwen3.7-MaxQwen3.6-Max-Preview
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)SimpleBenchSimpleBenchSimpleQA VerifiedSimpleQA VerifiedMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)CODINGSWE-bench VerifiedSWE-bench VerifiedSWE-benchSWE-benchAGENTSDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKCorpFin v2CorpFin v2
Every result as a table
TestQwen3.7-MaxQwen3.6-Max-Preview
Reasoning & knowledge
GPQA Diamond (Epoch AI)90.9%87.4%
SimpleBench70.4%63.0%
SimpleQA Verified55.8%52.0%
Maths
AIME-style maths (OTIS mock)95.6%91.1%
Coding
SWE-bench Verified77.3%76.6%
SWE-bench68.8%72.8%
Agents
DTBench92.3%87.2%
LMCA44.0%42.5%
Mystery game puzzles32.0%19.0%
Professional work
CorpFin v263.7%66.5%

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

This page as a chartDownload PNG