The Model Index
Up to four models

GLM-5.3 vs Qwen3.7 Flash

On the index (GPT-4 = 100), GLM-5.3 scores 168 and Qwen3.7 Flash 138. 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 GLM-5.3
Presets
GLM-5.3
168152–184
WeightsOpen
ReleasedAug 2026
Price in / out$0.070 / $1.4
Context1.05M
Core tests taken5 of 9
Qwen3.7 Flash
138121–155
WeightsClosed
ReleasedJul 2026
Price in / out$0.030 / $0.13
Context1M
Core tests taken2 of 9

GLM-5.3 leads Qwen3.7 Flash by 30 points, ahead on 2 of 2 shared core tests, at 7.3× the price.

Test by testthird-party results

GLM-5.3Qwen3.7 Flash
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)AGENTSMystery game puzzlesMystery game puzzles
Every result as a table
TestGLM-5.3Qwen3.7 Flash
Reasoning & knowledge
GPQA Diamond (Epoch AI)90.9%82.3%
Maths
FrontierMath (tiers 1-3)68.8%19.3%
AIME-style maths (OTIS mock)91.1%86.7%
Agents
Mystery game puzzles33.0%15.0%

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

This page as a chartDownload PNG