The Model for That

Checked

← All models

Z.ai · released Aug 14, 2026

GLM-5.3

GLM-5.3 is Z.ai's open-weight model and handles chat decently at a low price.

Open weights3 months oldThinks before answering
Reasoning41Coding50Writing60Vision–Agents43Value69
Input price
$1.2 / M
Output price
$4.18 / M
Context
1M tokens
Longest reply
131K
Reads
text
Knows up to
–

Where it shines

  • Its weights are open to download.
  • It scores 1496 on hard English prompts.
  • It costs about $1.20 in, $4.18 out.

Where it struggles

  • Its research job score of 40 is weak.

Where you can use it

  • Hugging FaceDownloadWeights are public.
  • Z.ai APIAPIAbout $1.20 in / $4.18 out per million tokens.
  • OpenRouterAPIListed as z-ai/glm-5.3

How it scores on each job

Scores run 0 to 100 and blend every measure we have for that job. The number after the dot is its rank among the 33 models in the lineup.

The evidence

MeasureScoreRank in lineupSource
Epoch Capabilities Index156#18Epoch AI
LMArena text1474#12LMArena
LMArena hard prompts1490#13LMArena
LMArena instruction following1480#11LMArena
LMArena multi-turn1470#14LMArena
LMArena creative writing1459#12LMArena
LMArena writing & language1469#13LMArena
LMArena coding1498#14LMArena
LMArena math1498#11LMArena
LMArena business & finance1459#16LMArena
LMArena legal & government1473#16LMArena
LMArena medicine1482#13LMArena
WebDev Arena1623#15LMArena
Agent Arena#23#13LMArena
GPQA Diamond91%#17Epoch AI
FrontierMath69%#18Epoch AI
SimpleQA Verified41%#20Epoch AI

Compare it with these