← All models
Compare

GLM-5.3 vs Kimi K3

Add, remove, or swap models to compare them side by side.

GLM-5.3Kimi K3
AttributeGLM-5.3Z.ai (Zhipu AI) · 3 in the newsKimi K3Moonshot · 35 in the news
Scores
Intelligence (ECI)157
Coding9599
Math81
Reasoning & Knowledge8578
Agentic & Tools84
Specifications
DeveloperZ.ai (Zhipu AI)Moonshot
FamilyKimi
ReleasedAug 14, 2026Jul 16, 2026
Parameters744B2.8T
AvailabilityAPI accessOpen weights (non-commercial)
Context window1M1M
Price — $/M input$1.40$2.80
Price — $/M output$4.40$14.00
Inputstexttext, image, video
Outputstexttext
Benchmarks
GPQA Diamond92%93%
Humanity's Last Exam42%47%
SciCode56%59%
AIME 2024/202597%
APEX39%
ARC-AGI95%
ARC-AGI-260%
SimpleQA Verified43%
WebDev Arena1682
WeirdML83%

Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.

Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.