← All models
Compare

DeepSeek-V4-Pro-0813 vs GLM-5

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

DeepSeek-V4-Pro-0813GLM-5
AttributeDeepSeek-V4-Pro-0813DeepSeek · 1 in the newsGLM-5Z.ai (Zhipu AI) · 25 in the news
Scores
Intelligence (ECI)155146
Coding7639
Math8820
Reasoning & Knowledge6929
Agentic & Tools6756
Specifications
DeveloperDeepSeekZ.ai (Zhipu AI)
FamilyDeepSeek
ReleasedAug 13, 2026Feb 12, 2026
Parameters1.6T744B
AvailabilityOpen weights (unrestricted)Open weights (unrestricted)
Context window1M205K
Price — $/M input$0.58$0.70
Price — $/M output$1.74$2.24
Inputstexttext
Outputstexttext
Benchmarks
AIME 2024/202599%80%
APEX47%17%
ARC-AGI91%45%
ARC-AGI-261%5%
GPQA Diamond92%88%
Humanity's Last Exam41%29%
SciCode51%46%
SimpleQA Verified53%
WebDev Arena15811436
WeirdML66%48%
FrontierMath16%
FrontierMath Tier 42%
SimpleBench53%
SWE-bench Verified72%
Terminal-Bench52%
τ²-bench98%

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.