← All models
Compare

DeepSeek-V4-Pro-0813 vs GLM-5.1

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

DeepSeek-V4-Pro-0813GLM-5.1
AttributeDeepSeek-V4-Pro-0813DeepSeek · 1 in the newsGLM-5.1Z.ai (Zhipu AI) · 7 in the news
Scores
Intelligence (ECI)155150
Coding7647
Math8857
Reasoning & Knowledge6946
Agentic & Tools6777
Specifications
DeveloperDeepSeekZ.ai (Zhipu AI)
FamilyDeepSeek
ReleasedAug 13, 2026Apr 7, 2026
Parameters1.6T754B
AvailabilityOpen weights (unrestricted)Open weights (unrestricted)
Context window1M205K
Price — $/M input$0.58$1.19
Price — $/M output$1.74$3.74
Inputstexttext
Outputstexttext
Benchmarks
AIME 2024/202599%93%
APEX47%41%
ARC-AGI91%
ARC-AGI-261%
GPQA Diamond92%90%
Humanity's Last Exam41%30%
SciCode51%45%
SimpleQA Verified53%34%
WebDev Arena15811508
WeirdML66%57%
FrontierMath33%
FrontierMath Tier 413%
SimpleBench55%
SWE-bench Verified74%
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.