← All models
Compare

DeepSeek-V4-Pro vs GLM-5.2

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

DeepSeek-V4-ProGLM-5.2
DeepSeek-V4-ProDeepSeek · 3 in the newsGLM-5.2Z.ai (Zhipu AI) · 7 in the news
Scores
Intelligence (ECI)150153
Coding7688
Math9141
Reasoning & Knowledge6877
Agentic & Tools92100
Specifications
DeveloperDeepSeekZ.ai (Zhipu AI)
FamilyDeepSeek
ReleasedApr 24, 2026Jun 16, 2026
Parameters1.6T
AvailabilityOpen weights (unrestricted)Open weights (unrestricted)
Context window1M1M
Price — $/M input$0.43$0.93
Price — $/M output$0.87$3.00
Inputstexttext
Outputstexttext
Benchmarks
AIME 2024/202597%86%
GPQA Diamond90%92%
Humanity's Last Exam36%40%
SciCode50%51%
SimpleBench61%
SimpleQA Verified57%38%
SWE-bench Verified78%79%
WebDev Arena14641593
WeirdML49%70%
τ²-bench96%99%

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.