← All models
Compare

DeepSeek-V4-Pro vs Kimi K2.6

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

DeepSeek-V4-ProKimi K2.6
DeepSeek-V4-ProDeepSeek · 3 in the newsKimi K2.6Moonshot · 7 in the news
Scores
Intelligence (ECI)150151
Coding7679
Math9176
Reasoning & Knowledge6868
Agentic & Tools9287
Specifications
DeveloperDeepSeekMoonshot
FamilyDeepSeekKimi
ReleasedApr 24, 2026Apr 20, 2026
Parameters1.6T1T
AvailabilityOpen weights (unrestricted)Open weights (unrestricted)
Context window1M262K
Price — $/M input$0.43$0.55
Price — $/M output$0.87$3.20
Inputstexttext, image
Outputstexttext
Benchmarks
AIME 2024/202597%96%
GPQA Diamond90%91%
Humanity's Last Exam36%36%
SciCode50%54%
SimpleBench61%
SimpleQA Verified57%39%
SWE-bench Verified78%77%
WebDev Arena14641526
WeirdML49%56%
τ²-bench96%96%
FrontierMath39%
FrontierMath Tier 415%

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.