← All models
Compare

DeepSeek-V4-Pro-0813 vs Kimi K2 Thinking

DeepSeek-V4-Pro-0813 (DeepSeek) and Kimi K2 Thinking (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeDeepSeek-V4-Pro-0813DeepSeek · 1 in the newsKimi K2 ThinkingMoonshot · 6 in the news
Scores
Intelligence (ECI)155146
Coding7839
Math8818
Reasoning & Knowledge6933
Agentic & Tools24
Specifications
DeveloperDeepSeekMoonshot
FamilyDeepSeekKimi
ReleasedAug 13, 2026Nov 6, 2025
Parameters1.6T1T
AvailabilityOpen weights (unrestricted)Open weights (restricted use)
Context window1M262K
Price — $/M input$0.58$0.60
Price — $/M output$1.74$2.50
Inputstexttext
Outputstexttext
Benchmarks
AIME 2024/202599%83%
ARC-AGI91%
ARC-AGI-261%
GPQA Diamond92%84%
Humanity's Last Exam41%24%
SciCode51%42%
SimpleQA Verified53%32%
WebDev Arena15821337
WeirdML66%43%
APEX4%
FrontierMath21%
FrontierMath Tier 40%
LiveCodeBench85%
METR task horizon54 min
MMLU-Pro85%
Terminal-Bench36%
τ²-bench93%

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.

Frequently asked questions

Is DeepSeek-V4-Pro-0813 better than Kimi K2 Thinking?

On Epoch AI's Capabilities Index, DeepSeek-V4-Pro-0813 scores higher (155) than Kimi K2 Thinking (146). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.

Which is cheaper, DeepSeek-V4-Pro-0813 or Kimi K2 Thinking?

DeepSeek-V4-Pro-0813 is cheaper on input tokens at $0.58 per million, versus $0.60 (representative OpenRouter pricing).

Which has a larger context window, DeepSeek-V4-Pro-0813 or Kimi K2 Thinking?

DeepSeek-V4-Pro-0813 supports up to 1M tokens, compared with 262K for the other.

Which is better for coding, DeepSeek-V4-Pro-0813 or Kimi K2 Thinking?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, DeepSeek-V4-Pro-0813 ranks higher — 78th vs 39th percentile among the models tracked on Model Beat.

Want a different match-up? Open the compare tool to add or swap models.

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