← All models
Compare

Gemini 3 Pro vs Kimi K3

Gemini 3 Pro (Google DeepMind) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeGemini 3 ProGoogle DeepMind · 1 in the newsKimi K3Moonshot · 22 in the news
Scores
Intelligence (ECI)153157
Coding5199
Math6883
Reasoning & Knowledge7479
Agentic & Tools5786
Specifications
DeveloperGoogle DeepMindMoonshot
FamilyGeminiKimi
ReleasedNov 18, 2025Jul 16, 2026
Parameters2.8T
AvailabilityAPI accessOpen weights (non-commercial)
Context window1M
Price — $/M input$3.00
Price — $/M output$14.00
Inputstext, image
Outputstext
Benchmarks
AIME 2024/202591%97%
APEX32%39%
ARC-AGI75%95%
ARC-AGI-231%60%
FrontierMath38%
FrontierMath Tier 419%
GDPval (win/tie rate)54%
GPQA Diamond93%93%
GSO (code optimization)19%
Humanity's Last Exam38%44%
METR task horizon3.7 h
SimpleBench76%
SimpleQA Verified73%43%
SWE-bench Verified73%
Terminal-Bench69%
WebDev Arena14711682
WeirdML70%83%
SciCode59%

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 Gemini 3 Pro better than Kimi K3?

On Epoch AI's Capabilities Index, Kimi K3 scores higher (157) than Gemini 3 Pro (153). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.

Which is better for coding, Gemini 3 Pro or Kimi K3?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 99th vs 51th 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.