← All models
Compare

Gemini 3 Flash vs Kimi K3

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

AttributeGemini 3 FlashGoogle DeepMind · 2 in the newsKimi K3Moonshot · 22 in the news
Scores
Intelligence (ECI)151157
Coding4999
Math5383
Reasoning & Knowledge5779
Agentic & Tools6386
Specifications
DeveloperGoogle DeepMindMoonshot
FamilyGeminiKimi
ReleasedDec 17, 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 2024/202593%97%
APEX24%39%
ARC-AGI85%95%
ARC-AGI-234%60%
FrontierMath36%
FrontierMath Tier 44%
GPQA Diamond83%93%
GSO (code optimization)10%
SimpleBench61%
SimpleQA Verified67%43%
SWE-bench Verified75%
Terminal-Bench64%
WebDev Arena14541682
WeirdML62%83%
Humanity's Last Exam44%
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 Flash better than Kimi K3?

On Epoch AI's Capabilities Index, Kimi K3 scores higher (157) than Gemini 3 Flash (151). 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 Flash or Kimi K3?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 99th vs 49th 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.