← All models
Compare

GPT-5.4 Mini vs Kimi K3

GPT-5.4 Mini (OpenAI) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeGPT-5.4 MiniOpenAIKimi K3Moonshot · 43 in the news
Scores
Intelligence (ECI)149158
Coding5697
Math3480
Reasoning & Knowledge3573
Agentic & Tools4080
Specifications
DeveloperOpenAIMoonshot
FamilyGPTKimi
ReleasedMar 17, 2026Jul 16, 2026
Parameters2.8T
AvailabilityAPI accessOpen weights (non-commercial)
Context window400K1M
Price — $/M input$0.75$2.10
Price — $/M output$4.50$10.95
Inputsfile, image, texttext, image, video
Outputstexttext
Benchmarks
AIME 2024/202589%97%
APEX25%39%
ARC-AGI64%95%
ARC-AGI-219%60%
FrontierMath28%
FrontierMath Tier 42%
GPQA Diamond87%93%
Humanity's Last Exam28%47%
SciCode52%60%
SimpleQA Verified29%51%
WebDev Arena13971674
WeirdML60%83%
τ²-bench83%
SimpleBench61%

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 GPT-5.4 Mini better than Kimi K3?

On Epoch AI's Capabilities Index, Kimi K3 scores higher (158) than GPT-5.4 Mini (149). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.

Which is cheaper, GPT-5.4 Mini or Kimi K3?

GPT-5.4 Mini is cheaper on input tokens at $0.75 per million, versus $2.10 (representative OpenRouter pricing).

Which has a larger context window, GPT-5.4 Mini or Kimi K3?

Kimi K3 supports up to 1M tokens, compared with 400K for the other.

Which is better for coding, GPT-5.4 Mini or Kimi K3?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 97th vs 56th 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.