← All models
Compare

Claude Opus 5.5 vs Kimi K3

Claude Opus 5.5 (Anthropic) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeClaude Opus 5.5Anthropic · 3 in the newsKimi K3Moonshot · 44 in the news
Scores
Intelligence (ECI)158
Coding10097
Math80
Reasoning & Knowledge10072
Agentic & Tools72
Specifications
DeveloperAnthropicMoonshot
FamilyClaudeKimi
ReleasedSep 22, 2026Jul 16, 2026
Parameters2.8T
AvailabilityOpen weights (non-commercial)
Context window1M1M
Price — $/M input$4.00$2.10
Price — $/M output$20.00$10.95
Inputstext, image, filetext, image, video
Outputstexttext
Benchmarks
Humanity's Last Exam61%47%
SciCode67%60%
AIME 2024/202597%
APEX51%
ARC-AGI95%
ARC-AGI-260%
GPQA Diamond93%
SimpleBench61%
SimpleQA Verified51%
WebDev Arena1674
WeirdML83%

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

Which is cheaper, Claude Opus 5.5 or Kimi K3?

Kimi K3 is cheaper on input tokens at $2.10 per million, versus $4.00 (representative OpenRouter pricing).

Which has a larger context window, Claude Opus 5.5 or Kimi K3?

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

Which is better for coding, Claude Opus 5.5 or Kimi K3?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Claude Opus 5.5 ranks higher — 100th vs 97th 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.