← All models
Compare

Claude Opus 4.7 vs Kimi K3

Add, remove, or swap models to compare them side by side.

Claude Opus 4.7Kimi K3
AttributeClaude Opus 4.7Anthropic · 4 in the newsKimi K3Moonshot · 22 in the news
Scores
Intelligence (ECI)156157
Coding9499
Math8683
Reasoning & Knowledge7579
Agentic & Tools7386
Specifications
DeveloperAnthropicMoonshot
FamilyClaudeKimi
ReleasedApr 16, 2026Jul 16, 2026
Parameters2.8T
AvailabilityAPI accessOpen weights (non-commercial)
Context window1M1M
Price — $/M input$5.00$3.00
Price — $/M output$25.00$14.00
Inputstext, image, filetext, image
Outputstexttext
Benchmarks
AIME 2024/202598%97%
APEX34%39%
ARC-AGI94%95%
ARC-AGI-276%60%
FrontierMath44%
FrontierMath Tier 423%
GPQA Diamond90%93%
GSO (code optimization)44%
Humanity's Last Exam36%44%
SciCode55%59%
SimpleBench63%
SimpleQA Verified51%43%
SWE-bench Verified83%
Terminal-Bench80%
WebDev Arena15671682
WeirdML76%83%
τ²-bench89%

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.

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