← All models
Compare

Claude Opus 4.8 vs Kimi K2.5

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

Claude Opus 4.8Kimi K2.5
Claude Opus 4.8Anthropic · 1 in the newsKimi K2.5Moonshot · 10 in the news
Scores
Intelligence (ECI)157148
Coding9646
Math9153
Reasoning & Knowledge7637
Agentic & Tools9439
Specifications
DeveloperAnthropicMoonshot
FamilyClaudeKimi
ReleasedMay 28, 2026Feb 2, 2026
Parameters1T
AvailabilityAPI accessOpen weights (unrestricted)
Context window1M262K
Price — $/M input$5.00$0.38
Price — $/M output$25.00$2.02
Inputstext, image, filetext, image
Outputstexttext
Benchmarks
AIME 2024/202598%92%
APEX43%14%
ARC-AGI93%65%
ARC-AGI-272%12%
FrontierMath47%28%
FrontierMath Tier 431%4%
GPQA Diamond91%88%
SimpleBench65%47%
SimpleQA Verified40%34%
WebDev Arena15521431
WeirdML83%46%
Humanity's Last Exam24%
SWE-bench Verified74%
Terminal-Bench43%

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.