0

Claude Opus 4.8 vs Kimi K2.5

Head to head on 28 shared benchmarks, with price, context window, and release dates.

Benchmark scores

51

evals · sort by any column, ⤢ to expand fullscreen

Model
Claude Opus 4.8

Anthropic

66.7%67.0%1835elo80.853.9%47.2%92.0%48.7%62.2%80.1%79.3%78.3%67.4%81.4%84.3%89.7%91.8%53.2%85.8%69.9%83.4%54.8%53.5%75.6%58.3%60.9%82.7%94.4%-15.5%80.4%14.5%1281elo40.0%13.4%22.5%1890elo56.9%---10.4%-69.0%---69.2%82.7%-70.9%63.4%
Kimi K2.5

Moonshot AI

68.3%39.0%1576elo74.935.8%27.9%78.9%13.2%43.7%72.5%77.9%61.4%57.4%77.7%84.9%76.0%62.0%39.3%76.4%66.5%63.3%49.9%39.6%74.2%18.9%26.3%17.5%81.3%96.1---------95.478.5%10421-87.1-7367.3%70.8%--69.4-56.8%
2 / 2 models
AttributeClaude Opus 4.8

Anthropic

Kimi K2.5

Moonshot AI

DescriptionClaude Opus 4.8 (Adaptive Reasoning, Max Effort) is an AI model from Anthropic.Kimi K2.5 is an AI model from Kimi.
FamilyClaudeKimi
Params--
Open weights-closed
License-Modified MIT
Released28 May 202627 Jan 2026
Context1,000,000262,144
Input $/1M$5.00$0.60
Output $/1M$25.00$3.00
Cache read $/1M$0.500$0.100
Cache write $/1M$6.250-
Speed0 tok/s0 tok/s
Latency0.00 s0.00 s
Modalitiestext, image, filetext, image
Providers--
PublisherAnthropicMoonshot AI
Reported scores

FAQ

Is Claude Opus 4.8 or Kimi K2.5 better?
Across the 28 benchmarks both models report on Sophon, Claude Opus 4.8 leads on 26 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
How do Claude Opus 4.8 and Kimi K2.5 compare on GPQA Diamond?
Claude Opus 4.8 scores 92.0% and Kimi K2.5 scores 78.9% on GPQA Diamond.
Which is cheaper, Claude Opus 4.8 or Kimi K2.5?
Kimi K2.5 is cheaper at $3.00 per million output tokens against $25.00 for Claude Opus 4.8 - about 8.3x.
When were Claude Opus 4.8 and Kimi K2.5 released?
Claude Opus 4.8 was released 28 May 2026 by Anthropic. Kimi K2.5 was released 27 Jan 2026 by Moonshot AI.

Comparing something else? Build your own side-by-side.