DataLearner logo

Claude Opus 4.8vsKimi K2.6

Across 9 shared benchmarks, Claude Opus 4.8 leads overall: Claude Opus 4.8 wins 9, Kimi K2.6 wins 0, with 0 ties and an average score difference of +9.13.

Anthropic
Claude Opus 4.8

Anthropic · 2026-05-28 · Reasoning model

Moonshot AI
Kimi K2.6

Moonshot AI · 2026-04-20 · Reasoning model

Claude Opus 4.89 wins(100%)(0%)0 winsKimi K2.6

Benchmark scores

Grouped by capability, sorted by largest gap within each. 9 shared benchmarks.

AI Agent - Tool Usage

Claude Opus 4.8 3/3
BenchmarkClaude Opus 4.8Kimi K2.6Diff
Terminal-Bench 2.178.9020 / 44Thinking High (With Tools)53.5643 / 44Thinking (No Tools)+25.34
MCP-Atlas82.206 / 38Deep Thinking (With Tools)69.4028 / 38Thinking (With Tools)+12.80
OSWorld-Verified83.404 / 26Extended (with tools)73.1015 / 26Thinking (With Tools)+10.30

Coding and Software Engineer

Claude Opus 4.8 2/2
BenchmarkClaude Opus 4.8Kimi K2.6Diff
SWE-Bench Pro - Public69.204 / 57Extended (with tools)58.6015 / 57Thinking (With Tools)+10.60
SWE-bench Verified88.605 / 114Extended (with tools)80.2014 / 114Thinking (With Tools)+8.40

General Knowledge

Claude Opus 4.8 2/2
BenchmarkClaude Opus 4.8Kimi K2.6Diff
LiveBench78.794 / 115Deep Thinking (No Tools)72.1728 / 115Thinking (No Tools)+6.62
HLE57.908 / 181Extended (with tools)5417 / 181Thinking (With Tools + Internet)+3.90

AI Agent - Information Search

Claude Opus 4.8 1/1
BenchmarkClaude Opus 4.8Kimi K2.6Diff
BrowseComp84.309 / 54Thinking High (With Tools + Internet)83.2014 / 54Thinking (With Tools + Internet)+1.10

General Evaluation

Claude Opus 4.8 1/1
BenchmarkClaude Opus 4.8Kimi K2.6Diff
GPQA Diamond93.6011 / 226Thinking High (No Tools)90.5035 / 226Thinking (No Tools)+3.10

Specs

FieldClaude Opus 4.8Kimi K2.6
PublisherAnthropicMoonshot AI
Release date2026-05-282026-04-20
Model typeReasoning modelReasoning model
ArchitectureDenseMoE
ParametersNot available1T
Context length1M256K
Max output125KNot available

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemClaude Opus 4.8Kimi K2.6
Text input$5 / 1M tokens$0.95 / 1M tokens
Text output$25 / 1M tokens$4 / 1M tokens
Cache read$0.5 / 1M tokens$0.16 / 1M tokens
Cache write$6.25 / 1M tokens$0.95 / 1M tokens

Summary

  • Claude Opus 4.8leads in:AI Agent - Tool Usage (3/3), Coding and Software Engineer (2/2), General Knowledge (2/2), AI Agent - Information Search (1/1), General Evaluation (1/1)

On average across the 9 shared benchmarks, Claude Opus 4.8 scores 9.13 higher.

Largest single-benchmark gap: Terminal-Bench 2.1 — Claude Opus 4.8 78.90 vs Kimi K2.6 53.56 (+25.34).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.