Claude Sonnet 4vsKimi K2.6

Claude Sonnet 4
Kimi K2.6
Specifications
Parameters
1T
Context window
256k
Benchmarks
Nonsense detection
BullshitBench v2
30%
65%Best
Coding
SWE-Bench Verified
72.7%
80.2%Best
Agentic coding
CursorBench v3.1
47.6%
Next.js coding
Next.js Evals
67%
Competitive coding
LiveCodeBench
89.6%
Science
GPQA Diamond
75.4%
90.5%Best
Community preference (code)
Arena Elo (Code)
1513
Overview
CompanyAnthropicMoonshot AI
Release dateMay 22 2025Apr 21 2026
AccessProprietaryOpen Weight

Which is better: Claude Sonnet 4 or Kimi K2.6?

Kimi K2.6 leads Claude Sonnet 4 on 3 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, GPQA Diamond). Claude Sonnet 4 shipped 334 days before Kimi K2.6, so benchmark comparisons should account for the intervening progress.

Claude Sonnet 4 is proprietary, while Kimi K2.6 is open weight.

On BullshitBench v2, Kimi K2.6 leads at 65% vs Claude Sonnet 4 at 30%. On SWE-Bench Verified, Kimi K2.6 leads at 80.2% vs Claude Sonnet 4 at 72.7%. On GPQA Diamond, Kimi K2.6 leads at 90.5% vs Claude Sonnet 4 at 75.4%.

Frequently asked questions

Claude Sonnet 4 was released by Anthropic on May 22 2025.

Kimi K2.6 was released by Moonshot AI on Apr 21 2026.

Kimi K2.6 leads on SWE-Bench Verified — Claude Sonnet 4 72.7% vs Kimi K2.6 80.2%.

Kimi K2.6 leads on GPQA Diamond — Claude Sonnet 4 75.4% vs Kimi K2.6 90.5%.

Claude Sonnet 4 is a proprietary model released by Anthropic. Kimi K2.6 is an open weight model released by Moonshot AI.

Other comparisons