OnlySOTA

Claude Sonnet 5.5 vs Kimi K3

Both are SOTA right now. Each row below is one board’s call on the two, and the marked figure is the one that board places higher. No row is added to another, so there is no overall winner: the boards measure different things, and where they split, that is the finding.

Board Claude Sonnet 5.5 Kimi K3
Artificial Analysis LLM Leaderboard Artificial Analysis Intelligence Index 56.0 No. 2 of 372 43.6 No. 18 of 372
Arena — Agent Overall 0.125 No. 3 of 49 0.042 No. 14 of 49
Artificial Analysis Coding Agents Artificial Analysis Coding Agent Index 0.684 No. 1 of 22 0.519 No. 15 of 22
HarnessTax — SWE-bench Lite SWE-bench Lite — 76.7% No. 4 of 7
HarnessTax — Terminal-Bench 2.0 Terminal-Bench 2.0 — 73.3% No. 4 of 7
Arena — Code Overall 1786 No. 3 of 109 1658 No. 13 of 109
Arena — Text Overall (style control) 1471 No. 45 of 306 1488 No. 16 of 306
Arena — Vision Overall (style control) 1268 No. 35 of 128 —

Each rank is the board’s own: the rank it publishes, or its place in its own order where it publishes none. The bar is how much of that board the model is ahead of. Scores from different boards cannot be compared.

At a glance

Developer Anthropic Kimi
Weights closed open
Released —2026-07-16
Price Blended Price, USD per 1M tokens (3:1 input:output) $4.00$6.00
Value: where it sits on the kill line SOTA SOTA

Claude Sonnet 5.5 →Kimi K3 → How the kill line is drawn →

Claude Sonnet 5.5 against the other SOTA models

Kimi K3 against the other SOTA models