Kimi K2.6 outperforms Claude, GPT-5.5, and Gemini in coding benchmark

Moonshot AI's Kimi K2.6, an open-weights Chinese model, has topped a programming challenge against major Western frontier models including Claude, GPT-5.5, and Gemini. The result marks a notable benchmark milestone for Chinese open-weights models competing directly with closed frontier labs.

Sources

X mentions

15k ▲

First seen

4Dago

Velocity

+4%/6h

CONTRIBUTING SOURCES

4 ARTICLES

X DISCOURSE

15k TOTAL · TOP 3

@Kimi_Moonshot3H · 49.4K

Meet Kimi K2.6 Agent Swarm 👋 Highlights： 🔹 Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from 100 / 1,500 in K2.5). 🔹 Outputs are real files, not chat - one run delivers 100+ files, 100,000-word literature reviews, or 20,000-row datasets. 🔹Heterogeneous skills - search, analysis, coding, long-form writing, and visual generation all running in parallel 🔗Try it at: https://t.co/2Tu8McUaUa

@Kimi_Moonshot19H · 49.0K

@Kimi_Moonshot2D · 59.3K

📢 Kimi K2.6 API is live • Input Price (Cache Hit): $0.16 / M tokens • Input Price (Cache Miss): $0.95 / M tokens • Output: $4.00 / M tokens Kimi K2.6 is our latest + most intelligent model - stronger long-horizon coding, better instruction following & self-correction. Native multimodal (text/image/video), thinking + non-thinking, 256K context. Supports tool calls, JSON / Partial mode, and web search. Try it → https://t.co/XCrgjXAqMw