All Topics

Technology

Art

Chinese open-weights model Kimi K2.6 beats Claude, GPT-5.5, and Gemini in AI coding contest

bazlightyear

29d ago· 8 min readenNews

90/100

Golden Brown

Bagelometer↗

Slow-proofed and worth the wait. Worth its weight in flour.

Score90TypenewsSentimentpositive

Summary

An AI coding contest (Day 12 - Word Gem Puzzle) saw Kimi K2.6, an open-weights model from Chinese startup Moonshot AI, defeat major Western models including Claude Opus 4.7, GPT-5.5, and Gemini. Kimi K2.6 scored 22 match points (7-1-0), with Xiaomi's MiMo V2-Pro taking second place. All Western frontier models finished below the top two, marking a significant shift in the AI competitive landscape.

Key quotes

· 3 pulled

Kimi K2.6, an open-weights model from Chinese startup Moonshot AI, won the challenge outright: 22 match points, 7-1-0.

Every model from the Western frontier labs landed below the top two.

The results were not what most people would have predicted.

Snippet from the RSS feed

By Rohana Rezel I’m running the ongoing AI Coding Contest where I pit major language models against each other in real-time programming tasks with objective scoring. Day 12 was the Word Gem Puzzle. Ten models entered. The results were not what most people

You might also wanna read

Datacurve's DeepSWE Benchmark Shows GPT-5.5 Leading AI Coding Models with 70% Pass Rate

A new benchmark called DeepSWE, released by startup Datacurve, reveals significant performance differences among AI coding models that were

share.transistor.fm·4d ago

Google's Gemini 3 AI Model Tops Benchmarks and Leaderboards, Outperforming Competitors

Google's Gemini 3 AI model has been released to widespread acclaim, topping benchmarks and leaderboards while outperforming competitors like

The Verge·6mo ago

Anthropic Releases Claude Opus 4.5 AI Model Amid Cybersecurity Concerns

Anthropic has released Claude Opus 4.5, positioning it as the world's best AI model for coding, agents, and computer use, claiming it surpas

The Verge·6mo ago

Google's Android Bench leaderboard ranks GPT 5.5 above Gemini for Android app development

Google launched the Android Bench benchmarking portal in March to help developers choose the best AI models for Android app development. The

bit.ly·1d ago

Alibaba's Qwen3.7-Max ranks 4th globally in coding benchmark, beating OpenAI and Google models

Alibaba's latest AI model, Qwen3.7-Max, has secured the fourth spot globally on the Code Arena coding leaderboard with a score of 1,541, out

scmp.com·4d ago

MiniCPM 4.0: Open-source 8B multimodal AI model outperforms GPT-4o and Gemini Pro on vision benchmarks

MiniCPM 4.0 is an ultra-efficient 8B open-source multimodal AI model designed for on-device use that outperforms larger models like GPT-4o a

Product Hunt·9mo ago