Kimi K3 Tops WebDev Leaderboard
ylecun · x · 2026-07-19
Shares report that Kimi K3 ranks No. 1 on the WebDev human preference leaderboard, outperforming closed-source models like Claude Fable 5 on terminal/long-context coding tasks closer to real-world dev.
The post emphasizes these results come at roughly one-third the cost, with full weights dropping for free within 10 days, directly challenging the narrative of expensive closed-source models.
More from Models
- FrontierML benchmark shows open models still far behind closed ones on end-to-end ML work — scaling01 · 2026-10-27
- Mirendil debuts Fern, its first from-scratch model with up to 10M-token context — shayan_ · 2026-10-27
- Week 3 of "Fable 5.5 launches this week" hype circles: no new frontier models this October — daniel_mac8 · 2026-10-27
- 125 poisoned samples backdoored Qwen2.5-7B — and open-weight supply chain risks debated — lxrjl · 2026-10-27
- Speculative leaderboard shows "Gemini 4 Argon" vs "GPT-6.1 Sol"; observer calls MiniMax parity suspicious — teortaxesTex · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27