Kimi K3 Matches Opus 4.8 in Coding, Tops Open-Weight Models
sergeykarayev · x · 2026-08-01
On a custom SWE-bench, Kimi K3 delivers quality on par with Opus 4.8 on a Rails codebase for a fraction of the cost.
It outperforms the next best open-weight model, GLM 5.2, by about 8 points, making it the leading open-weight model currently available.
Related event: Kimi K3 Matches Opus in Coding, Tops Open-Source(2 posts)→
More from coding & agent
- DeepSeek-V4-Flash-High Tops Price-Performance in Frontend Code Arena, Ranks #7 Overall — arena · 2026-08-01
- claude-pulse: Real-Time Status Bar Monitor for Claude Code Usage Limits — tom_doerr · 2026-08-01
- Waterloo's R2L Lab to Recruit PhDs, Focusing on Agents and Reasoning Research — hllo_wrld · 2026-08-01
- Codex Agent Autonomously Files Bug Reports with Support Chatbot — ___Patrice___ · 2026-08-01
- AgentIR: Deep Research Agents That Leverage Reasoning Context for Retrieval — hllo_wrld · 2026-08-01
- Getting Computer-Use Clicks Under 10ms: Cloud Sandbox Architecture Optimization — charles_irl · 2026-08-01