Kimi K3 Sets New Open-Weights Record on Epoch Capabilities Index, Approaching GPT-5
rohanpaul_ai · x · 2026-07-23
Moonshot's Kimi K3 achieved a score of 156 on the Epoch Capabilities Index (ECI), setting a new record for open-weights models.
The ECI aggregates dozens of separate benchmarks into a single score, preventing single-test overfitting from distorting the overall ranking. On this index, Kimi K3 ranks between Anthropic's Opus 4.6 and OpenAI's GPT 5.4, slightly ahead of GPT 5.6 Luna.
Related event: Kimi K3 Sets New Open-Source ECI Record but Still Lags Behind(3 posts)→
More from Models
- DeepSeek cut KV cache per token from 389KB to 890B in two years as open-closed gap debate rages — teortaxesTex · 2026-10-27
- Unverified: fable 5.5 speculated at 4-5T parameters to outscale 1-3T Opus — haider1 · 2026-10-27
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27
- Custom VQA benchmark under 48GB VRAM: Qwen3.8-Flash-Next leads, Qwen3.8-27B regressed — EmilPi · 2026-10-27