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: Moonshot's Kimi K3 Sets New Open-Source ECI Record(2 posts)→
More from Models
- Moonshot Kimi K3 distillation claim faces timeline pushback over Fable 5 — kristoph · 2026-07-23
- Thread claims GPT-5.6 Sol helped solve 6 open Erdős problems in 5 days — jxnlco · 2026-07-23
- Google says Gemini now handles 22B API tokens a minute and has 950M app users — rseroter · 2026-07-23
- Enterprise Agent Benchmarks: Gemini 3.1/3.5 Strong But Trail Fable and Sol — echen · 2026-07-23
- Benchmark results say Kimi K3 is near the frontier on chat, but still behind on agents and science — echen · 2026-07-23
- Claude 3 Opus appears to be acting strangely, with users joking it feels like a base model — repligate · 2026-07-23