Kimi 2.5 is as good as Sonnet 4.5, ChatGPT O3 and Grok 4
Open source models are almost as good as frontier LLMs
Epoch AI @EpochAIResearch · February 4, 2026 ↗Kimi K2.5 set a new record among open-weight models on the Epoch Capabilities Index (ECI), which combines multiple benchmarks onto a single scale. Its score of 147 is about on par with o3, Grok 4, and Sonnet 4.5. It still lags the overall frontier.
It’s crazy how good good open source LLMs have gotten.
Kimi K2.5 set a new record among open-weight models on the Epoch Capabilities Index (ECI), which combines multiple benchmarks onto a single scale. Its score of 147 is about on par with o3, Grok 4, and Sonnet 4.5. It still lags the overall frontier.
