Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works
Moonshot models by SI-IQ
6 models from Moonshot have independent benchmark results in our data. The best ranked is Kimi K3 with an SI-IQ of 127.
Models
| 1 | Kimi K3open Moonshot | 127124–130 | 8 |
| 2 | Kimi K2.6open Moonshot | 121118–124 | 9 |
| 3 | Kimi K2.5open Moonshot | 119112–125 | 5 |
| 4 | Kimi K2.7 Codeopen Moonshot | 118115–122 | 7 |
| 5 | Kimi K2 Thinkingopen Moonshot | 11299–126 | 2 too little data |
| 6 | Kimi K2 (Sep 2025)open Moonshot | 10592–118 | 2 too little data |
Data sources: Aider polyglot leaderboard data (Apache-2.0); Arena leaderboard dataset on Hugging Face (CC BY 4.0); Berkeley Function Calling Leaderboard, Gorilla project (Apache-2.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..