Best Moonshot AI model for coding
- Kimi K3 leads
- 62.3
- models ranked
- 4
- lead over #2
- +8.9
Coding index · read October 22
As of October 22, 2026, MoonshotAI Kimi K3 leads 4 scored Moonshot AI models with a coding index of 62.3, ahead of MoonshotAI Kimi K2.7 Code (53.4) and MoonshotAI Kimi K2.6 (52.1).
The full best LLM for coding ranking combines this benchmark with others.
Ordered by index, highest first. The dots show how many benchmarks stand behind each score.
| Rank | Model | Coding index | Evidence | Output $/Mtok |
|---|---|---|---|---|
| 1 | Kimi K3 Moonshot AI | 62.3 | $15.00 | |
| 2 | Kimi K2.7 Code Moonshot AI | 53.4 | $4.00 | |
| 3 | Kimi K2.6 Moonshot AI | 52.1 | $4.00 | |
| 4 | Kimi K2.5 Moonshot AI | 38.6 | $2.85 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Every Moonshot AI model with a Vibe Coding Index score, ordered as the ranking orders them: by how many benchmarks stand behind the score, then by the score.
- Aider polyglot leaderboard, fetched
- LiveBench, fetched , board updated October 14, 2026
- SWE-bench (swebench.com), fetched
- LMArena WebDev, fetched
Fewer than five models carry this number, or they all share it, so this list is kept for reference and out of search results until the data grows.