Kimi K3 — benchmark results
Provider: Moonshot. Access: API.
Unified ELO 1971 ± 35, rank #34 of 1756 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Chatbot Arena (Code) | 1679 | Elo | 100 |
| LLM Stats (APEX-Agents) | 37.6 | Score (%) | 100 |
| LLM Stats (AutomationBench) | 30.8 | Score (%) | 100 |
| LLM Stats (BabyVision) | 85.7 | Score (%) | 100 |
| LLM Stats (BrowseComp) | 91.2 | Score (%) | 100 |
| LLM Stats (DeepSearchQA) | 95 | Score (%) | 100 |
| LLM Stats (MCP Atlas) | 84.2 | Score (%) | 100 |
| LLM Stats (MathVision) | 97.8 | Score (%) | 100 |
| LLM Stats (Program Bench) | 77.8 | Score (%) | 100 |
| LLM Stats (Toolathlon) | 73.2 | Score (%) | 100 |
| Tau3 Banking | 33.4 | Success Rate (%) | 100 |
| AA SciCode | 58.68 | Accuracy (%) | 99.6 |
Interactive version: aibenchmarks.dev/model?slug=kimi-k3 · How the rankings work · Data refreshed daily, snapshot 2026-07-17.