Kimi K3 — benchmark results

Provider: Moonshot. Released 2026-07-17. Access: API.

Unified ELO 1985 ± 20, rank #28 of 1776 rated models, from 125 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Chatbot Arena (Code)1678Elo100
Design Arena (3D)1438Elo100
Design Arena (UI Components)1448Elo100
Design Arena (Website)1382Elo100
LLM Stats (APEX-Agents)37.6Score (%)100
LLM Stats (AutomationBench)30.8Score (%)100
LLM Stats (BabyVision)85.7Score (%)100
LLM Stats (BrowseComp)91.2Score (%)100
LLM Stats (DeepSearchQA)95Score (%)100
LLM Stats (MathVision)97.8Score (%)100
LLM Stats (Program Bench)77.8Score (%)100
LLM Stats (ZEROBench)41Score (%)100

Interactive version: theaggregate.ai/model?slug=kimi-k3 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.