LiveCodeBench v6 Leaderboard 2026 — Results Across 2 Real AI Models

LiveCodeBench v6 leaderboard

LiveCodeBench v6

2 models tested · Updated 2026-04-20 · Verified sources only

      Kimi K2.6 leads at 89.6%
    

Moonshot AI · HuggingFace/moonshotai · 2026-04-20

Near frontier-level coding. Trails Gemini 3.1 Pro (91.7) by 2 points.

89.6%

OpenAI · arxiv/2604.08644 · 2026-04-14

From EXAONE 4.5 technical report. Trails EXAONE 4.5 33B (81.4).

78.1%