HMMT Nov 2025 Leaderboard 2026 — Results Across 4 Real AI Models

HMMT Nov 2025 leaderboard

HMMT Nov 2025

4 models tested · Updated 2026-06-13 · Verified sources only

      Claude Opus 4.8 leads at 96.5%
    

Anthropic · Blog/Z.ai · 2026-06-13

Ties GPT-5.5.

96.5%

Alibaba · Blog/Z.ai · 2026-06-13

Between GLM-5.2 (94.4) and Opus 4.8 (96.5).

95.0%

Z.ai · Blog/Z.ai · 2026-06-13

Matches DeepSeek V4 Pro (94.4).

94.4%

MiniMax · Blog/Z.ai · 2026-06-13

Well below frontier (GLM-5.2 94.4).

84.4%