SuperCLUE General (November 2025) - Hallucination Control: leaderboard

Metric: Score. Source: www.superclueai.com. 32 models tracked.

Top models

#ModelScore
1GPT-5.2 (High)92.55
2Gemini 2.5 Pro90.38
3Claude Opus 4.5 (Thinking)90.33
4GPT-5.1 (High)88.8
5Grok 488.39
6Gemini 3 Pro (Preview)87.78
7GLM-4.786.84
8DeepSeek V3.2 (Thinking)85.17
9GLM-4.684.73
10O3 (High)83.81
11DeepSeek V3.2 Speciale82.95
12DeepSeek V3.2 Exp (Thinking)82.3
13Claude Sonnet 4.5 (Thinking)82.11
14Hunyuan-T1-2025082281.82
15Qwen 3 Max78.39

Interactive version: theaggregate.ai/benchmark?slug=superclue-general-november-2025-hallucination-control · How It Works · Data refreshed daily, snapshot 2026-09-19.