SuperCLUE General (November 2025) - Hallucination Control: leaderboard

SuperCLUE general leaderboard, November 2025 edition (2025年11月): hallucination control (幻觉控制) score (总排行榜 sheet). SuperCLUE's periodic Chinese-language general evaluation uses a new question set each edition, so editions are separate boards. Score 0-100, higher is better.

Metric: Score. Source: www.superclueai.com. Saturation forecast: Estimated already saturated. 32 models tracked.

Top models

#ModelScoreOverall rank
1GPT-5.2 (High)92.55#115 (GPT-5.2)
2Gemini 2.5 Pro90.38#159
3Claude Opus 4.5 (Thinking)90.33#87 (Claude Opus 4.5)
4Doubao-Seed-1.6-251015 (Thinking)89.17#208 (Doubao-Seed-1.6-251015)
5GPT-5.1 (High)88.8#145 (GPT-5.1)
6Grok 488.39#189
7Gemini 3 Pro (Preview)87.78#71
8GLM-4.786.84#202
9DeepSeek V3.2 (Thinking)85.17#210 (DeepSeek V3.2)
10GLM-4.684.73#265
11O3 (High)83.81#132 (O3)
12DeepSeek V3.2 Speciale82.95#138
13DeepSeek V3.2 Exp (Thinking)82.3#241 (DeepSeek V3.2 Exp)
14Claude Sonnet 4.5 (Thinking)82.11#148 (Claude Sonnet 4.5)
15Hunyuan-T1-2025082281.82#306

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=superclue-general-november-2025-hallucination-control · How It Works · Data refreshed daily, snapshot 2026-11-05.