SuperCLUE General (July 2026) - Hallucination Control: leaderboard
SuperCLUE general leaderboard, July 2026 edition (2026年7月): hallucination control (幻觉控制) score from the 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. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V4 Pro (0813) (Max) | 89.73 | #58 (DeepSeek V4 Pro (0813)) |
| 2 | DeepSeek V4.1 Flash (Max) | 87.16 | #37 (DeepSeek V4.1 Flash) |
| 3 | Qwen 3.8 Max (Max) | 86.08 | #34 (Qwen 3.8 Max) |
| 4 | Qwen 3.8 Flash (Max) | 86.08 | #62 (Qwen 3.8 Flash) |
| 5 | Kimi K3 (Max) | 83.85 | #35 (Kimi K3) |
| 6 | GLM-5.3 Flash (Max) | 81.81 | #77 (GLM-5.3 Flash) |
| 7 | GLM-5.2 (Max) | 80.66 | #80 (GLM-5.2) |
| 8 | DeepSeek V4 Pro (Max) | 79.7 | #112 (DeepSeek V4 Pro) |
| 9 | GLM-5.3 (Max) | 79.35 | #44 (GLM-5.3) |
| 10 | Hy3 (High) | 79.2 | #100 (Hy3) |
| 11 | Doubao-Seed-2.1-Pro (High) | 78.85 | |
| 12 | DeepSeek V4 Flash (Max) | 78.25 | #155 (DeepSeek V4 Flash) |
| 13 | MiniMax-M3 | 70.44 | #151 |
| 14 | LongCat 2.0 | 70.02 | #220 |
| 15 | Step 3.7 Flash (High) | 63.51 | #247 (Step 3.7 Flash) |
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-july-2026-hallucination-control · How It Works · Data refreshed daily, snapshot 2026-11-05.