SuperCLUE General (May 2026) - Hallucination Control: leaderboard
Metric: Score. Source: www.superclueai.com. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 (High) | 87.48 |
| 2 | GPT-5.5 (High) | 87.26 |
| 3 | Gemini 3.1 Pro (Preview) (High) | 87.23 |
| 4 | Gemini 3.5 Flash (High) | 86.16 |
| 5 | Qwen 3.6 Max (Preview) (Thinking) | 85.14 |
| 6 | Gemma 4 31B | 82.95 |
| 7 | Claude Opus 4.7 (High) | 81.11 |
| 8 | DeepSeek V4 Pro (Max) | 79.14 |
| 9 | Kimi K2.6 (Thinking) | 78.66 |
| 10 | Ernie 5.1 | 76.81 |
| 11 | GLM-5.1 | 74.67 |
| 12 | MiniMax-M3 | 73.17 |
| 13 | DeepSeek V4 Flash (Max) | 70.9 |
| 14 | Grok 4.3 | 70.51 |
| 15 | Hy3-preview (High) | 67.62 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-may-2026-hallucination-control · How It Works · Data refreshed daily, snapshot 2026-09-19.