SuperCLUE General (July 2025) - Hallucination Control: leaderboard
Metric: Score. Source: www.superclueai.com. 47 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4 (Thinking) | 90.24 |
| 2 | Doubao-Seed-1.6-thinking-250715 | 89.59 |
| 3 | Gemini 2.5 Flash | 89.36 |
| 4 | Hunyuan-T1-20250711 | 83.39 |
| 5 | GPT-5 (High) | 83.08 |
| 6 | Step 2 16K | 83.03 |
| 7 | Gemini 2.5 Pro | 83 |
| 8 | DeepSeek R1 0528 | 82.28 |
| 9 | DeepSeek V3.1 (Thinking) | 82.19 |
| 10 | DeepSeek V3 (0324) | 81.71 |
| 11 | Grok 4 | 79.65 |
| 12 | GLM-4.5 | 78.42 |
| 13 | O3 (High) | 77.41 |
| 14 | O4 Mini (High) | 75.9 |
| 15 | SenseNova V6 Reasoner | 75.57 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-july-2025-hallucination-control · How It Works · Data refreshed daily, snapshot 2026-09-19.