Perception or Prejudice — leaderboard
Metric: HR (self-reported). Source: benchmarklist.com. 27 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 33.5 |
| 2 | GPT-5.5 | 28 |
| 3 | Gemini 3.1 Pro (Preview) | 27.4 |
| 4 | Gemini 2.5 Pro | 20 |
| 5 | GPT-5.4 | 17.9 |
| 6 | Gemini 2.5 Flash | 16.9 |
| 7 | Claude Opus 4.6 | 16.8 |
| 8 | Qwen 3.5 397B A17B | 15.9 |
| 9 | Qwen 3 VL 235B A22B | 12.8 |
| 10 | Claude Sonnet 4.6 | 12.5 |
| 11 | Claude Haiku 4.5 | 12.4 |
| 12 | Gemma 4 31B | 11.3 |
| 13 | GPT-5.4 Mini | 11.3 |
| 14 | O4 Mini | 7.8 |
| 15 | Llama 4 Maverick | 5.8 |
Interactive version: theaggregate.ai/benchmark?slug=perception-or-prejudice · How the rankings work · Data refreshed daily, snapshot 2026-07-22.