FREAK - Position: leaderboard
Metric: Accuracy (%) on the position questions of FREAK's 1,799 questions (1,000 multiple-choice with cyclic option permutations and 799 free-form judged by GPT-5-mini) on photorealistic images edited to contradict commonsense; reasoning enabled where the model supports it; higher is better. Source: arxiv.org. Saturation forecast: Around 2033. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 43.41 | #145 |
| 2 | GPT-4.1 | 39.37 | #240 |
| 3 | O3 (High) | 38.77 | #121 (O3) |
| 4 | InternVL3-78B | 38.41 | #345 |
| 5 | Qwen 2.5 VL 72B Instruct | 38.22 | #364 |
| 6 | GLM-4.5V | 37.41 | #339 |
| 7 | InternVL3-38B | 37.21 | #395 |
| 8 | O4 Mini | 35.87 | #172 |
| 9 | Gemini 2.5 Flash | 35.46 | #237 |
| 10 | Phi-4 Multimodal Instruct | 32.77 | #896 |
| 11 | Qwen 2.5 VL 32B Instruct | 31.77 | #443 |
| 12 | Claude Sonnet 4 (Thinking) | 25.45 | #194 (Claude Sonnet 4) |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=freak-position · How It Works · Data refreshed daily, snapshot 2026-10-11.