DailyClue - Spatial Relationship: leaderboard
Metric: Accuracy (%) on spatial relationship reasoning (motion, occlusion, relative position) on DailyClue, 666 question-image pairs from daily scenarios whose answer requires finding a decisive visual clue; question-clue-answer triplets drafted by GPT-5 and Gemini 2.5 Pro, manually verified, and kept only when at most two of o4-mini, Gemini 2.5 Flash and Claude 3.7 Sonnet answered correctly; exact match, with a Gemini 2.5 Pro judge for open-ended answers; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 61.35 |
| 2 | O4 Mini | 58.28 |
| 3 | GPT-5 | 57.67 |
| 4 | Claude 3.7 Sonnet | 57.06 |
| 5 | Gemini 2.5 Flash | 55.83 |
| 6 | InternVL3-78B | 54.6 |
| 7 | Claude Sonnet 4.5 | 53.99 |
| 8 | Claude Sonnet 4 | 52.15 |
| 9 | Qwen 3 VL 235B A22B (Thinking) | 49.08 |
| 10 | InternVL3-38B | 47.85 |
| 11 | Qwen 2.5 VL 72B Instruct | 47.85 |
| 12 | Qwen 3 VL 235B A22B Instruct | 46.63 |
| 13 | Qwen 2.5 VL 32B Instruct | 42.94 |
| 14 | Qwen 2.5 VL 7B Instruct | 39.88 |
Interactive version: theaggregate.ai/benchmark?slug=dailyclue-spatial-relationship · How It Works · Data refreshed daily, snapshot 2026-10-07.