DailyClue: leaderboard
Metric: Overall accuracy (%) 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 August 2027. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 56.9 |
| 2 | GPT-5 | 50.9 |
| 3 | Gemini 2.5 Flash | 50 |
| 4 | O4 Mini | 47 |
| 5 | Qwen 3 VL 235B A22B (Thinking) | 44.59 |
| 6 | Claude Sonnet 4.5 | 41.74 |
| 7 | Claude Sonnet 4 | 41.74 |
| 8 | Claude 3.7 Sonnet | 41.14 |
| 9 | InternVL3-78B | 40.84 |
| 10 | Qwen 2.5 VL 72B Instruct | 40.84 |
| 11 | Qwen 3 VL 235B A22B Instruct | 40.69 |
| 12 | InternVL3-38B | 36.94 |
| 13 | Qwen 2.5 VL 32B Instruct | 35.59 |
| 14 | InternVL3-8B | 31.08 |
| 15 | Qwen 2.5 VL 7B Instruct | 30.63 |
Interactive version: theaggregate.ai/benchmark?slug=dailyclue · How It Works · Data refreshed daily, snapshot 2026-10-07.