DailyClue: leaderboard

Visual clue-driven reasoning in daily scenarios on DailyClue (2026, Seek-and-Solve): 666 image questions across location identification, spatial relationships, daily commonsense and scientific commonsense, built so that the answer depends on spotting a decisive visual clue in a cluttered everyday image. Overall accuracy in percent; higher is better.

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 March 2027. 23 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro56.9#276
2GPT-550.9#178
3Gemini 2.5 Flash50#463
4O4 Mini47#368
5Thyme-7B46.25#1036
6Qwen 3 VL 235B A22B (Thinking)44.59#459
7Claude Sonnet 4.541.74#261
8Claude Sonnet 441.74#410
9Claude 3.7 Sonnet41.14#470
10InternVL3-78B40.84#759
11Qwen 2.5 VL 72B Instruct40.84#841
12Qwen 3 VL 235B A22B Instruct40.69#532
13InternVL3-38B36.94#939
14Qwen 2.5 VL 32B Instruct35.59#1062
15LLaVA-OneVision-72B33.18#1771

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=dailyclue · How It Works · Data refreshed daily, snapshot 2026-11-21.