TimeSpot - Local Time: leaderboard
Metric: Accuracy (%) of the predicted local time of day within one hour on TimeSpot's 1,455 ground-level photographs from 80 countries, each answered zero-shot in a structured multi-field schema from the image alone; a Gemini-2.5-Flash judge normalizes each field (synonyms, abbreviations) and marks it correct or not; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 27 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-4.1V-9B (Thinking) | 33.74 | #457 (GLM-4.1V-9B) |
| 2 | Qwen 2.5 VL 32B Instruct | 31.1 | #443 |
| 3 | Mistral Medium 3.1 | 30.73 | #400 |
| 4 | GLM-4.5V | 30.51 | #339 |
| 5 | GPT-4o Mini | 30.32 | #588 |
| 6 | InternVL3-78B | 29.64 | #345 |
| 7 | GPT-5.2 | 29.35 | #105 |
| 8 | Qwen 2.5 VL 72B Instruct | 28.71 | #364 |
| 9 | Gemini 2.0 Flash (Thinking) | 27.49 | #331 (Gemini 2.0 Flash) |
| 10 | Gemini 2.0 Flash | 27.35 | #331 |
| 11 | Gemma 3 27B (IT) | 26.34 | #509 |
| 12 | Qwen 3 VL 235B A22B Instruct | 26.22 | #264 |
| 13 | Llama 3.2 11B Instruct | 25.74 | #1112 |
| 14 | Qwen 2.5 VL 7B Instruct | 25.68 | #643 |
| 15 | Gemini 2.5 Flash (Non-reasoning) | 25.15 | #237 (Gemini 2.5 Flash) |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=timespot-local-time · How It Works · Data refreshed daily, snapshot 2026-10-11.