TimeSpot - Continent: leaderboard
Metric: Accuracy (%) of the predicted continent 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: Around January 2027. 27 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash (Non-reasoning) | 90.51 | #237 (Gemini 2.5 Flash) |
| 2 | Gemini 2.5 Flash (Thinking) | 90.31 | #237 (Gemini 2.5 Flash) |
| 3 | Gemini 2.0 Flash | 89.07 | #331 |
| 4 | Gemini 2.0 Flash (Thinking) | 88.66 | #331 (Gemini 2.0 Flash) |
| 5 | Qwen 2.5 VL 7B Instruct | 85.7 | #643 |
| 6 | GLM-4.5V | 85.32 | #339 |
| 7 | GLM-4.1V-9B (Thinking) | 84.44 | #457 (GLM-4.1V-9B) |
| 8 | GPT-5 Mini | 83.62 | #176 |
| 9 | Qwen 3 VL 235B A22B Instruct | 83.41 | #264 |
| 10 | GPT-4o Mini | 82.68 | #588 |
| 11 | O4 Mini | 82.39 | #172 |
| 12 | GPT-5.2 | 81.93 | #105 |
| 13 | Gemma 3 27B (IT) | 79.59 | #509 |
| 14 | Qwen 2.5 VL 32B Instruct | 78.56 | #443 |
| 15 | Llama 3.2 90B Vision Instruct | 78.08 | #611 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=timespot-continent · How It Works · Data refreshed daily, snapshot 2026-10-11.