TimeSpot - Environment Type: leaderboard
Metric: Accuracy (%) of the predicted environment type (such as urban, suburban or rural) 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 | Qwen 2.5 VL 7B Instruct | 75.21 | #643 |
| 2 | GLM-4.1V-9B (Thinking) | 68.54 | #457 (GLM-4.1V-9B) |
| 3 | O4 Mini | 66.64 | #172 |
| 4 | Gemini 2.5 Flash (Thinking) | 64.47 | #237 (Gemini 2.5 Flash) |
| 5 | Gemini 2.5 Flash (Non-reasoning) | 64.32 | #237 (Gemini 2.5 Flash) |
| 6 | GLM-4.5V | 62.51 | #339 |
| 7 | Mistral Medium 3.1 | 61.72 | #400 |
| 8 | InternVL3-78B | 61.37 | #345 |
| 9 | Gemini 2.0 Flash | 60.96 | #331 |
| 10 | Qwen 2.5 VL 32B Instruct | 60.82 | #443 |
| 11 | Qwen 3 VL 235B A22B Instruct | 60.43 | #264 |
| 12 | GPT-5 Mini | 60.01 | #176 |
| 13 | Gemini 2.0 Flash (Thinking) | 59.93 | #331 (Gemini 2.0 Flash) |
| 14 | Llama 3.2 90B Vision Instruct | 59.04 | #611 |
| 15 | Qwen 2.5 VL 72B Instruct | 58.14 | #364 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=timespot-environment-type · How It Works · Data refreshed daily, snapshot 2026-10-11.