XWOD - Weather Classification: leaderboard
XWOD (2026) weather classification probe: from a single street-level driving image, a vision-language model must name the dominant extreme weather as one of seven labels (rain, snow, fog, haze or dust, flooding, tornado, wildfire), zero-shot, over 700 class-balanced test images. Top-1 accuracy in percent; higher is better.
Metric: Top-1 accuracy (%, times 100) of XWOD-LLM-WC: a vision-language model names the dominant extreme weather of a single street-level image as one of seven labels (rain, snow, fog, haze/sand/dust, flooding, tornado, wildfire), on a class-balanced probe of 700 XWOD test images (100 per class, fixed seed, longest side at most 1024 px); one zero-shot single-turn prompt without chain of thought, the free-text reply canonicalized by exact match and a keyword fallback, unmatched replies counted wrong; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 4 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 75.71 | #102 |
| 2 | Gemini 3.1 Flash Lite (Preview) | 75 | #419 |
| 3 | Claude Opus 4.7 | 74.71 | #86 |
| 4 | GPT-5.5 | 71.86 | #56 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=xwod-weather-classification · How It Works · Data refreshed daily, snapshot 2026-11-22.