GeoMMBench - Time Series: leaderboard
Metric: Micro-averaged accuracy (%) on the time-series questions of the GeoMMBench test set (expert-written multimodal geoscience and remote sensing multiple-choice and numeric questions, zero-shot, LMMs-Eval, rule-based answer extraction, invalid outputs counted wrong); higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 36 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.0 Flash | 63 |
| 2 | Qwen 2 VL 7B | 58.7 |
| 3 | Gemini 1.5 Pro | 58.7 |
| 4 | GPT-4o | 56.5 |
| 5 | O1 | 56.5 |
| 6 | Qwen 2.5 VL 7B | 52.2 |
| 7 | GPT-5 | 50 |
| 8 | Qwen 2 VL 2B | 47.8 |
| 9 | Phi-4 Multimodal Instruct | 47.8 |
Interactive version: theaggregate.ai/benchmark?slug=geommbench-time-series · How It Works · Data refreshed daily, snapshot 2026-10-07.