GeoMMBench: leaderboard
Expert-written multimodal geoscience and remote sensing questions on the GeoMMBench (2026) test set, spanning remote sensing, photogrammetry, GIS and GNSS across optical, SAR, LiDAR, elevation, spectral and thermal data, answered zero-shot. Micro-averaged accuracy in percent; higher is better.
Metric: Micro-averaged accuracy (%) on all 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 February 2027. 35 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 1.5 Pro | 70.7 | #1063 |
| 2 | Gemini 2.0 Flash | 70.1 | #723 |
| 3 | GPT-4o | 68.5 | #751 |
| 4 | Qwen 3 VL 30B | 66.7 | #561 |
| 5 | O1 | 65.8 | #403 |
| 6 | Qwen 3 VL 8B | 65.8 | #917 |
| 7 | Qwen 3 VL 4B | 63.2 | #1151 |
| 8 | Qwen 2.5 VL 7B | 62.5 | #1862 |
| 9 | GPT-4V | 61 | #1470 |
| 10 | Qwen 2 VL 7B | 59.8 | #2275 |
| 11 | Qwen 2.5 VL 3B | 58.1 | #2639 |
| 12 | LLaVA-OneVision-7B | 57.3 | #2981 |
| 13 | InternVL2.5-8B | 56.8 | #2370 |
| 14 | Phi-4 Multimodal Instruct | 55.3 | #4154 |
| 15 | LLaVA-NeXT-34B | 54.2 | #3443 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=geommbench · How It Works · Data refreshed daily, snapshot 2026-11-21.