GeoMMBench - Perception: leaderboard
The perception questions (scene, object and sensor-level recognition) of GeoMMBench (2026), an expert-written multimodal geoscience and remote sensing question benchmark answered zero-shot (test set). Micro-averaged accuracy in percent; higher is better.
Metric: Micro-averaged accuracy (%) on the perception questions (scene, object and sensor-level recognition and fine-grained interpretation) 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 2029. 35 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 1.5 Pro | 68.2 | #1063 |
| 2 | Gemini 2.0 Flash | 66.2 | #723 |
| 3 | GPT-4o | 63.9 | #751 |
| 4 | Qwen 2 VL 7B | 63.5 | #2275 |
| 5 | O1 | 63.5 | #403 |
| 6 | Qwen 3 VL 8B | 62.5 | #917 |
| 7 | Qwen 3 VL 30B | 61.2 | #561 |
| 8 | Qwen 2.5 VL 7B | 59.2 | #1862 |
| 9 | Qwen 3 VL 4B | 58.9 | #1151 |
| 10 | GPT-4V | 58.5 | #1470 |
| 11 | Qwen 2.5 VL 3B | 57.9 | #2639 |
| 12 | CogVLM2 | 57.9 | |
| 13 | LLaVA-OneVision-7B | 57.5 | #2981 |
| 14 | InternVL2.5-8B | 55.2 | #2370 |
| 15 | Phi-4 Multimodal Instruct | 53.2 | #4154 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=geommbench-perception · How It Works · Data refreshed daily, snapshot 2026-11-21.