GeoMMBench - Principles: leaderboard
The principles and theory questions 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 principles and theoretical understanding 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 | 71.5 | #1071 |
| 2 | Gemini 2.0 Flash | 68.9 | #731 |
| 3 | GPT-4o | 65.8 | #754 |
| 4 | O1 | 64.2 | #407 |
| 5 | Qwen 3 VL 30B | 63.2 | #566 |
| 6 | Qwen 3 VL 8B | 61.4 | #927 |
| 7 | Qwen 2.5 VL 7B | 59.8 | #1878 |
| 8 | GPT-4V | 59.8 | #1483 |
| 9 | Qwen 3 VL 4B | 58.2 | #1163 |
| 10 | Qwen 2.5 VL 3B | 54.3 | #2664 |
| 11 | Qwen 2 VL 7B | 53.8 | #2300 |
| 12 | LLaVA-OneVision-7B | 53.5 | #3002 |
| 13 | Phi-4 Multimodal Instruct | 53.3 | #4155 |
| 14 | LLaVA-NeXT-34B | 50.7 | #3483 |
| 15 | InternVL2.5-8B | 50.4 | #2393 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=geommbench-principles · How It Works · Data refreshed daily, snapshot 2026-11-22.