WildFireVQA - Cross-Modal Reasoning: leaderboard

WildFireVQA (2026) is an aerial wildfire-monitoring visual question answering benchmark built from paired RGB and radiometric thermal drone imagery, with multiple-choice answers generated by Gemini 2.5 Pro or, for some questions, computed from sensor data, then audited by manual verification and consistency checks. This board is accuracy in percent on the cross-modal reasoning questions with RGB images; higher is better.

Metric: Accuracy (%) on the 4 cross-modal reasoning question types of the WildFireVQA wildfire-monitoring multiple-choice questions (34 question types, 6,097 aerial frames each, from FLAME drone imagery with model-generated or sensor-derived labels, manually verified), RGB image input without retrieved thermal statistics; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 4 models tracked. Updated 15 Nov 2026.

Top models

#ModelScoreOverall rank
1Qwen 3 VL 8B Instruct57.45#1029
2MiniCPM-V-250.41#7564
3llava-v1.6-mistral-7B38.75#3999
4InternVL2-8B31.23#3227

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=wildfirevqa-cross-modal-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.