List your company

Overall on GEODRIVE-BENCH

78.6Overall ScoreDRIVEOPD‡
40.74450.57260.470.228Jun 1, 2026

Evaluation results

MethodLinks
DRIVEOPD‡Setting=Rule-Given, Backbone=InternVL3-8B2026.0678.6
Qwen3-VL-8BSetting=Rule-Given2026.0677.7
DRIVEOPD‡Setting=Direct, Backbone=InternVL3-8B2026.0677.3
InternVL3-8BSetting=Rule-Given2026.0677.2
DRIVEOPD‡Setting=Reasoning, Backbone=InternVL3-8B2026.0677.1
InternVL3.5-8BSetting=Rule-Given2026.0676.8
DRIVEOPD†Setting=Direct, Backbone=Qwen2.5-VL-7B2026.0675.7
Gemma3-12BSetting=Rule-Given2026.0672.2
DRIVEOPD†Setting=Rule-Given, Backbone=Qwen2.5-VL-7B2026.0671.6
Qwen2.5-VL-7BSetting=Rule-Given2026.0670.3
DRIVEOPD†Setting=Reasoning, Backbone=Qwen2.5-VL-7B2026.0668.4
Llama-3.2-11B-VSetting=Rule-Given2026.0663.6
InternVL3-8BSetting=Direct2026.0661
Gemma3-12BSetting=Direct2026.0660.1
InternVL3.5-8BSetting=Direct2026.0659.9
Qwen3-VL-8BSetting=Direct2026.0658.8
Gemma3-12BSetting=Reasoning2026.0658.5
Qwen2.5-VL-7BSetting=Direct2026.0657.9
InternVL3-8BSetting=Reasoning2026.0657.4
LLaVA-1.6-7BSetting=Rule-Given2026.0657.1
InternVL3.5-8BSetting=Reasoning2026.0654.6
Qwen2.5-VL-7BSetting=Reasoning2026.0651.8
Qwen3-VL-8BSetting=Reasoning2026.0650.5
Llama-3.2-11B-VSetting=Reasoning2026.0647
Llama-3.2-11B-VSetting=Direct2026.0645.5
LLaVA-1.6-7BSetting=Reasoning2026.0643.2
LLaVA-1.6-7BSetting=Direct2026.0642.2