List your company

Embodied Question Answering on OpenEQA v1.0 (test)

67.7LLM-MatchCoV
44.996850.890956.78562.6791Jan 8, 2026

Evaluation results

MethodLinks
CoVBackbone=GLM-4.6v, Action Steps=62026.0167.78.51.04
CoVBackbone=GLM-4.6v, Action Steps=72026.0167.64——
CoVBackbone=GLM-4.6v, Action Steps=22026.0167.33——
CoVBackbone=GLM-4.6v, Action Steps=52026.0167.23——
CoVBackbone=GLM-4.6v, Action Steps=32026.0167.2——
CoVBackbone=GLM-4.6v, Action Steps=12026.0167——
CoVBackbone=GLM-4.6v, Action Steps=42026.0166.3——
BaselineBackbone=GLM-4.6v2026.0162.4——
CoVBackbone=Qwen3-VL-Flash, Action Steps=42026.0159.8213.621.82
CoVBackbone=Qwen3-VL-Flash, Action Steps=72026.0159.77——
CoVBackbone=Qwen3-VL-Flash, Action Steps=62026.0159.39——
CoVBackbone=Gemini-2.5-Flash, Action Steps=62026.0159.2311.73.73
CoVBackbone=Gemini-2.5-Flash, Action Steps=72026.0159.16——
CoVBackbone=Qwen3-VL-Flash, Action Steps=22026.0159.07——
CoVBackbone=Qwen3-VL-Flash, Action Steps=32026.0159.03——
CoVBackbone=Qwen3-VL-Flash, Action Steps=52026.0159.03——
CoVBackbone=Gemini-2.5-Flash, Action Steps=52026.0158.82——
CoVBackbone=Gemini-2.5-Flash, Action Steps=32026.0158.8——
CoVBackbone=Qwen3-VL-Flash, Action Steps=12026.0158.75——
CoVBackbone=Gemini-2.5-Flash, Action Steps=42026.0158.15——
CoVBackbone=Gemini-2.5-Flash, Action Steps=22026.0157.15——
CoVBackbone=Gemini-2.5-Flash, Action Steps=12026.0157.1——
BaselineBackbone=Qwen3-VL-Flash2026.0152.65——
BaselineBackbone=Gemini-2.5-Flash2026.0152.3——
CoVBackbone=GPT-4o-Mini, Action Steps=72026.0151.62——
CoVBackbone=GPT-4o-Mini, Action Steps=52026.0151.5612.43.43
CoVBackbone=GPT-4o-Mini, Action Steps=62026.0151.41——
CoVBackbone=GPT-4o-Mini, Action Steps=42026.0150.8——
CoVBackbone=GPT-4o-Mini, Action Steps=22026.0150.15——
CoVBackbone=GPT-4o-Mini, Action Steps=12026.0149.85——
CoVBackbone=GPT-4o-Mini, Action Steps=32026.0149.6——
BaselineBackbone=GPT-4o-Mini2026.0145.87——