Share your thoughts, 1 month free Claude Pro on usSee more

Visual Grounded Reasoning on TRIG

38.69Chart Score

PreciseDoc-Reasoner

Updated 1mo ago

Evaluation Results

Method	Links
PreciseDoc-Reasoner 2026.06		38.69	49.81	29.66	67.5	46.42
Gemini-3-Pro 2026.06		18.86	30.94	20.82	50.42	30.26
Qwen3VL-30B-a3b-thinking 2026.06		12.05	39.07	15.49	68.34	33.74
Gemini-3-Flash 2026.06		11.81	22.35	14.7	37.03	21.47
Qwen3VL-8B 2026.06		8.27	31.19	9.3	65.16	28.48
GPT-4o 2026.06		3.9	1.79	1.6	13.73	5.26
GPT-5.2 2026.06		3.09	1.87	2.17	11.98	4.78
Qwen3.5-27B 2026.06		2.89	14.77	5.41	57.04	20.03
InternLM-XComposer2-4KHD-7B 2026.06		1.04	0.1	0.9	0.14	0.55
Monkey-Chat 2026.06		0.77	0.19	0.15	0.45	0.39
Qwen3.5-9B 2026.06		0.73	20.43	5.08	44.64	17.72
InternVL3-8B 2026.06		0.72	17.61	2.02	21.97	10.58
MiniCPM-Llama3-V 2.5 2026.06		0.44	1.4	0.65	4.96	1.86
InternLM-XComposer2-VL-7B 2026.06		0.15	0.2	0.13	0.57	0.26
LLaVA-v1.6-Vicuna-13B 2026.06		0	0	0	0	0
Qwen2-VL-7B 2026.06		0	0	0	0	0
Qwen2.5-VL-7B 2026.06		0	0	0	0	0
InternVL2-8B 2026.06		0	0	0	0	0
InternVL2.5-8B 2026.06		0	0	0	0	0
Gemini-2.0-Flash 2026.06		0	0	0	0	0
Gemini-2.5-Flash 2026.06		0	0	0	0	0