Measurement Reading on MeasureBench Real-world benchmark leaderboard · SOTA2 Research

Measurement Reading on MeasureBench Real-world

30.2Overall AccuracyGemini-2.5-Pro

Evaluation Results

Method	Links
Gemini-2.5-Pro2026.04		30.2	31.5	80.2	21.9	3.8
GPT-5-Mini2026.04		22	20.8	70.8	16.9	2.9
Qwen3-VL-4B-Instruct + TriSCA2026.04		20.5	28.5	41.7	10.4	1.9
Gemini-2.5-Flash2026.04		20.2	20.5	65.6	13	1
GPT-52026.04		19.8	18.3	66.7	15.2	2.9
Qwen3-VL-8B2026.04		15.3	14.5	53.1	11.3	0
Qwen2.5-VL-7B2026.04		14.6	13.8	49	11.4	0
Qwen2.5-VL-72B2026.04		14.5	12.2	55.2	12.2	0
Qwen3-VL-4B-Instruct2026.04		13.7	12	43.8	11.9	1
Qwen2.5-VL-32B2026.04		11.7	9	51.6	9.7	0