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

Scientific Multimodal Reasoning on SFE

44.06Accuracy

GPT-5

Updated 1mo ago

Evaluation Results

Method	Links
GPT-5 2026.04		44.06
Intern-S1 2026.04		43.98
S1-VL-32B-RL 2026.04		43.1
Gemini 2.5 Pro 2026.04		43
S1-VL-32B-SFT 2026.04		42.58
Qwen3-VL-235B-A22B-Thinking 2026.04		39.98
Gemini 2.5 Flash 2026.04		37.6
Qwen3-VL-32B-Thinking 2026.04		37.5
Intern-S1-mini 2026.04		36.93
Thyme-VL 2026.04		25.37