List your company

Scientific Multimodal Reasoning on SFE

44.06AccuracyGPT-5
24.622429.668734.71539.7613Apr 23, 2026

Evaluation results

MethodLinks
GPT-52026.0444.06
Intern-S1Parameter Count=235B+6B2026.0443.98
S1-VL-32B-RLParameter Count=32B, Training Phase=RL2026.0443.1
Gemini 2.5 Pro2026.0443
S1-VL-32B-SFTParameter Count=32B, Training Phase=SFT2026.0442.58
Qwen3-VL-235B-A22B-ThinkingParameter Count=235B-A22B, Reasoning Mode=Thinking2026.0439.98
Gemini 2.5 Flash2026.0437.6
Qwen3-VL-32B-ThinkingParameter Count=32B, Reasoning Mode=Thinking2026.0437.5
Intern-S1-miniParameter Count=8B2026.0436.93
Thyme-VLParameter Count=7B2026.0425.37