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

Engineering Design Workflow Evaluation on Beams2D

100TC

GPT-5-mini

Updated 14d ago

Evaluation Results

Method	Links
GPT-5-mini 2026.05		100	65
GPT-5-mini 2026.05		100	66
GPT-5-mini 2026.05		100	65
GPT-5-mini 2026.05		100	63
Gemini-3-Flash 2026.05		100	88
Gemini-3-Flash 2026.05		100	65
Gemini-3-Flash 2026.05		100	64
Gemini-3-Flash 2026.05		100	63
Gemini-3-Flash 2026.05		100	70
Qwen3-4B 2026.05		100	64
Qwen3-4B 2026.05		100	61
Qwen3-4B 2026.05		100	65
Qwen3.5-4B 2026.05		100	69
Qwen3.5-4B 2026.05		100	69
GPT-5-mini 2026.05		93	66
GPT-5-mini 2026.05		93	66
Gemini-3-Flash 2026.05		93	69
Qwen3.5-4B 2026.05		93	66
GPT-5-mini 2026.05		87	82
Gemini-3-Flash 2026.05		87	65
Qwen3.5-4B 2026.05		85	66
Qwen3.5-4B 2026.05		73	59
Qwen3.5-4B 2026.05		60	62
Qwen3-4B 2026.05		47	53
Qwen3-4B 2026.05		40	57
Qwen3.5-4B 2026.05		33	48
GPT-5-mini 2026.05		1	0.66
GPT-5-mini 2026.05		1	0.63
Gemini-3-Flash 2026.05		1	0.65
Gemini-3-Flash 2026.05		1	0.63
Qwen3-4B 2026.05		1	0.64
Qwen3-4B 2026.05		1	0.61
Qwen3.5-4B 2026.05		1	0.69
GPT-5-mini 2026.05		0.93	0.66
Qwen3.5-4B 2026.05		0.93	0.66
Gemini-3-Flash 2026.05		0.87	0.65
Qwen3.5-4B 2026.05		0.6	0.62
Qwen3-4B 2026.05		0.4	0.57
Qwen3-4B 2026.05		0	45
Qwen3-4B 2026.05		0	29