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

Makespan Accuracy on Robotouille

20Makespan Accuracy

Gemini-3-flash

Updated 1d ago

Evaluation Results

Method	Links
Gemini-3-flash 2026.05		20
GPT-5-mini 2026.05		20
DeepSeek-V4-Flash 2026.05		20
Qwen3.6 35B A3B 2026.05		10
Gemini-3-flash 2026.05		0
Gemini-3-flash 2026.05		0
GPT-5-mini 2026.05		0
GPT-5-mini 2026.05		0
DeepSeek-V4-Flash 2026.05		0
DeepSeek-V4-Flash 2026.05		0
Qwen3.6 35B A3B 2026.05		0
Qwen3.6 35B A3B 2026.05		0