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

Terminal Agent Tasks on OpenThoughts TBLite

15.1Pass@1

Qwen3-14B

Updated 2mo ago

Evaluation Results

Method	Links
Qwen3-14B 2026.05		15.1
OT-SFT 2026.05		12.9
OT-SFT 2026.05		11.6
Qwen3-8B 2026.05		11.4
Qwen3-14B 2026.05		9.8
Qwen3-8B 2026.05		9.5
OT-SFT 2026.05		6
Qwen3-14B 2026.05		5.7
Qwen3-8B 2026.05		4.9