List your company

Terminal Agent Tasks on val100 (val)

73.1Pass@1OT-SFT
32.64443.14753.6564.153May 23, 2026

Evaluation results

MethodLinks
OT-SFTSetup=ECHO2026.0573.1
Qwen3-14BSetup=ECHO2026.0565
Qwen3-8BSetup=ECHO2026.0563.7
OT-SFTSetup=GRPO2026.0563.5
Qwen3-14BSetup=GRPO2026.0560.3
Qwen3-8BSetup=GRPO2026.0554.9
OT-SFTSetup=SFT2026.0538.5
Qwen3-14BSetup=Base2026.0535.3
Qwen3-8BSetup=Base2026.0534.2