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

Genetic Circuit Design on Cello-OOD

52.6Task Success Rate (TSR)

Qwen3-8B RLVF-H-C

Updated 9d ago

Evaluation Results

Method	Links
Qwen3-8B RLVF-H-C 2026.05		52.6
Gemma-3-12B RLVF-H-C 2026.05		46.8
Llama-3.1-8B RLVF-H-C 2026.05		45.2
Qwen3-8B RLVF-HIER 2026.05		44.1
Qwen3-8B RLVF-BIN 2026.05		36.2
Qwen3-8B SFT 2026.05		32.4
Gemma-3-12B SFT 2026.05		28.8
OPUS 4.5 2026.05		28.4
Llama-3.1-8B SFT 2026.05		27.6
OPUS 4.5 2026.05		18.6
Qwen3-8B BASE 2026.05		5.1