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

Genetic Circuit Design on Literature-91

44.9Task Success Rate (TSR)

Qwen3-8B RLVF-H-C

Updated 9d ago

Evaluation Results

Method	Links
Qwen3-8B RLVF-H-C 2026.05		44.9
Gemma-3-12B RLVF-H-C 2026.05		39
Qwen3-8B RLVF-HIER 2026.05		37.8
Llama-3.1-8B RLVF-H-C 2026.05		37.1
Qwen3-8B RLVF-BIN 2026.05		31.1
Qwen3-8B SFT 2026.05		27.3
Gemma-3-12B SFT 2026.05		23.4
Llama-3.1-8B SFT 2026.05		22.4
OPUS 4.5 2026.05		21.7
OPUS 4.5 2026.05		14.8
Qwen3-8B BASE 2026.05		4.4