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

Genetic Circuit Design on Cello-ID

66.2Task Success Rate (TSR)

Qwen3-8B RLVF-H-C

Updated 9d ago

Evaluation Results

Method	Links
Qwen3-8B RLVF-H-C 2026.05		66.2
Gemma-3-12B RLVF-H-C 2026.05		59
Qwen3-8B RLVF-HIER 2026.05		58.3
Llama-3.1-8B RLVF-H-C 2026.05		57.4
Qwen3-8B RLVF-BIN 2026.05		50.4
Qwen3-8B SFT 2026.05		46.2
Gemma-3-12B SFT 2026.05		41.2
Llama-3.1-8B SFT 2026.05		39.8
OPUS 4.5 2026.05		36.5
OPUS 4.5 2026.05		25.4
Qwen3-8B BASE 2026.05		8.2