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

Genetic Circuit Design on Procedural (test)

72.7Task Success Rate (TSR)

Qwen3-8B RLVF-H-C

Updated 9d ago

Evaluation Results

Method	Links
Qwen3-8B RLVF-H-C 2026.05		72.7
Qwen3-8B RLVF-HIER 2026.05		67.7
Gemma-3-12B RLVF-H-C 2026.05		66.2
Llama-3.1-8B RLVF-H-C 2026.05		64.1
Qwen3-8B RLVF-BIN 2026.05		58.6
Qwen3-8B SFT 2026.05		53.9
Gemma-3-12B SFT 2026.05		49
Llama-3.1-8B SFT 2026.05		47.2
OPUS 4.5 2026.05		41.8
OPUS 4.5 2026.05		30.8
Qwen3-8B BASE 2026.05		10.4