List your company

Genetic Circuit Design on Procedural (test)

72.7Task Success Rate (TSR)Qwen3-8B RLVF-H-C
7.90824.72941.5558.371May 14, 2026

Evaluation results

MethodLinks
Qwen3-8B RLVF-H-CTraining Protocol=GenCircuit-RL (Hierarchical-Curriculum)2026.0572.7
Qwen3-8B RLVF-HIERTraining Protocol=RLVF-Hierarchical2026.0567.7
Gemma-3-12B RLVF-H-CTraining Protocol=GenCircuit-RL (Hierarchical-Curriculum)2026.0566.2
Llama-3.1-8B RLVF-H-CTraining Protocol=GenCircuit-RL (Hierarchical-Curriculum)2026.0564.1
Qwen3-8B RLVF-BINTraining Protocol=RLVF-Binary2026.0558.6
Qwen3-8B SFTTraining Protocol=Supervised fine-tuning2026.0553.9
Gemma-3-12B SFTTraining Protocol=Supervised fine-tuning2026.0549
Llama-3.1-8B SFTTraining Protocol=Supervised fine-tuning2026.0547.2
OPUS 4.5Few-shot Setting=5-shot2026.0541.8
OPUS 4.5Few-shot Setting=0-shot2026.0530.8
Qwen3-8B BASEFew-shot Setting=0-shot2026.0510.4