List your company

Logical Reasoning on SynLogic

8.7pass@1F-GRPO
4.1245.3126.57.688Feb 6, 2026

Evaluation results

MethodLinks
F-GRPOBackbone=Qwen2.5-7B, Group Size (N)=82026.028.757
F-CISPOBackbone=Qwen2.5-7B, Group Size (N)=82026.028.260
CISPOBackbone=Qwen2.5-7B, Group Size (N)=82026.02853.6
GRPOBackbone=Qwen2.5-7B, Group Size (N)=82026.027.951.3
F-DAPOBackbone=Qwen2.5-7B, Group Size (N)=82026.027.962.4
DAPOBackbone=Qwen2.5-7B, Group Size (N)=82026.027.553.3
F-CISPOBackbone=Llama-3.2-3B-Instruct, Group Size (N)=82026.025.433.9
CISPOBackbone=Qwen2.5-1.5B-Math, Group Size (N)=82026.025.226.3
DAPOBackbone=Qwen2.5-1.5B-Math, Group Size (N)=82026.02526.9
GRPOBackbone=Qwen2.5-1.5B-Math, Group Size (N)=82026.024.927.4
F-DAPOBackbone=Qwen2.5-1.5B-Math, Group Size (N)=82026.024.926.4
F-CISPOBackbone=Qwen2.5-1.5B-Math, Group Size (N)=82026.024.926.1
F-GRPOBackbone=Qwen2.5-1.5B-Math, Group Size (N)=82026.024.827.5
DAPOBackbone=Llama-3.2-3B-Instruct, Group Size (N)=82026.024.828.9
GRPOBackbone=Llama-3.2-3B-Instruct, Group Size (N)=82026.024.736.4
F-GRPOBackbone=Llama-3.2-3B-Instruct, Group Size (N)=82026.024.635.5
F-DAPOBackbone=Llama-3.2-3B-Instruct, Group Size (N)=82026.024.333
CISPOBackbone=Llama-3.2-3B-Instruct, Group Size (N)=82026.024.329.4