List your company
ResearchFormerly WizWand

Mathematical Reasoning on AMC (Pass@N and Token Usage)

56.8Mean@16OptPO-GRPO
9.16821.53433.946.266Dec 2, 2025
Updated 8mo ago

Evaluation results

MethodLinks
OptPO-GRPOBackbone=Qwen2.5-7B, Methodology=OptPO, RL Algorithm=GRPO2025.1256.877.157.8—49.06
OptPO+Rei++Backbone=Qwen2.5-7B, Methodology=OptPO, RL Algorithm=Rei++2025.125679.557.8—43.5
TTRL-PPOBackbone=Qwen2.5-7B, Methodology=TTRL, RL Algorithm=PPO2025.1254.379.555.4——
OptPO-PPOBackbone=Qwen2.5-7B, Methodology=OptPO, RL Algorithm=PPO2025.1253.279.555.4—41.66
TTRL-Rei++Backbone=Qwen2.5-7B, Methodology=TTRL, RL Algorithm=Rei++2025.1252.980.755.4——
TTRL-GRPOBackbone=Qwen2.5-7B, Methodology=TTRL, RL Algorithm=GRPO2025.1252.178.354.2——
OptPO-GRPOBackbone=Qwen2.5-Math-1.5B, Methodology=OptPO, RL Algorithm=GRPO2025.1248.581.954.2—26.93
TTRL-PPOBackbone=Qwen2.5-Math-1.5B, Methodology=TTRL, RL Algorithm=PPO2025.1248.183.155.4——
OptPO-PPOBackbone=Qwen2.5-Math-1.5B, Methodology=OptPO, RL Algorithm=PPO2025.1248.183.153—26.8
TTRL-GRPOBackbone=Qwen2.5-Math-1.5B, Methodology=TTRL, RL Algorithm=GRPO2025.1247.783.154.2——
TTRL-Rei++Backbone=Qwen2.5-Math-1.5B, Methodology=TTRL, RL Algorithm=Rei++2025.1239.381.949.4——
OptPO-Rei++Backbone=Qwen2.5-Math-1.5B, Methodology=OptPO, RL Algorithm=Rei++2025.1238.381.944.6—27.42
OptPO-PPOBackbone=Llama-3.2-1B-Instruct, Methodology=OptPO, RL Algorithm=PPO2025.1217.154.222.9—41.76
OptPO-GRPOBackbone=Llama-3.2-1B-Instruct, Methodology=OptPO, RL Algorithm=GRPO2025.1215.255.416.9—78.36
TTRL-GRPOBackbone=Llama-3.2-1B-Instruct, Methodology=TTRL, RL Algorithm=GRPO2025.1214.951.818.1——
TTRL-PPOBackbone=Llama-3.2-1B-Instruct, Methodology=TTRL, RL Algorithm=PPO2025.1213.955.419.3——
TTRL-Rei++Backbone=Llama-3.2-1B-Instruct, Methodology=TTRL, RL Algorithm=Rei++2025.1211.454.216.9——
OptPO-Rei++Backbone=Llama-3.2-1B-Instruct, Methodology=OptPO, RL Algorithm=Rei++2025.121151.813.3—18.96