List your company
ResearchFormerly WizWand

Mathematical Reasoning on AIME 2024 (Pass@16, Mean@16, Token Metrics)

24.4Mean Score @16TTRL-PPO
0.5846.76712.9519.133Dec 2, 2025
Updated 8mo ago

Evaluation results

MethodLinks
TTRL-PPOBackbone=Qwen2.5-7B, Methodology=TTRL, RL Algorithm=PPO2025.1224.446.723.3——
OptPO-PPOBackbone=Qwen2.5-7B, Methodology=OptPO, RL Algorithm=PPO2025.122443.326.7—42.85
TTRL-GRPOBackbone=Qwen2.5-7B, Methodology=TTRL, RL Algorithm=GRPO2025.1223.54023.3——
OptPO-GRPOBackbone=Qwen2.5-7B, Methodology=OptPO, RL Algorithm=GRPO2025.1223.543.323.3—38.56
TTRL-Rei++Backbone=Qwen2.5-7B, Methodology=TTRL, RL Algorithm=Rei++2025.1220.84023.3——
OptPO+Rei++Backbone=Qwen2.5-7B, Methodology=OptPO, RL Algorithm=Rei++2025.1220.64023.3—41.45
TTRL-PPOBackbone=Qwen2.5-Math-1.5B, Methodology=TTRL, RL Algorithm=PPO2025.1218.546.723.3——
OptPO-PPOBackbone=Qwen2.5-Math-1.5B, Methodology=OptPO, RL Algorithm=PPO2025.121646.723.3—15.2
TTRL-GRPOBackbone=Qwen2.5-Math-1.5B, Methodology=TTRL, RL Algorithm=GRPO2025.1215.643.320——
OptPO-GRPOBackbone=Qwen2.5-Math-1.5B, Methodology=OptPO, RL Algorithm=GRPO2025.1214.646.720—17.25
TTRL-Rei++Backbone=Qwen2.5-Math-1.5B, Methodology=TTRL, RL Algorithm=Rei++2025.1211.943.320——
OptPO-Rei++Backbone=Qwen2.5-Math-1.5B, Methodology=OptPO, RL Algorithm=Rei++2025.1210.446.720—14.35
TTRL-PPOBackbone=Llama-3.2-1B-Instruct, Methodology=TTRL, RL Algorithm=PPO2025.123.8306.7——
OptPO-PPOBackbone=Llama-3.2-1B-Instruct, Methodology=OptPO, RL Algorithm=PPO2025.123.8306.7—13.7
TTRL-GRPOBackbone=Llama-3.2-1B-Instruct, Methodology=TTRL, RL Algorithm=GRPO2025.123.523.36.7——
OptPO-GRPOBackbone=Llama-3.2-1B-Instruct, Methodology=OptPO, RL Algorithm=GRPO2025.121.7206.7—47.62
OptPO-Rei++Backbone=Llama-3.2-1B-Instruct, Methodology=OptPO, RL Algorithm=Rei++2025.121.723.36.7—30.02
TTRL-Rei++Backbone=Llama-3.2-1B-Instruct, Methodology=TTRL, RL Algorithm=Rei++2025.121.516.76.7——