List your company

Mathematical Reasoning on OlymMATH

9.3AccuracyNExt
4.8285.9897.158.311Apr 13, 2026

Evaluation results

MethodLinks
NExt#Steps=250, Backbone=Qwen2.5-14B-Instruct2026.049.3
GRPO w/ FP#Steps=250, Backbone=Qwen2.5-14B-Instruct2026.048.8
GRPO w/ FP#Steps=400, Backbone=Qwen2.5-14B-Instruct2026.048.8
GRPO w/ LoRA#Steps=400, Backbone=Qwen2.5-14B-Instruct2026.048.8
GRPO w/ LoRA#Steps=250, Backbone=Qwen2.5-14B-Instruct2026.047.8
AlphaRL#Steps=250, Backbone=Qwen2.5-14B-Instruct2026.047.8
RL-Extra#Steps=250, Backbone=Qwen2.5-14B-Instruct2026.047.6
GRPO w/ FP#Steps=400, Backbone=Qwen2.5-7B-Instruct2026.046.8
NExt#Steps=250, Backbone=Qwen2.5-7B-Instruct2026.046.5
GRPO w/ FP#Steps=250, Backbone=Qwen2.5-7B-Instruct2026.046
RL-Extra#Steps=250, Backbone=Qwen2.5-7B-Instruct2026.045.8
Backbone Model#Steps=-, Backbone=Qwen2.5-14B-Instruct2026.045.4
Backbone Model#Steps=-, Backbone=Qwen2.5-7B-Instruct2026.045.3
GRPO w/ LoRA#Steps=250, Backbone=Qwen2.5-7B-Instruct2026.045
GRPO w/ LoRA#Steps=400, Backbone=Qwen2.5-7B-Instruct2026.045
AlphaRL#Steps=250, Backbone=Qwen2.5-7B-Instruct2026.045