List your company

Mathematical Reasoning on OlyBench (Pass@1 accuracy)

47.1Pass@1 AccuracyrStar
23.1829.3935.641.81Aug 8, 2025Sep 11, 2025Oct 16, 2025Nov 19, 2025Dec 24, 2025Jan 27, 2026Mar 3, 2026

Evaluation results

MethodLinks
rStarFine-tuning base=Qwen2.5-Math-7B, Comparison Group=Non-comparable Baselines2025.0847.1
LUFFYFine-tuning base=Qwen2.5-Math-7B, Comparison Group=Non-comparable Baselines2025.0845.6
PrismBase model=Qwen3-4B-Base2026.0345.58
R-ZeroBase model=Qwen3-4B-Base2026.0344.59
ReLIFTFine-tuning base=Qwen2.5-Math-7B, Comparison Group=Non-comparable Baselines2025.0844.3
R-FewBase model=Qwen3-4B-Base, Selection percentage=5%2026.0342.8
SPICEBase model=Qwen3-4B-Base2026.0342.7
R-FewBase model=Qwen3-4B-Base, Selection percentage=1%2026.0342.4
Simple-RLFine-tuning base=Qwen2.5-Math-7B, Comparison Group=Comparable Baselines (zero setting or less expert data)2025.0840.7
InstructFine-tuning base=Qwen2.5-Math-7B, Comparison Group=Non-comparable Baselines2025.0839.9
DPO-R1Fine-tuning base=Qwen2.5-Math-7B, Comparison Group=Comparable Baselines (zero setting or less expert data)2025.0838.8
Absolute ZeroBase model=Qwen3-4B-Base2026.0338.5
DPO-VPFine-tuning base=Qwen2.5-Math-7B, Comparison Group=Comparable Baselines (zero setting or less expert data)2025.0838.2
DPO-LoRRFine-tuning base=Qwen2.5-Math-7B, Iteration=iter32025.0837.2
DPO-LoRRFine-tuning base=Qwen2.5-Math-7B, Iteration=iter22025.0837
PRIMEFine-tuning base=Qwen2.5-Math-7B, Comparison Group=Non-comparable Baselines2025.0835.6
S1Fine-tuning base=Qwen2.5-Math-7B, Comparison Group=Comparable Baselines (zero setting or less expert data)2025.0835.1
DPO-LoRRFine-tuning base=Qwen2.5-Math-7B, Iteration=iter12025.0835.1
Qwen3-4B-Base2026.0334.8
LIMOFine-tuning base=Qwen2.5-Math-7B, Comparison Group=Comparable Baselines (zero setting or less expert data)2025.0832.3
PURE-VRFine-tuning base=Qwen2.5-Math-7B, Comparison Group=Comparable Baselines (zero setting or less expert data)2025.0828.1
Qwen2.5Fine-tuning base=Qwen2.5-Math-7B, Comparison Group=Base2025.0824.1