List your company

General Reasoning on MMLU-P, ARC-c, and GPQA

52.1MMLU-P ScorePOPO
-2.08411.98326.0540.117Oct 10, 2025Nov 17, 2025Dec 26, 2025Feb 3, 2026Mar 14, 2026Apr 22, 2026May 31, 2026

Evaluation results

MethodLinks
POPOBackbone=DSR-7B, Finetuning=true, Runtime=34h2026.0552.176.325.251.2
DAPOBackbone=DSR-7B, Finetuning=true, Runtime=55h2026.055276.923.450.8
ARPOBackbone=DSR-7B, Finetuning=true, Runtime=31h2026.0551.675.724.450.6
MoPPSBackbone=DSR-7B, Finetuning=true, Runtime=32h2026.0551.676.725.451.2
GRPOBackbone=DSR-7B, Finetuning=true, Runtime=31h2026.0550.975.623.850.1
DSR-7BBackbone=DSR-7B, Finetuning=false2026.0550.576.119.248.6
GRPO + Meta-HintsBackbone=Qwen2.5-7B2025.1050.288.830.456.5
HINTBackbone=Qwen2.5-7B2025.1050.28932.857.3
BREADBackbone=Qwen2.5-7B2025.1049.388.230.255.9
LUFFYBackbone=Qwen2.5-7B2025.1048.88626.853.9
GRPOBackbone=Qwen2.5-7B2025.10488829.455.1
SFTBackbone=Qwen2.5-7B2025.1046.285.125.652.3
VanillaBackbone=Qwen2.5-7B2025.104685.325.652.3
HINTBackbone=LLaMa3.1-8B2025.103975.330.448.2
GRPO + Meta-HintsBackbone=LLaMa3.1-8B2025.1036.474.82846.4
BREADBackbone=Qwen2.5-3B2025.1036.37218.242.2
GRPOBackbone=Qwen2.5-3B2025.1036.274.41642.2
HINTBackbone=Qwen2.5-3B2025.1035.578.820.444.9
GRPO + Meta-HintsBackbone=Qwen2.5-3B2025.103577.61843.5
LUFFYBackbone=Qwen2.5-3B2025.1034.270.215.239.9
BREADBackbone=LLaMa3.1-8B2025.1033.970.427.243.8
LUFFYBackbone=LLaMa3.1-8B2025.1033.366.825.541.9
GRPOBackbone=LLaMa3.1-8B2025.10337026.443.1
SFTBackbone=Qwen2.5-3B2025.103246.41129.8
VanillaBackbone=Qwen2.5-3B2025.1028.844.811.428.3
SFTBackbone=LLaMa3.1-8B2025.1026.552.418.332.4
GRESOBackbone=DSR-1.5B, Finetuning=true, Runtime=27h2026.0524.746.726.432.6
DAPOBackbone=DSR-1.5B, Finetuning=true, Runtime=30h2026.0524.546.726.832.7
POPOBackbone=DSR-1.5B, Finetuning=true, Runtime=16h2026.0522.645.930.332.9
ReMixBackbone=DSR-1.5B, Finetuning=true, Runtime=16h2026.0522.545.327.731.8
GRPOBackbone=DSR-1.5B, Finetuning=true, Runtime=16h2026.0522.345.427.531.7
ARPOBackbone=DSR-1.5B, Finetuning=true, Runtime=16h2026.0522.345.326.331.3
REPOBackbone=DSR-1.5B, Finetuning=true, Runtime=19h2026.0521.944.927.431.4
MoPPSBackbone=DSR-1.5B, Finetuning=true, Runtime=17h2026.0521.444.627.531.2
RRBackbone=DSR-1.5B, Finetuning=true, Runtime=14h2026.0521.245.427.131.2
DSR-1.5BBackbone=DSR-1.5B, Finetuning=false2026.0521.142.22328.8
VanillaBackbone=LLaMa3.1-8B2025.100000