List your company

Math Reasoning on Math Reasoning Long Q, Long A (test)

0.65Pass@1GEMMA2-9B-IT
0.24960.353550.45750.56145Feb 2, 2026

Evaluation results

MethodLinks
GEMMA2-9B-ITWatermark=None2026.020.65——
WorldCupBackbone=GEMMA2-9B-IT, k=12026.020.630.6760.659
MPACBackbone=GEMMA2-9B-IT2026.020.6250.670.67
WorldCupBackbone=GEMMA2-9B-IT, k=22026.020.60.6780.755
BiMarkBackbone=GEMMA2-9B-IT2026.020.590.6760.706
LLAMA3.1-8B-ITWatermark=None2026.020.5——
WorldCupBackbone=LLAMA3.1-8B-IT, k=12026.020.4680.8140.917
WorldCupBackbone=LLAMA3.1-8B-IT, k=22026.020.4450.8920.947
BiMarkBackbone=LLAMA3.1-8B-IT2026.020.420.8680.922
WorldCupBackbone=MINISTRAL-8B-IT, k=12026.020.3550.7770.854
MPACBackbone=LLAMA3.1-8B-IT2026.020.3430.8560.927
MINISTRAL-8B-ITWatermark=None2026.020.34——
WorldCupBackbone=MINISTRAL-8B-IT, k=22026.020.3150.8980.953
BiMarkBackbone=MINISTRAL-8B-IT2026.020.310.7670.877
MPACBackbone=MINISTRAL-8B-IT2026.020.2650.7850.879