List your company
ResearchFormerly WizWand

Mathematical Reasoning on Math Benchmarks

76.9Accuracy (%)R1-Distill-Qwen3-8B
54.43660.26866.171.932Sep 29, 2025
Updated 7mo ago

Evaluation results

MethodLinks
R1-Distill-Qwen3-8BContext Length=2048, Monitoring Strategy=None2025.0976.902,048100
R1-Distill-Qwen3-8BContext Length=4096, Monitoring Strategy=None2025.0976.904,096100
BoostAbstentionBase Model=R1-Distill-Qwen3-8B, Context Length=20482025.0976.902,048100
BoostAbstentionBase Model=R1-Distill-Qwen3-8B, Context Length=40962025.0976.904,096100
GPT-oss-20BContext Length=2048, Monitoring Strategy=None2025.0974.602,02997
GPT-oss-20BContext Length=4096, Monitoring Strategy=None2025.0974.604,01597
BoostAbstentionBase Model=GPT-oss-20B, Context Length=20482025.0974.602,02397
BoostAbstentionBase Model=GPT-oss-20B, Context Length=40962025.0974.603,93384.8
MonitorexpressBase Model=GPT-oss-20B, Context Length=20482025.0974.61001,13521.2
MonitorexpressBase Model=GPT-oss-20B, Context Length=40962025.0974.61001,49915.2
MonitorexpressBase Model=R1-Distill-Qwen3-8B, Context Length=20482025.0974.663.31,45540
MonitorexpressBase Model=R1-Distill-Qwen3-8B, Context Length=40962025.0974.663.32,55130
MonitorhiddenBase Model=R1-Distill-Qwen3-8B, Context Length=20482025.0973.897.978722.2
MonitorhiddenBase Model=R1-Distill-Qwen3-8B, Context Length=40962025.0973.897.91,2430
MonitorhiddenBase Model=GPT-oss-20B, Context Length=20482025.0973.798.91,78478.4
MonitorhiddenBase Model=GPT-oss-20B, Context Length=40962025.0973.798.93,3175.4
QwQ-32BContext Length=2048, Monitoring Strategy=None2025.0971.502,048100
QwQ-32BContext Length=4096, Monitoring Strategy=None2025.0971.504,096100
BoostAbstentionBase Model=QwQ-32B, Context Length=20482025.0971.502,048100
BoostAbstentionBase Model=QwQ-32B, Context Length=40962025.0971.504,096100
MonitorexpressBase Model=QwQ-32B, Context Length=20482025.0971.51001,16432.4
MonitorexpressBase Model=QwQ-32B, Context Length=40962025.0971.51001,82832.4
MonitorhiddenBase Model=QwQ-32B, Context Length=20482025.0971.596.92620
MonitorhiddenBase Model=QwQ-32B, Context Length=40962025.0971.596.92620
R1-Distill-Qwen-32BContext Length=2048, Monitoring Strategy=None2025.0956.202,048100
R1-Distill-Qwen-32BContext Length=4095, Monitoring Strategy=None2025.0956.204,09597.4
BoostAbstentionBase Model=R1-Distill-Qwen-32B, Context Length=20482025.0956.202,00594.7
BoostAbstentionBase Model=R1-Distill-Qwen-32B, Context Length=40962025.0956.203,90391.2
MonitorexpressBase Model=R1-Distill-Qwen-32B, Context Length=20482025.0956.21008010
MonitorexpressBase Model=R1-Distill-Qwen-32B, Context Length=40962025.0956.21008010
MonitorhiddenBase Model=R1-Distill-Qwen-32B, Context Length=20482025.0955.3974575.3
MonitorhiddenBase Model=R1-Distill-Qwen-32B, Context Length=40962025.0955.3975655.3