List your company

General Performance Evaluation on Performance Bench Aggregate

82.49Average ScoreDeepSeek-R1-Distill-Qwen-32B (Reasoning)
64.747669.353873.9678.5662Jan 9, 2026

Evaluation results

MethodLinks
DeepSeek-R1-Distill-Qwen-32B (Reasoning)Model Family=Qwen2.5-32B2026.0182.49
ReasonAnyModel Family=Qwen2.5-32B2026.0178.54
TIESModel Family=Qwen2.5-32B2026.0169.17
DAREModel Family=Qwen2.5-32B2026.0168.45
Qwen2.5-32B-Instruct (Safety)Model Family=Qwen2.5-32B2026.0168.25
Task ArithmeticModel Family=Qwen2.5-32B2026.0167.82
FuseLLMModel Family=Qwen2.5-32B2026.0166.65
LinearModel Family=Qwen2.5-32B2026.0165.92
LEDModel Family=Qwen2.5-32B2026.0165.43