List your company

Language Understanding on MMLU (full)

75.9Macro AccuracyQwen-2.5-7B-Instruct
61.02864.88968.7572.611Sep 8, 2025

Evaluation results

MethodLinks
Qwen-2.5-7B-InstructNumber of shots=10, temperature=02025.0975.9
Qwen-2.5-7B-InstructNumber of shots=50, temperature=02025.0975.8
Qwen-2.5-7BNumber of shots=10, temperature=02025.0975.5
Qwen-2.5-7BNumber of shots=50, temperature=02025.0975.4
MACHINELEARNINGLMNumber of shots=50, temperature=02025.0975.4
MACHINELEARNINGLMNumber of shots=10, temperature=02025.0975.1
Qwen-2.5-7B-InstructNumber of shots=0, temperature=02025.0973.8
Qwen-2.5-7BNumber of shots=0, temperature=02025.0973.5
MACHINELEARNINGLMNumber of shots=0, temperature=02025.0973.2
TabuLa-8BNumber of shots=10, temperature=0, maximum sequence length=8k2025.0965.2
TabuLa-8BNumber of shots=0, temperature=0, maximum sequence length=8k2025.0961.6