List your company

Pairwise Classification on 20 system prompts

97.1TF-IDF AccuracyGPT-4.1-NANO
76.71682.00887.392.592Jun 21, 2026

Evaluation results

MethodLinks
GPT-4.1-NANOModel=GPT-4.1-NANO2026.0697.1-0.358-0.156
GPT-4O-MINIModel=GPT-4O-MINI2026.0696.4-0.302-0.17
QWEN-4B-INSTRUCTModel=QWEN-4B-INSTRUCT2026.0691.4-0.411-0.328
LLAMA-3.1-8B-INSTRUCTModel=LLAMA-3.1-8B-INSTRUCT2026.0680.9-0.342-0.316
GPT-OSS-120BModel=GPT-OSS-120B2026.0679.3-0.128-0.128
GPT-OSS-20BModel=GPT-OSS-20B2026.0677.5-0.162-0.142