List your company

Pairwise Discrimination on Management and Economics Research Pitch Pairs shared pairwise subset (test)

78.67Distance 1 AccuracySFT GPT-4.1
68.2770.9773.6776.37Mar 17, 2026

Evaluation results

MethodLinks
SFT GPT-4.1task=label-free2026.0378.67899284.33
GPT-5.2 Hightask=label-free2026.0369.33859478.67
GPT-4.1 (baseline)task=label-free2026.0369.33799076
Gemini 3.1 Protask=label-free2026.0368.67868677.33