List your company

Instruction Following on MT-Bench (test) using ROUGE/BLEU

28.4ROUGE-1 ScoreAP-1k-TACOS
18.20820.85423.526.146Jul 4, 2025

Evaluation results

MethodLinks
AP-1k-TACOS2025.0728.410.424.38.8
AP-1k-Longest2025.0726.110.219.92.6
Alpaca-52k2025.0722.98.618.72.6
AP-1k-AG2025.0718.67.616.65