List your company

Essay Scoring on ASAP-SAS (Prompts 3, 4, 7, 8, 9)

0.661QWK (Prompt 3)Llama3-8B-Inst.
0.55180.580150.60850.63685Jan 8, 2026

Evaluation results

MethodLinks
Llama3-8B-Inst.Assessment=Score + Feedback, Feedback Quality=High Quality (FeedEval)2026.010.6610.610.5510.5950.7290.6290.035
Llama3-8B-Inst.Assessment=Score + Feedback, Feedback Quality=High Quality (GPT-5.1)2026.010.6360.5890.5360.5460.7050.6020.03
Llama3-8B-Inst.Assessment=Score + Feedback, Feedback Quality=Low Quality (FeedEval)2026.010.6170.6040.5210.5630.7040.6020.03
Qwen3-8BAssessment=Score + Feedback, Feedback Quality=High Quality (FeedEval)2026.010.6060.6170.5210.5630.7260.6070.03
Llama3-8B-Inst.Assessment=Score + Feedback, Feedback Quality=Low Quality (GPT-5.1)2026.010.5840.6060.4740.5530.70.5830.025
Qwen3-8BAssessment=Score + Feedback, Feedback Quality=Low Quality (FeedEval)2026.010.5820.5770.4910.5530.7060.5820.035
Qwen3-8BAssessment=Score + Feedback, Feedback Quality=High Quality (GPT-5.1)2026.010.5730.5750.4750.5470.6680.5680.04
Qwen3-8BAssessment=Score Only, Feedback Quality=N/A2026.010.570.5850.4830.5420.6910.5740.027
Qwen3-8BAssessment=Score + Feedback, Feedback Quality=Low Quality (GPT-5.1)2026.010.5680.5770.4580.540.6840.5650.034
Llama3-8B-Inst.Assessment=Score Only, Feedback Quality=N/A2026.010.5560.5510.5340.5270.6340.560.037