List your company

Essay Scoring on ASAP++ (five-fold averaged results)

0.712Overall ScoreQwen3-8B
0.430160.503330.57650.64967Jan 8, 2026

Evaluation results

MethodLinks
Qwen3-8BAssessment=Score Only, Feedback Quality=None2026.010.7120.6930.6960.6770.710.6760.6740.6810.6840.689
Qwen3-8BAssessment=Score + Feedback, Feedback Quality=High Quality (FeedEval)2026.010.6610.6990.7090.6830.7190.6730.6940.6880.6980.692
Qwen3-8BAssessment=Score + Feedback, Feedback Quality=High Quality (GPT-5.1)2026.010.6590.6830.6990.6730.7020.6710.6820.6780.6830.681
Qwen3-8BAssessment=Score + Feedback, Feedback Quality=Low Quality (FeedEval)2026.010.6570.6820.6970.6730.6940.6710.6560.6740.6840.676
Qwen3-8BAssessment=Score + Feedback, Feedback Quality=Low Quality (GPT-5.1)2026.010.6520.6940.7030.6720.7040.6670.6840.6680.6710.679
Llama3-8B-InstAssessment=Score Only, Feedback Quality=None2026.010.4760.5460.5850.540.580.580.4820.4910.4760.528
Llama3-8B-InstAssessment=Score + Feedback, Feedback Quality=High Quality (FeedEval)2026.010.4510.6010.6120.5870.6170.5750.5980.5980.5790.58
Llama3-8B-InstAssessment=Score + Feedback, Feedback Quality=Low Quality (FeedEval)2026.010.4490.5760.6050.5750.6020.570.5560.5630.5580.562
Llama3-8B-InstAssessment=Score + Feedback, Feedback Quality=Low Quality (GPT-5.1)2026.010.4460.5580.6050.5810.6130.5540.5650.5720.5470.56
Llama3-8B-InstAssessment=Score + Feedback, Feedback Quality=High Quality (GPT-5.1)2026.010.4410.5930.6020.5840.6110.5380.5320.5610.5570.558