List your company

Multiple-choice Question Answering on MMLU-ProX T5

25.2AccuracyCOMPASS-ECDA
23.53623.96824.424.832Apr 22, 2026

Evaluation results

MethodLinks
COMPASS-ECDABackbone=LLaMA-3.1-Instruct-8B, Number of random seeds=32026.0425.2
Full RetrainingBackbone=LLaMA-3.1-Instruct-8B, Number of random seeds=32026.0425.1
Naive Fine-tuningBackbone=LLaMA-3.1-Instruct-8B, Number of random seeds=32026.0424.6
EWCBackbone=LLaMA-3.1-Instruct-8B, Number of random seeds=32026.0424.1
Random RehearsalBackbone=LLaMA-3.1-Instruct-8B, Number of random seeds=32026.0423.6