Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multiple Choice Question Answering on ARC Challenge (Non-generative Acc)

0.6451Non-generative Accuracy

BF16

0.2154760.3270130.438550.550087Dec 5, 2025
Updated 3d ago

Evaluation Results

MethodLinks
2025.12
0.6451
2025.12
0.6399
2025.12
0.628
2025.12
0.6254
2025.12
0.6203
2025.12
0.6195
2025.12
0.6101
2025.12
0.5998
2025.12
0.5989
2025.12
0.5964
2025.12
0.558
2025.12
0.5546
2025.12
0.5538
2025.12
0.5375
2025.12
0.5341
2025.12
0.5315
2025.12
0.5273
2025.12
0.5213
2025.12
0.5213
2025.12
0.5196
2025.12
0.5178
2025.12
0.4948
2025.12
0.494
2025.12
0.4872
2025.12
0.4795
2025.12
0.4761
2025.12
0.4744
2025.12
0.4692
2025.12
0.4035
2025.12
0.3797
2025.12
0.372
2025.12
0.3174
2025.12
0.2521
2025.12
0.244
2025.12
0.2423
2025.12
0.232