Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Question Answering on SimpleQA (Acc, BAS, ECE, AURC)

32.9Accuracy

Grok-3

1.30489.507417.7125.9126Apr 3, 2026Apr 10, 2026Apr 18, 2026Apr 26, 2026May 4, 2026May 12, 2026May 20, 2026
Updated 13d ago

Evaluation Results

MethodLinks
2026.04
32.9-0.960.165
2026.04
29.9-0.4852.760
2026.04
28.7-1.0964.268
2026.04
21.4-1.370.576
2026.04
20.2-1.2668.874
2026.04
19.6-0.8660.871
2026.04
19.4-2.9768.175
2026.04
17.6-0.634975
2026.04
12-0.6658.577
2026.04
10.9-1.6382.689
2026.04
8.9-3.8684.289
2026.04
8.5-3.6384.191
2026.05
6.45---
2026.05
6.38---
5.2---
2026.05
4.46---
2026.05
4.27---
2026.05
4.21---
4.09---
2026.05
2.52---