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

Logical Reasoning on LogicNLI

63.55Accuracy

Ours

22.93833.481544.02554.5685Oct 20, 2025Nov 28, 2025Jan 6, 2026Feb 14, 2026Mar 25, 2026May 3, 2026Jun 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
63.5500.04741,321.94----
2026.05
63.55-47.391,321.940---
2025.10
63.442.0618.45-----
2025.10
62.942.069.9-----
2025.10
62.742.0638.5-----
2026.05
62358.50.05832,049.53----
2026.05
62-58.312,049.53358.5---
2026.05
61.55358.50.0462,049.59----
2026.05
61.55-45.952,049.59358.5---
2025.10
61.442.0630.47-----
2026.05
61.2500.03821,336.44----
2026.05
61.25-38.181,336.440---
2025.10
60.342.060.72-----
2025.10
59.142.0621.17-----
2026.05
53.7336.50.13154,177.9----
2026.05
53.7-131.494,177.9336.5---
2025.10
49.2350.0846.92-----
2026.06
48.9----462.599129.38591.985
2026.06
47.4----432.131132.102564.248
2026.05
45.05336.50.1034,199.92----
2026.05
45.05-102.954,199.92336.5---
2026.06
44.5----473.971121.277595.263
2026.04
32.1-------
2026.04
30.8-------
2026.04
25.4-------
2026.04
24.5-------