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

Zero-shot Evaluation Suite (ARC, BOOLQ, PIQA, WINO)

77.28Average Score

FP

37.364847.727458.0968.4526May 29, 2025Jul 29, 2025Sep 29, 2025Nov 30, 2025Jan 31, 2026Apr 3, 2026Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
77.28-----
2026.05
71.48-----
2025.05
70.12-----
2026.05
70.04-----
2025.05
69.82-----
2025.05
69.5-----
2025.05
69.47-----
2025.05
69.23-----
2025.05
68.88-----
2025.05
68.42-----
2025.05
67.69-----
2025.05
67.67-----
2025.05
67.64-----
2025.05
67.59-----
2025.05
67.54-----
2025.05
67.46-----
2025.05
67.42-----
2025.05
66.99-----
2025.05
66.94-----
2026.05
66.78-----
2025.05
66.38-----
2025.05
66.26-----
2025.05
66.11-----
2025.05
65.44-----
2026.06
50.05-----
2026.06
48.8-----
2026.06
47.45-----
2026.06
45.39-----
2026.05
38.9-----
2024.06
-60.586.985.382.480.3
2024.06
-3567.384.771.976.7
2024.06
-56.183.985.881.380.6
2024.06
-31.136.685.758.876.4
2024.06
-48.677.88577.879.7
2024.06
-18.332.282.154.768.9
2024.06
-2835.283.657.172.6
2024.06
-50.280.18179.772.9
2024.06
-50.279.781.379.773.1
2024.06
-50.279.679.579.473.4
2024.06
-46.477.479.977.972.9
2024.06
-49.279.38079.274.5
2024.06
-39.272.976.675.668.2
2024.06
-44.275.276.777.670.7