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

Instruction Following on IFEval (test)

84.8IFEval Score

SPOT

16.78434.44252.169.758Apr 17, 2025Jun 9, 2025Aug 1, 2025Sep 23, 2025Nov 15, 2025Jan 7, 2026Mar 2, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.03
84.8---
2026.03
83---
2026.03
81.5---
2026.02
81.17---
2026.03
80---
2026.03
79.6---
2026.03
73.6---
2026.03
73.2---
2026.03
71.2---
2026.03
68.6---
2026.02
64.51---
2026.02
63.96---
2026.02
63.96---
2026.02
63.03---
2026.03
62.1---
2026.02
53.68---
2026.02
53.21---
2026.02
47.91---
2025.05
44.55---
2025.05
44.55---
2025.05
44.18---
2026.02
43.54---
2025.05
42.51---
2026.02
41.72---
2025.05
41.22---
2026.02
39.84---
2025.05
39.37---
2026.02
36---
2026.02
35.49---
2025.04
35.3---
2025.05
35.3---
2025.04
33.64---
2025.04
33.64---
2026.02
33.1---
2026.02
32.97---
2025.04
32.9---
2026.02
32.27---
2025.04
29.21---
2025.04
29.02---
2025.05
29.02---
2026.02
29---
2025.04
28.84---
2026.02
28.1---
2026.02
26.24---
2026.02
22---
2026.02
21.4---
2026.02
20.9---
2026.02
20.9---
2026.02
20.8---
2026.02
20.7---
2026.02
20.7---
2026.02
20.6---
2026.02
20.5---
2026.02
19.8---
2026.02
19.4---
2025.04
-19.04--
2025.04
-33.64--
2025.04
-25.32--
2025.04
-30.87--
2025.04
-27.91--
2025.04
-30.87--
2025.04
-20.52--
2025.04
-31.79--
2025.04
-27.36--
2025.04
-29.76--
2025.04
-29.39--
2025.04
-29.76--
2025.04
-11.46--
2025.04
-48.8--
2025.04
-34.38--
2025.04
-42.33--
2025.04
-41.4--
2025.04
-45.84--
2026.02
-61.3--
2026.02
-62.46--
2026.02
-63.27--
2026.02
-77.35--
2026.02
-80.5--
2025.07
-17.22--
2025.07
-17.17--
2025.07
-17.08--
2025.07
-16.44--
2025.07
-22.82--
2025.07
-22.76--
2025.07
-23.18--
2025.07
-21.83--
2025.07
-21.24--
2025.07
-20.92--
2025.07
-22.24--
2025.07
-21.7--
2025.07
-20.72--
2025.07
-20.89--
2025.07
-20.37--
2025.07
-21.14--
2025.07
-35.08--
2025.07
-33.98--
2025.07
-34.82--
2025.07
-35.74--
2026.04
-62.96-34
2026.04
--62.48-