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

Instruction Following on IFEval

95IFEval Accuracy

Qwen3.5-27B

81.06484.68288.391.918Apr 23, 2025Jun 21, 2025Aug 19, 2025Oct 17, 2025Dec 15, 2025Feb 12, 2026Apr 13, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.04
95---------------------------
2026.04
92.8---------------------------
2026.03
91.2---------------------------
2026.03
91.1---------------------------
2026.03
90.4---------------------------
2026.01
90.3---------------------------
2026.01
89.8---------------------------
2026.04
89.7---------------------------
2026.04
89.6---------------------------
2026.01
89.3---------------------------
2025.12
89.28---------------------------
2025.12
88.72---------------------------
2025.12
88.54---------------------------
2025.12
88.54---------------------------
2025.12
88.54---------------------------
2025.12
88.35---------------------------
2026.04
88.2---------------------------
2026.02
88.17---------------------------
2026.04
88.17---------------------------
2025.12
87.99---------------------------
2026.01
87.8---------------------------
2026.03
87.8---------------------------
2025.04
87.7---------------------------
2026.01
87.5---------------------------
2025.12
87.25---------------------------
2026.01
87.2---------------------------
2026.01
86.9---------------------------
2026.02
86.86---------------0.875.47----------
2026.02
86.57---------------------------
2026.03
86.51---------------------------
2026.02
86.37---------------------------
2026.04
86.32---------------------------
2026.04
86.32---------------------------
2026.04
86.32---------------------------
2026.01
86.2---------------------------
2026.02
86.17---------------0.996.34----------
2025.12
86.14---------------------------
2025.05
86---------------------------
2026.04
85.95---------------------------
2026.02
85.9---------------------------
2025.12
85.77---------------------------
2025.11
85.62---------------------------
2026.02
85.6---------------14.12----------
2026.03
85.58---------------------------
2026.02
85.4---------------------------
2026.04
85.4---------------------------
2026.04
85.39---------------------------
2026.02
85.32---------------------------
2026.03
85.32---------------------------
2026.02
85.24---------------1.14.48----------
2025.12
85.21---------------------------
2026.03
85.21---------------------------
2025.05
85---------------------------
2025.05
85---------------------------
84.77---------------------------
2026.03
84.76---------------------------
2026.04
84.73---------------------------
2026.04
84.7---------------------------
2026.04
84.7---------------------------
2026.04
84.7---------------------------
2026.04
84.7---------------------------
2026.04
84.7---------------------------
2026.04
84.7---------------------------
2026.04
84.5---------------------------
2026.03
84.45---------------------------
2026.03
84.45---------------------------
2026.03
84.29---------------------------
2026.02
84.2---------------------------
2026.03
84.07---------------------------
2026.01
84---------------------------
2025.05
84---------------------------
2025.12
83.92---------------------------
2026.01
83.9---------------------------
2025.04
83.9---------------------------
2026.03
83.73---------------------------
2026.02
83.7---------------------------
2026.01
83.6---------------------------
2026.04
83.6---------------------------
2026.03
83.55---------------------------
2025.12
83.36---------------------------
2026.04
83.2---------------------------
2026.01
83---------------------------
2026.02
83---------------------------
2025.05
83---------------------------
2026.03
82.99---------------------------
2026.02
82.8---------------------------
2026.02
82.8---------------------------
2026.03
82.8---------------------------
2026.04
82.8---------------------------
2026.03
82.63---------------------------
2026.04
82.6---------------------------
2026.02
82.31---------------0.724.04----------
2026.02
82.25---------------------------
2025.05
82---------------------------
2025.05
82---------------------------
2026.02
81.9---------------------------
2026.03
81.9---------------------------
2026.04
81.8---------------------------
2026.02
81.7---------------------------
2026.02
81.6---------------------------
Showing 100 of 1402 rows
...