Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Question Answering on ARC Easy (Accuracy)

98.2Accuracy

Mistral Small 24B Inst 2501

79.27284.18689.194.014Sep 11, 2024Dec 8, 2024Mar 6, 2025Jun 3, 2025Aug 30, 2025Nov 26, 2025Feb 23, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.01
98.2-0
2026.01
98.2-0
2026.01
98--
2026.01
98--
2026.01
97.8-0
2026.01
97.8-0
2026.01
97.5--
2026.01
97.4--
2026.01
97.3-0.1
2026.01
97.3-0.1
2026.01
97.3--
2026.01
97.3--
2026.01
96.4--
2026.01
96.4--
2026.01
96.2--
2026.01
96.2--
2025.09
94.84--
2025.09
94.73--
2025.09
94.63--
2025.09
94.63--
2025.09
94.58--
2026.01
94.1--
2026.01
94.1--
2025.09
94.05--
2025.09
93.84--
2025.09
93.74--
2026.01
93.2-0
2026.01
93.2-0
2025.09
93.16--
2025.09
92.89--
2026.01
92.1-0.3
2026.01
92.1-0.3
2026.01
92-0.1
2026.01
92-0.1
2026.01
91.9--
2026.01
91.8--
2026.01
91--0.1
2026.01
91--0.1
2026.01
91--0.1
2026.01
91--0.1
2025.05
90.2--
2025.05
90--
2025.05
90--
2026.02
89.58.7-
2026.02
89.5--
2026.02
89.2--
2026.02
89--
2026.02
88.8--
2026.01
88.6-0
2026.01
88.6-0
2026.01
88.5-0.3
2026.01
88.4--0.2
2026.01
88.4--0.2
2026.01
88.3-0.3
2026.01
88.3-0.2
2026.01
88.3-0.1
2026.01
87.9--
2026.01
87.8--
2026.02
87.7--
2026.02
86.9--
2025.09
86.74--
2026.01
86.7-2.7
2025.09
86.53--
2025.09
86.53--
2025.05
86.5--
2025.09
86.32--
2026.02
85.9--
2025.09
85.58--
2025.09
85.21--
2025.09
85.11--
2026.01
84.8-0.3
2025.09
84.79--
2026.01
84.5-0
2025.05
84.4--
2025.09
84.27--
2025.05
84.2--
2025.09
84.06--
2026.01
84--0.1
2026.01
83.59--
2026.02
83.043.7-
2025.07
82.49--
2025.07
82.49--
2026.02
81.8--
2026.02
81.552.21-
2024.09
81.5--
2026.01
81.4--
2026.01
81.4--
2026.02
81--
2026.02
81--
2026.02
80.8--
2024.09
80.8--
2026.02
80.7--
2025.07
80.64--
2025.07
80.6--
2026.02
80.561.22-
2026.01
80.56--
2026.01
80.51--
2026.01
80.43--
2026.02
80.180.84-
2025.05
80--
Showing 100 of 386 rows