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

Reasoning on Multilingual ARC-E 8 Seen Languages

85.7ARC-E Accuracy

Base

52.9461.44569.9578.455Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
85.7
2026.06
85.4
2026.06
85.3
2026.06
85.2
2026.06
84.8
2026.06
81.7
2026.06
80.7
2026.06
80.2
2026.06
80.1
2026.06
78.9
2026.06
64.3
2026.06
63.9
2026.06
63.9
2026.06
63.7
2026.06
63.7
2026.06
63.5
2026.06
61.5
2026.06
61.3
2026.06
60
2026.06
54.2