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

Long-context Understanding on Infini-Bench (test)

17.26Math Score

SHAREDLLM

2.27366.164310.05513.9457Mar 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
17.2636.9997.31
2026.03
16.1229.865.73
2026.03
15.5637.1795.18
2026.03
14.7228.7162.37
2026.03
13.8233.6582.79
2026.03
12.1432.0580.58
2026.03
12.0325.2816.13
2026.03
11.2735.8152.85
2026.03
9.9528.832.31
2026.03
9.9324.1749.85
2026.03
8.8126.253.66
2026.03
8.2921.1641.1
2026.03
7.8217.7343.51
2026.03
7.2618.849.75
2026.03
6.2325.744.87
2026.03
632.315.23
2026.03
5.4121.1912.48
2026.03
4.7316.1815.71
2026.03
3.8119.7714.98
2026.03
3.5720.655.41
2026.03
2.8522.791.85