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

General Assistant on GAIA (Pass@1 L1/L2/L3)

88.68Pass@1 (L1)

Mem2Evolve

14.11233.47152.8372.189Apr 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
88.6882.5657.6976.31
2026.04
81.1375.5846.1572.73
2026.04
74.2969.0647.667.36
2026.04
35.8524.4219.2326.5
2026.04
30.1915.1211.5418.95
2026.04
30.1916.2819.2321.9
2026.04
28.318.613.4620.4
2026.04
26.4217.4411.5418.47
2026.04
26.4217.4415.3819.75
2026.04
24.5317.4411.5417.84
2026.04
24.5319.7811.5418.62
2026.04
22.6419.7811.5417.99
2026.04
16.9812.797.6912.49