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

General Capability on BBH, GSM8K, MMLU, TruthfulQA, HumanEval, MBPP

26.77Average Score

ADG

Updated 4d ago

Evaluation Results

Method	Links
ADG 2026.04		26.77
ADG 2026.04		26.23
ADG 2026.04		26.13
SuperFiltering 2026.04		26.03
ZIP 2026.04		25.95
SelectIT 2026.04		25.85
ZIP 2026.04		25.61
Rethinking 2026.04		25.57
Rethinking 2026.04		25.45
IFD 2026.04		25.33
SelectIT 2026.04		25.32
SCAR 2026.04		25.14
MIG 2026.04		25.06
Random 2026.04		25.01
SCAR 2026.04		24.99
SuperFiltering 2026.04		24.99
Random 2026.04		24.95
Rethinking 2026.04		24.8
ZIP 2026.04		24.79
IFD 2026.04		24.74
SCAR 2026.04		24.74
All Data 2026.04		24.73
SuperFiltering 2026.04		24.73
SelectIT 2026.04		24.68
MIG 2026.04		24.67
Random 2026.04		24.55
IFD 2026.04		24.52
All Data 2026.04		24.21
MIG 2026.04		24.2
All Data 2026.04		23.12