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

General Knowledge Evaluation on General-purpose benchmarks average (test)

73.8Accuracy

Qwen3 8B

61.42464.63767.8571.063Feb 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
73.823.5
2026.02
64.827.6
2026.02
64.727.3
2026.02
64.628
2026.02
64.427.3
2026.02
64.427.9
2026.02
64.227.8
2026.02
64.127.1
2026.02
64.127.7
2026.02
6427.5
2026.02
63.826.7
2026.02
61.930.5