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

Aggregate Model Evaluation on RouterBench subsampled 2500 s

79.1Accuracy

Qwen 7B (Gem)

54.6661.00567.3573.695Jan 29, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
79.1
2026.01
78.3
2026.01
74.7
2026.01
73.2
2026.01
71.6
2026.01
71.3
2026.01
69.6
2026.01
55.6