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

Text Generation on Spec-Bench Overall

2.33SD Score

SpecBound

1.25881.53691.8152.0931Apr 14, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
2.33
2026.04
2.16
2026.04
2.15
2026.04
1.93
2026.04
1.81
2026.04
1.81
2026.04
1.71
2026.04
1.7
2026.04
1.52
2026.04
1.5
2026.04
1.47
2026.04
1.47
2026.04
1.46
2026.04
1.45
2026.04
1.44
2026.04
1.39
2026.04
1.37
2026.04
1.35
2026.04
1.33
2026.04
1.31
2026.04
1.3