Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-form generation on WritingBench
Loading...
5.1
Score
Large
4.164
4.407
4.65
4.893
Mar 27, 2026
Score
#Steps
Speedup (×)
Updated 20d ago
Evaluation Results
Method
Method
Links
Score
#Steps
Speedup (×)
Large
Agent=DDV2
2026.03
5.1
9.1
1
AgentCollab
Agent=DDV2
2026.03
5
9.59
2.43
RouteLLM
Agent=DDV2
2026.03
4.7
10.27
2.21
FrugalGPT
Agent=DDV2
2026.03
4.5
12.22
1.94
Small
Agent=DDV2
2026.03
4.4
17.25
3.2
Random
Agent=DDV2
2026.03
4.2
13.1
1.29
Feedback
Search any
task
Search any
task