Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended Generation on Finance
Loading...
29.19
ROUGE-Lsum
TF-TTCL
22.7212
24.4006
26.08
27.7594
Apr 15, 2026
ROUGE-Lsum
Updated 3d ago
Evaluation Results
Method
Method
Links
ROUGE-Lsum
TF-TTCL
Model=DeepSeek-V3.2
2026.04
29.19
TF-TTCL
Model=Qwen-Plus
2026.04
28.31
Base LLM
Model=Qwen-Plus
2026.04
26.47
TF-GRPO
Model=DeepSeek-V3.2
2026.04
25.8
Base LLM
Model=DeepSeek-V3.2
2026.04
25.78
TF-GRPO
Model=Qwen-Plus
2026.04
25
Chain-of-Thought
Model=DeepSeek-V3.2
2026.04
24.28
Chain-of-Thought
Model=Qwen-Plus
2026.04
22.97
Feedback
Search any
task
Search any
task