Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-table Reasoning on BIRD 3-table
Loading...
56.25
Accuracy
CPO
17.25
27.375
37.5
47.625
Jun 3, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
CPO
Model=Qwen3-14B
2026.06
56.25
CPO
Model=Llama-3.1-8B
2026.06
56.25
Q&A SFT
Model=Qwen3-14B
2026.06
50
Trace SFT
Model=Qwen3-14B
2026.06
50
CPO
Model=Mistral-8B
2026.06
43.75
Trace SFT
Model=Llama-3.1-8B
2026.06
43.75
Q&A SFT
Model=Mistral-8B
2026.06
31.25
Q&A SFT
Model=Llama-3.1-8B
2026.06
31.25
Trace SFT
Model=Mistral-8B
2026.06
18.75
Feedback
Search any
task
Search any
task