Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-SQL on Spider no-easy
Loading...
61.4
Accuracy
SFT
31.76
39.455
47.15
54.845
May 26, 2026
Accuracy
Updated 7d ago
Evaluation Results
Method
Method
Links
Accuracy
SFT
Model=Qwen2.5-7B-Instr...
2026.05
61.4
Base
Model=Qwen2.5-7B-Instr...
2026.05
61.2
RLSTA
Model=Qwen2.5-7B-Instr...
2026.05
59.8
MAIGO
Model=Qwen2.5-7B-Instr...
2026.05
59.6
GRPO
Model=Qwen2.5-7B-Instr...
2026.05
59.4
RLSTA
Model=Qwen2.5-3B-Instr...
2026.05
52
MAIGO
Model=Qwen2.5-3B-Instr...
2026.05
51.9
GRPO
Model=Qwen2.5-3B-Instr...
2026.05
51.7
SFT
Model=Qwen2.5-3B-Instr...
2026.05
50.8
Base
Model=Qwen2.5-3B-Instr...
2026.05
50.7
MAIGO
Model=Qwen2.5-7B-Instr...
2026.05
50
RLSTA
Model=Qwen2.5-7B-Instr...
2026.05
45
MAIGO
Model=Qwen2.5-3B-Instr...
2026.05
44.9
SFT
Model=Qwen2.5-7B-Instr...
2026.05
44.1
GRPO
Model=Qwen2.5-7B-Instr...
2026.05
42.5
Base
Model=Qwen2.5-7B-Instr...
2026.05
42.2
RLSTA
Model=Qwen2.5-3B-Instr...
2026.05
37
SFT
Model=Qwen2.5-3B-Instr...
2026.05
36.6
GRPO
Model=Qwen2.5-3B-Instr...
2026.05
34
Base
Model=Qwen2.5-3B-Instr...
2026.05
32.9
Feedback
Search any
task
Search any
task