Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Language-to-Code Generation on WikiTQ official (dev)
Loading...
70.9
Execution Accuracy
Oracle
46.252
52.651
59.05
65.449
Feb 16, 2023
Execution Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Execution Accuracy
Oracle
generator_model=code-d...
2023.02
70.9
Codex Binder
finetuning=false
2023.02
62.6
LEVER
generator_model=code-d...
2023.02
61.1
TaCube
finetuning=true
2023.02
59.7
Codex SQL
finetuning=false
2023.02
57.6
TaPEX*
finetuning=true
2023.02
57
EP + Voting
generator_model=code-d...
2023.02
50.6
EP + ML
generator_model=code-d...
2023.02
50.1
Codex QA
finetuning=false
2023.02
49.3
ML
generator_model=code-d...
2023.02
48.3
Greedy
generator_model=code-d...
2023.02
47.2
Feedback
Search any
task
Search any
task