Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Table Question Answering on WikiTableQuestions OOD
Loading...
83.34
Accuracy
SkillGrad
41.2408
52.1704
63.1
74.0296
May 26, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
SkillGrad
Backbone=GPT-5.4, Init...
2026.05
83.34
SkillGrad
Backbone=GPT-5.4, Init...
2026.05
82.38
Trace2Skill
Backbone=GPT-5.4, Init...
2026.05
81.91
EvoSkill
Backbone=GPT-5.4, Init...
2026.05
80.95
Trace2Skill
Backbone=GPT-5.4, Init...
2026.05
79.05
No Skill
Backbone=GPT-5.4, Init...
2026.05
78.57
Base xlsx Skill
Backbone=GPT-5.4, Init...
2026.05
78.57
EvoSkill
Backbone=GPT-5.4, Init...
2026.05
78.09
Base xlsx Skill
Backbone=GPT-5.4, Init...
2026.05
77.14
SkillGrad
Backbone=GPT-4.1, Init...
2026.05
73.65
Trace2Skill
Backbone=GPT-4.1, Init...
2026.05
60
SkillGrad
Backbone=GPT-4.1, Init...
2026.05
53.81
EvoSkill
Backbone=GPT-4.1, Init...
2026.05
53.33
No Skill
Backbone=GPT-4.1, Init...
2026.05
52.86
Trace2Skill
Backbone=GPT-4.1, Init...
2026.05
51.43
Base xlsx Skill
Backbone=GPT-4.1, Init...
2026.05
48.58
EvoSkill
Backbone=GPT-4.1, Init...
2026.05
43.33
Base xlsx Skill
Backbone=GPT-4.1, Init...
2026.05
42.86
Feedback
Search any
task
Search any
task