Out-of-Distribution Table Question Answering on WikiTableQuestions (WikiTQ)
84.47WikiTQ AccuracySkillCAT
Evaluation Results
| Method | Links | |
|---|---|---|
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Deepening2026.06 | 84.47 | |
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Creation2026.06 | 84.47 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Deepening2026.06 | 81.55 | |
| No-SkillSkill Author=Qwen3.5-35B-A3B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 79.61 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 79.61 | |
| No-SkillSkill Author=Qwen3.5-122B-A10B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 79.61 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Deepening2026.06 | 79.24 | |
| Human-WrittenSkill Author=Qwen3.5-35B-A3B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 78.64 | |
| Human-WrittenSkill Author=Qwen3.5-122B-A10B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 78.64 | |
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 76.7 | |
| Human-WrittenSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Deepening2026.06 | 74.68 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Creation2026.06 | 72.82 | |
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 66.02 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 61.17 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Creation2026.06 | 56.05 | |
| Human-WrittenSkill Author=Qwen3.5-35B-A3B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 54.37 | |
| Human-WrittenSkill Author=Qwen3.5-122B-A10B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 54.37 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Deepening2026.06 | 51.22 | |
| No-SkillSkill Author=Qwen3.5-35B-A3B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 45.63 | |
| No-SkillSkill Author=Qwen3.5-122B-A10B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 45.63 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Creation2026.06 | 38.14 | |
| ParametricSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Creation2026.06 | 23.73 | |
| ParametricSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Creation2026.06 | 20.14 | |
| Human-WrittenSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Deepening2026.06 | 9.02 |