Overall Spreadsheet Performance on SpreadsheetBench and WikiTableQuestions Combined
58.32Average ScoreSkillCAT
Evaluation Results
| Method | Links | |
|---|---|---|
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Deepening2026.06 | 58.32 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Deepening2026.06 | 56.44 | |
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 55.88 | |
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Creation2026.06 | 53.54 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 53.23 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Deepening2026.06 | 49.17 | |
| No-SkillSkill Author=Qwen3.5-35B-A3B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 46.92 | |
| No-SkillSkill Author=Qwen3.5-122B-A10B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 46.92 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Creation2026.06 | 46.52 | |
| Human-WrittenSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Deepening2026.06 | 44.09 | |
| Human-WrittenSkill Author=Qwen3.5-35B-A3B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 39.57 | |
| Human-WrittenSkill Author=Qwen3.5-122B-A10B, Skill User=gemma-4-31B-it, Setting=Deepening2026.06 | 39.57 | |
| SkillCATSkill Author=Qwen3.5-35B-A3B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 33.52 | |
| SkillCATSkill Author=Qwen3.5-122B-A10B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 33.06 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Creation2026.06 | 31.46 | |
| Human-WrittenSkill Author=Qwen3.5-35B-A3B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 28.3 | |
| Human-WrittenSkill Author=Qwen3.5-122B-A10B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 28.3 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Deepening2026.06 | 26.36 | |
| ParametricSkill Author=Qwen3.5-122B-A10B, Skill User=Qwen3.5-122B-A10B, Setting=Creation2026.06 | 26 | |
| Trace2Skill +Comb.Skill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Creation2026.06 | 20.34 | |
| No-SkillSkill Author=Qwen3.5-35B-A3B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 18.8 | |
| No-SkillSkill Author=Qwen3.5-122B-A10B, Skill User=gpt-5.4-mini, Setting=Deepening2026.06 | 18.8 | |
| ParametricSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Creation2026.06 | 14.47 | |
| Human-WrittenSkill Author=Qwen3.5-35B-A3B, Skill User=Qwen3.5-35B-A3B, Setting=Deepening2026.06 | 8.77 |