TableGPT2-7B: benchmark results
Provider: Other.
Aggregate Rating 1503 ± 49, rank #2294 of 10916 rated models, from 5 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| TabVerse - QA (Markdown Text) | 42.14 | Exact-match accuracy (%) answering table questions from Mark | 43.8 |
| TabVerse - QA (HTML Text) | 44.43 | Exact-match accuracy (%) answering table questions from HTML | 37.5 |
| TabVerse - QA (LaTeX Text) | 41.57 | Exact-match accuracy (%) answering table questions from LaTe | 37.5 |
| DataGovBench - Table QA | 5.7 | Question-set accuracy (%; 211 simple and decomposable questi | 22.2 |
| BIRD-Python - SQL | 34.03 | LLM-validated execution accuracy (%; generated SQL executed | 16.7 |
Interactive version: theaggregate.ai/model?slug=tablegpt2-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.