WildTableBench - Numerical: leaderboard
Accuracy in percent on the numerical category: basic arithmetic, ranking, conditional aggregates and multi-step conditional computation, free-form questions about real-world table images collected from the web (WildTableBench, 2026), answers judged against the reference by GPT-5.2. Higher is better.
Metric: Accuracy (%) on the Numerical question category (C2, question-weighted over its subtypes), 928 human-verified questions over 402 real-world table images, free-form answers judged by GPT-5.2 against the reference answer, high reasoning effort where configurable; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 21 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Pro | 71.9 | #146 | |
| 2 | Kimi K2.5 | Thinking | 50.6 | #272 |
| 3 | Gemini 3 Flash | 49.7 | #180 | |
| 4 | Claude Opus 4.6 | High | 46.7 | #114 |
| 5 | GPT-5.2 | High | 45.8 | #190 |
| 6 | Seed 2.0 Pro | High | 44.9 | #226 |
| 7 | Claude Sonnet 4.6 | High | 34.1 | #179 |
| 8 | Qwen 3 VL 235B A22B (Thinking) | 33.5 | #462 | |
| 9 | Qwen 3 VL 32B (Thinking) | 27.8 | #577 | |
| 10 | Qwen 3 VL 235B A22B Instruct | 26.6 | #541 | |
| 11 | GPT-5 Mini | High | 24.3 | #373 |
| 12 | GLM-4.6V | 24 | #721 | |
| 13 | Qwen 3 VL 32B Instruct | 22.5 | #607 | |
| 14 | Qwen 3 VL 8B (Thinking) | 15 | #924 | |
| 15 | O3 | High | 11.4 | #242 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=wildtablebench-numerical · How It Works · Data refreshed daily, snapshot 2026-11-22.