WildTableBench - Multi-step Conditional: leaderboard
A WildTableBench (2026) subtype on a multi-step numeric result under several nested conditions, asked about real-world table images from the web. Accuracy in percent, free-form answers judged against the reference by GPT-5.2; higher is better.
Metric: Accuracy (%) on the Multi-step Conditional subtype (C2-M), 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 | 66.4 | #146 | |
| 2 | Gemini 3 Flash | 51 | #180 | |
| 3 | GPT-5.2 | High | 49 | #190 |
| 4 | Kimi K2.5 | Thinking | 45.5 | #272 |
| 5 | Claude Opus 4.6 | High | 45.5 | #114 |
| 6 | Seed 2.0 Pro | High | 42 | #226 |
| 7 | Claude Sonnet 4.6 | High | 34.3 | #179 |
| 8 | Qwen 3 VL 235B A22B (Thinking) | 32.2 | #462 | |
| 9 | Qwen 3 VL 235B A22B Instruct | 25.2 | #541 | |
| 10 | Qwen 3 VL 32B Instruct | 23.8 | #607 | |
| 11 | GLM-4.6V | 23.8 | #721 | |
| 12 | Qwen 3 VL 32B (Thinking) | 23.8 | #577 | |
| 13 | GPT-5 Mini | High | 21.7 | #373 |
| 14 | O3 | High | 14 | #242 |
| 15 | Qwen 3 VL 8B (Thinking) | 8.4 | #924 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=wildtablebench-multi-step-conditional · How It Works · Data refreshed daily, snapshot 2026-11-22.