# Symbolic Chain of Thought Reasoning on TableBench Source: [Symbolic Chain of Thought Reasoning on TableBench]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:02:19.020Z Evaluation of model performance on the TableBench dataset specifically for Symbolic Chain of Thought Reasoning tasks, measured by Rge. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Symbolic Chain of Thought Reasoning | | Dataset (including any stated split) | TableBench | | Metric | Rge | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 13 of 13 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Rge](): Lower is better; unit: SCALAR. ## Recorded results | Method | Rge | Result date | Report paper | | --- | --- | --- | --- | | TableLLM | 1.99 | Not recorded | 694b737b53fdd5c3617399cd | | Llama-3.1-8B | 21.94 | Not recorded | 694b737b53fdd5c3617399cd | | Table-R1-Zero-7B | 28.89 | Not recorded | 694b737b53fdd5c3617399cd | | TableGPT2-7B | 40.7 | Not recorded | 694b737b53fdd5c3617399cd | | GPT-4o | 41.43 | Not recorded | 694b737b53fdd5c3617399cd | | Qwen3-8B | 41.86 | Not recorded | 694b737b53fdd5c3617399cd | | Qwen-Plus | 44.06 | Not recorded | 694b737b53fdd5c3617399cd | | QwQ-32B | 44.84 | Not recorded | 694b737b53fdd5c3617399cd | | Qwen3-72B | 45.68 | Not recorded | 694b737b53fdd5c3617399cd | | Qwen3-14B | 47.36 | Not recorded | 694b737b53fdd5c3617399cd | | Qwen3-32B | 47.47 | Not recorded | 694b737b53fdd5c3617399cd | | TableGPT-R1-8B | 49.53 | Not recorded | 694b737b53fdd5c3617399cd | | DeepSeek-V3 | 50.11 | Not recorded | 694b737b53fdd5c3617399cd | ### TableLLM Rge: 1.99. Result ID: 699943eb5698665ec4ae0281. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale Group":"Comparable"}. This record does not assert independent reproduction. ### Llama-3.1-8B Rge: 21.94. Result ID: 699943eb5698665ec4ae0282. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale Group":"Comparable"}. This record does not assert independent reproduction. ### Table-R1-Zero-7B Rge: 28.89. Result ID: 699943eb5698665ec4ae0283. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale Group":"Comparable"}. This record does not assert independent reproduction. ### TableGPT2-7B Rge: 40.7. Result ID: 699943eb5698665ec4ae0284. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale Group":"Comparable"}. This record does not assert independent reproduction. ### GPT-4o Rge: 41.43. Result ID: 699943eb5698665ec4ae028a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale Group":"Larger"}. This record does not assert independent reproduction. ### Qwen3-8B Rge: 41.86. Result ID: 699943eb5698665ec4ae0280. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale Group":"Comparable"}. This record does not assert independent reproduction. ### Qwen-Plus Rge: 44.06. Result ID: 699943eb5698665ec4ae028c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale Group":"Larger"}. This record does not assert independent reproduction. ### QwQ-32B Rge: 44.84. Result ID: 699943eb5698665ec4ae0289. [Reporting paper]() Recorded evaluation configuration: {"Model Scale Group":"Larger"}. This record does not assert independent reproduction. ### Qwen3-72B Rge: 45.68. Result ID: 699943eb5698665ec4ae0288. [Reporting paper]() Recorded evaluation configuration: {"Model Scale Group":"Larger"}. This record does not assert independent reproduction. ### Qwen3-14B Rge: 47.36. Result ID: 699943eb5698665ec4ae0286. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale Group":"Larger"}. This record does not assert independent reproduction. ### Qwen3-32B Rge: 47.47. Result ID: 699943eb5698665ec4ae0287. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale Group":"Larger"}. This record does not assert independent reproduction. ### TableGPT-R1-8B Rge: 49.53. Result ID: 699943eb5698665ec4ae0285. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale Group":"Comparable"}. This record does not assert independent reproduction. ### DeepSeek-V3 Rge: 50.11. Result ID: 699943eb5698665ec4ae028b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale Group":"Larger"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.