# Edge Count on Synthetic Benchmark Source: [Edge Count on Synthetic Benchmark]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:55.608Z Evaluation of model performance on the Edge Count task using the Synthetic Benchmark dataset, measured by Accuracy and Absolute Error. 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 | Edge Count | | Dataset (including any stated split) | Synthetic Benchmark | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [Absolute Error](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | NAG-LoRA | 94.95 | Not recorded | 69802f69a8b01e76cc8e14e4 | | NAG-Zero | 93 | Not recorded | 69802f69a8b01e76cc8e14e4 | | Qwen3-LoRA | 86.35 | Not recorded | 69802f69a8b01e76cc8e14e4 | | GraphTokenE | 59.73 | Not recorded | 69802f69a8b01e76cc8e14e4 | | GraphTokenN | 45.97 | Not recorded | 69802f69a8b01e76cc8e14e4 | | GraphTokenG | 40.6 | Not recorded | 69802f69a8b01e76cc8e14e4 | | Qwen3-Direct | 31.15 | Not recorded | 69802f69a8b01e76cc8e14e4 | ### NAG-LoRA Accuracy: 94.95. Result ID: 69965d0f5698665ec4a2c3f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Training":"LoRA fine-tuning"}. This record does not assert independent reproduction. ### NAG-Zero Accuracy: 93. Result ID: 69965d0f5698665ec4a2c3ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Mode":"Zero-shot"}. This record does not assert independent reproduction. ### Qwen3-LoRA Accuracy: 86.35. Result ID: 69965d0f5698665ec4a2c3ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Training":"LoRA fine-tuning"}. This record does not assert independent reproduction. ### GraphTokenE Accuracy: 59.73. Result ID: 69965d0f5698665ec4a2c3ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M"}. This record does not assert independent reproduction. ### GraphTokenN Accuracy: 45.97. Result ID: 69965d0f5698665ec4a2c3ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M"}. This record does not assert independent reproduction. ### GraphTokenG Accuracy: 40.6. Result ID: 69965d0f5698665ec4a2c3eb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M"}. This record does not assert independent reproduction. ### Qwen3-Direct Accuracy: 31.15. Result ID: 69965d0f5698665ec4a2c3ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.