# Node Count on synthetic benchmark 1.0 (test) Source: [Node Count on synthetic benchmark 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:55.591Z Evaluation of model performance on the Node Count task using the test split of the synthetic benchmark version 1.0, 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 | Node Count | | Dataset (including any stated split) | synthetic benchmark 1.0 (test) | | 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 | | --- | --- | --- | --- | | Qwen3-LoRA | 100 | Not recorded | 69802f69a8b01e76cc8e14e4 | | NAG-LoRA | 100 | Not recorded | 69802f69a8b01e76cc8e14e4 | | NAG-Zero | 99.85 | Not recorded | 69802f69a8b01e76cc8e14e4 | | GraphTokenN | 94.38 | Not recorded | 69802f69a8b01e76cc8e14e4 | | GraphTokenE | 93.26 | Not recorded | 69802f69a8b01e76cc8e14e4 | | GraphTokenG | 82.02 | Not recorded | 69802f69a8b01e76cc8e14e4 | | Qwen3-Direct | 45.65 | Not recorded | 69802f69a8b01e76cc8e14e4 | ### Qwen3-LoRA Accuracy: 100. Result ID: 69965d0f5698665ec4a2c3e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Training":"LoRA fine-tuning"}. This record does not assert independent reproduction. ### NAG-LoRA Accuracy: 100. Result ID: 69965d0f5698665ec4a2c3e9. [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: 99.85. Result ID: 69965d0f5698665ec4a2c3e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Mode":"Zero-shot"}. This record does not assert independent reproduction. ### GraphTokenN Accuracy: 94.38. Result ID: 69965d0f5698665ec4a2c3e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Granularity":"Node-level embeddings"}. This record does not assert independent reproduction. ### GraphTokenE Accuracy: 93.26. Result ID: 69965d0f5698665ec4a2c3e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Granularity":"Edge-level embeddings"}. This record does not assert independent reproduction. ### GraphTokenG Accuracy: 82.02. Result ID: 69965d0f5698665ec4a2c3e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Granularity":"Global pooled representation"}. This record does not assert independent reproduction. ### Qwen3-Direct Accuracy: 45.65. Result ID: 69965d0f5698665ec4a2c3e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Mode":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.