# AST evaluation on BFCL live\_multiple Source: [AST evaluation on BFCL live\_multiple]() Collection index: [llms.txt]() Data updated: 2026-06-16T09:58:01.846Z Evaluation of Abstract Syntax Tree (AST) performance on the BFCL live\_multiple dataset, using metrics such as free name accuracy, free AST accuracy, and various AST configuration scores. 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 | AST evaluation | | Dataset (including any stated split) | BFCL live\_multiple | | Metric | Free Name Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Free Name Accuracy](): Higher is better; unit: PERCENT. - [Free AST Accuracy](): Higher is better; unit: PERCENT. - [Forced-Base AST Accuracy](): Higher is better; unit: PERCENT. - [Gated AST Accuracy](): Higher is better; unit: PERCENT. - [Gold Ceiling Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Free Name Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen2.5-7B | 94.3 | Not recorded | 6a30d90ad33dfb23e783d1fc | | Llama-3.1-8B | 94 | Not recorded | 6a30d90ad33dfb23e783d1fc | | Pooled (3 main) | 92.6 | Not recorded | 6a30d90ad33dfb23e783d1fc | | Qwen3-8B | 91.3 | Not recorded | 6a30d90ad33dfb23e783d1fc | | Qwen2.5-1.5B | 89.3 | Not recorded | 6a30d90ad33dfb23e783d1fc | | xLAM-2-8B† | 34.7 | Not recorded | 6a30d90ad33dfb23e783d1fc | ### Qwen2.5-7B Free Name Accuracy: 94.3. Result ID: 6a311e14fbc373592c2df8fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### Llama-3.1-8B Free Name Accuracy: 94. Result ID: 6a311e14fbc373592c2df8fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### Pooled (3 main) Free Name Accuracy: 92.6. Result ID: 6a311e14fbc373592c2df8fe. [Reporting paper]() Recorded evaluation configuration: {"Model":"Pooled (3 main)"}. This record does not assert independent reproduction. ### Qwen3-8B Free Name Accuracy: 91.3. Result ID: 6a311e14fbc373592c2df8fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### Qwen2.5-1.5B Free Name Accuracy: 89.3. Result ID: 6a311e14fbc373592c2df8f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction. ### xLAM-2-8B† Free Name Accuracy: 34.7. Result ID: 6a311e14fbc373592c2df8fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"xLAM-2-8B†"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.