# Tool-use agent performance on BFCL V3 Source: [Tool-use agent performance on BFCL V3]() Collection index: [llms.txt]() Data updated: 2026-04-07T10:55:53.109Z Evaluation of model performance on general tool utilization capabilities using the BFCL V3 dataset, measured by Avg@4 and Pass@4 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 | Tool-use agentic performance | | Dataset (including any stated split) | BFCL V3 | | Metric | Avg@4 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 - [Avg@4](): Higher is better; unit: PERCENT. - [Pass@4](): Higher is better; unit: PERCENT. ## Recorded results | Method | Avg@4 | Result date | Report paper | | --- | --- | --- | --- | | SkillX | 79.5 | Not recorded | 69d48fc27d0172140ec745ee | | ExpeL | 78.83 | Not recorded | 69d48fc27d0172140ec745ee | | AWM | 77.17 | Not recorded | 69d48fc27d0172140ec745ee | | No Memory | 76.67 | Not recorded | 69d48fc27d0172140ec745ee | | A-Mem | 76.5 | Not recorded | 69d48fc27d0172140ec745ee | | SkillX | 66.83 | Not recorded | 69d48fc27d0172140ec745ee | | ExpeL | 66.33 | Not recorded | 69d48fc27d0172140ec745ee | | ExpeL | 66 | Not recorded | 69d48fc27d0172140ec745ee | | AWM | 65.33 | Not recorded | 69d48fc27d0172140ec745ee | | No Memory | 65.17 | Not recorded | 69d48fc27d0172140ec745ee | | A-Mem | 65.17 | Not recorded | 69d48fc27d0172140ec745ee | | AWM | 64.67 | Not recorded | 69d48fc27d0172140ec745ee | | SkillX | 63.67 | Not recorded | 69d48fc27d0172140ec745ee | | ExpeL | 59.33 | Not recorded | 69d48fc27d0172140ec745ee | | ExpeL | 57.33 | Not recorded | 69d48fc27d0172140ec745ee | | AWM | 56.67 | Not recorded | 69d48fc27d0172140ec745ee | | AWM | 55.67 | Not recorded | 69d48fc27d0172140ec745ee | | No Memory | 53.67 | Not recorded | 69d48fc27d0172140ec745ee | | A-Mem | 53.67 | Not recorded | 69d48fc27d0172140ec745ee | ### SkillX Avg@4: 79.5. Result ID: 69d4e2b247f34ce924bd82d1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GLM-4.6","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### ExpeL Avg@4: 78.83. Result ID: 69d4e2b247f34ce924bd82d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GLM-4.6","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### AWM Avg@4: 77.17. Result ID: 69d4e2b247f34ce924bd82cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GLM-4.6","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### No Memory Avg@4: 76.67. Result ID: 69d4e2b247f34ce924bd82cd. [Reporting paper]() Recorded evaluation configuration: {"Model":"GLM-4.6","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### A-Mem Avg@4: 76.5. Result ID: 69d4e2b247f34ce924bd82ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GLM-4.6","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### SkillX Avg@4: 66.83. Result ID: 69d4e2b247f34ce924bd82cc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Kimi-K2-Instruct-0905","Experience extraction model alignment":"GLM-4.6 used for experience extraction"}. This record does not assert independent reproduction. ### ExpeL Avg@4: 66.33. Result ID: 69d4e2b247f34ce924bd82ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Kimi-K2-Instruct-0905","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### ExpeL Avg@4: 66. Result ID: 69d4e2b247f34ce924bd82cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Kimi-K2-Instruct-0905","Experience extraction model alignment":"GLM-4.6 used for experience extraction"}. This record does not assert independent reproduction. ### AWM Avg@4: 65.33. Result ID: 69d4e2b247f34ce924bd82c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Kimi-K2-Instruct-0905","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### No Memory Avg@4: 65.17. Result ID: 69d4e2b247f34ce924bd82c6. [Reporting paper]() Recorded evaluation configuration: {"Model":"Kimi-K2-Instruct-0905","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### A-Mem Avg@4: 65.17. Result ID: 69d4e2b247f34ce924bd82c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Kimi-K2-Instruct-0905","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### AWM Avg@4: 64.67. Result ID: 69d4e2b247f34ce924bd82c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Kimi-K2-Instruct-0905","Experience extraction model alignment":"GLM-4.6 used for experience extraction"}. This record does not assert independent reproduction. ### SkillX Avg@4: 63.67. Result ID: 69d4e2b247f34ce924bd82c5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen3-32B","Experience extraction model alignment":"GLM-4.6 used for experience extraction"}. This record does not assert independent reproduction. ### ExpeL Avg@4: 59.33. Result ID: 69d4e2b247f34ce924bd82c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-32B","Experience extraction model alignment":"GLM-4.6 used for experience extraction"}. This record does not assert independent reproduction. ### ExpeL Avg@4: 57.33. Result ID: 69d4e2b247f34ce924bd82c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-32B","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### AWM Avg@4: 56.67. Result ID: 69d4e2b247f34ce924bd82c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-32B","Experience extraction model alignment":"GLM-4.6 used for experience extraction"}. This record does not assert independent reproduction. ### AWM Avg@4: 55.67. Result ID: 69d4e2b247f34ce924bd82c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-32B","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### No Memory Avg@4: 53.67. Result ID: 69d4e2b247f34ce924bd82bf. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-32B","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. ### A-Mem Avg@4: 53.67. Result ID: 69d4e2b247f34ce924bd82c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-32B","Experience extraction model alignment":"Aligned with inference model"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.