# Tool Planning on m&m Source: [Tool Planning on m&m]() Collection index: [llms.txt]() Data updated: 2026-03-16T09:15:02.024Z Evaluation of model performance on Tool Planning tasks using the m&m dataset, measured by various F1 scores related to tool selection, argument prediction, planning, and execution. 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 Planning | | Dataset (including any stated split) | m&m | | Metric | Tool Selection F1 (Step-by-step) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Tool Selection F1 (Step-by-step)](): Higher is better; unit: PERCENT. - [Argument Prediction F1 (Step-by-step)](): Higher is better; unit: PERCENT. - [Planning F1 (Multi-step)](): Higher is better; unit: PERCENT. - [Execution F1 (Multi-step)](): Higher is better; unit: PERCENT. - [Average F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Tool Selection F1 (Step-by-step) | Result date | Report paper | | --- | --- | --- | --- | | ToolTree | 91.92 | Not recorded | 69b78e650636e5bf4afbda98 | | LATS | 88.89 | Not recorded | 69b78e650636e5bf4afbda98 | | A\* | 87.17 | Not recorded | 69b78e650636e5bf4afbda98 | | ToT | 86.28 | Not recorded | 69b78e650636e5bf4afbda98 | | CoT | 85.58 | Not recorded | 69b78e650636e5bf4afbda98 | | Best-First | 84.47 | Not recorded | 69b78e650636e5bf4afbda98 | | ReAct | 83.58 | Not recorded | 69b78e650636e5bf4afbda98 | | Zero-shot | 78.52 | Not recorded | 69b78e650636e5bf4afbda98 | | ToolTree | 77.25 | Not recorded | 69b78e650636e5bf4afbda98 | | LATS | 76.84 | Not recorded | 69b78e650636e5bf4afbda98 | | ToT | 75.58 | Not recorded | 69b78e650636e5bf4afbda98 | | A\* | 75.16 | Not recorded | 69b78e650636e5bf4afbda98 | | Best-First | 74.42 | Not recorded | 69b78e650636e5bf4afbda98 | | ReAct | 73.55 | Not recorded | 69b78e650636e5bf4afbda98 | | Zero-Shot | 72.48 | Not recorded | 69b78e650636e5bf4afbda98 | | CoT | 70.13 | Not recorded | 69b78e650636e5bf4afbda98 | ### ToolTree Tool Selection F1 (Step-by-step): 91.92. Result ID: 69b7c9fe47f34ce9249fae72. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction. ### LATS Tool Selection F1 (Step-by-step): 88.89. Result ID: 69b7c9fe47f34ce9249fae71. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction. ### A\* Tool Selection F1 (Step-by-step): 87.17. Result ID: 69b7c9fe47f34ce9249fae70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction. ### ToT Tool Selection F1 (Step-by-step): 86.28. Result ID: 69b7c9fe47f34ce9249fae6f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction. ### CoT Tool Selection F1 (Step-by-step): 85.58. Result ID: 69b7c9fe47f34ce9249fae6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction. ### Best-First Tool Selection F1 (Step-by-step): 84.47. Result ID: 69b7c9fe47f34ce9249fae6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction. ### ReAct Tool Selection F1 (Step-by-step): 83.58. Result ID: 69b7c9fe47f34ce9249fae6c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction. ### Zero-shot Tool Selection F1 (Step-by-step): 78.52. Result ID: 69b7c9fe47f34ce9249fae6b. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction. ### ToolTree Tool Selection F1 (Step-by-step): 77.25. Result ID: 69b7c9fe47f34ce9249fae6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### LATS Tool Selection F1 (Step-by-step): 76.84. Result ID: 69b7c9fe47f34ce9249fae69. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### ToT Tool Selection F1 (Step-by-step): 75.58. Result ID: 69b7c9fe47f34ce9249fae67. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### A\* Tool Selection F1 (Step-by-step): 75.16. Result ID: 69b7c9fe47f34ce9249fae68. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### Best-First Tool Selection F1 (Step-by-step): 74.42. Result ID: 69b7c9fe47f34ce9249fae66. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### ReAct Tool Selection F1 (Step-by-step): 73.55. Result ID: 69b7c9fe47f34ce9249fae64. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### Zero-Shot Tool Selection F1 (Step-by-step): 72.48. Result ID: 69b7c9fe47f34ce9249fae63. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### CoT Tool Selection F1 (Step-by-step): 70.13. Result ID: 69b7c9fe47f34ce9249fae65. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-4o-mini"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.