# Tool Response Generation on GTM Multi-turn Source: [Tool Response Generation on GTM Multi-turn]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:45:30.544Z Evaluation of model performance on generating responses that correctly utilize tools, assessed using criteria such as Format, Logic, Semantics, Completeness, and Consistency. 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 Response Generation | | Dataset (including any stated split) | GTM Multi-turn | | Metric | Format Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [Format Score](): Higher is better; unit: PERCENT. - [Logic Score](): Higher is better; unit: PERCENT. - [Semantics Score](): Higher is better; unit: PERCENT. - [Completeness Score](): Higher is better; unit: PERCENT. - [Consistency Score](): Higher is better; unit: PERCENT. - [Overall Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Format Score | Result date | Report paper | | --- | --- | --- | --- | | GTM-1.5B | 97.2 | Not recorded | 69326755d6b0dd3342934552 | | Qwen2.5-7B-Instruct | 91.4 | Not recorded | 69326755d6b0dd3342934552 | | Qwen2.5-14B-Instruct | 88 | Not recorded | 69326755d6b0dd3342934552 | | Llama-3.2-3B-Instruct | 82.4 | Not recorded | 69326755d6b0dd3342934552 | | Qwen2.5-3B-Instruct | 80 | Not recorded | 69326755d6b0dd3342934552 | | InternLM2.5-20B | 79.8 | Not recorded | 69326755d6b0dd3342934552 | | Qwen2.5-1.5B-Instruct | 74.1 | Not recorded | 69326755d6b0dd3342934552 | | Qwen2.5-0.5B-Instruct | 66.7 | Not recorded | 69326755d6b0dd3342934552 | | InternLM2.5-7B | 63.6 | Not recorded | 69326755d6b0dd3342934552 | | Llama-3.2-1B-Instruct | 38.3 | Not recorded | 69326755d6b0dd3342934552 | | InternLM2.5-1.8B | 34.8 | Not recorded | 69326755d6b0dd3342934552 | ### GTM-1.5B Format Score: 97.2. Result ID: 69962f425698665ec470f8d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"1.5B"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Format Score: 91.4. Result ID: 69962f425698665ec470f8cd. [Reporting paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-14B-Instruct Format Score: 88. Result ID: 69962f425698665ec470f8ce. [Reporting paper]() Recorded evaluation configuration: {"Model Size":"14B"}. This record does not assert independent reproduction. ### Llama-3.2-3B-Instruct Format Score: 82.4. Result ID: 69962f425698665ec470f8d0. [Reporting paper]() Recorded evaluation configuration: {"Model Size":"3B"}. This record does not assert independent reproduction. ### Qwen2.5-3B-Instruct Format Score: 80. Result ID: 69962f425698665ec470f8cc. [Reporting paper]() Recorded evaluation configuration: {"Model Size":"3B"}. This record does not assert independent reproduction. ### InternLM2.5-20B Format Score: 79.8. Result ID: 69962f425698665ec470f8d3. [Reporting paper]() Recorded evaluation configuration: {"Model Size":"20B"}. This record does not assert independent reproduction. ### Qwen2.5-1.5B-Instruct Format Score: 74.1. Result ID: 69962f425698665ec470f8cb. [Reporting paper]() Recorded evaluation configuration: {"Model Size":"1.5B"}. This record does not assert independent reproduction. ### Qwen2.5-0.5B-Instruct Format Score: 66.7. Result ID: 69962f425698665ec470f8ca. [Reporting paper]() Recorded evaluation configuration: {"Model Size":"0.5B"}. This record does not assert independent reproduction. ### InternLM2.5-7B Format Score: 63.6. Result ID: 69962f425698665ec470f8d2. [Reporting paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### Llama-3.2-1B-Instruct Format Score: 38.3. Result ID: 69962f425698665ec470f8cf. [Reporting paper]() Recorded evaluation configuration: {"Model Size":"1B"}. This record does not assert independent reproduction. ### InternLM2.5-1.8B Format Score: 34.8. Result ID: 69962f425698665ec470f8d1. [Reporting paper]() Recorded evaluation configuration: {"Model Size":"1.8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.