# Tool Retrieval on TOOLRET In-Domain (Avg)

Source: [Tool Retrieval on TOOLRET In-Domain (Avg)](<https://www.sota2.com/research/sota/tool-retrieval-on-toolret-in-domain-avg>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:11:09.135Z

Evaluation of model performance on tool retrieval capabilities using the averaged In-Domain results from the TOOLRET dataset, measured by nDCG@10 and Completeness@10.

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 Retrieval |
| Dataset (including any stated split) | TOOLRET In-Domain (Avg) |
| Metric | nDCG@10 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [nDCG@10](<https://www.sota2.com/research/sota/tool-retrieval-on-toolret-in-domain-avg.md?metric=nDCG%4010>): Higher is better; unit: PERCENT.

- [Completeness@10](<https://www.sota2.com/research/sota/tool-retrieval-on-toolret-in-domain-avg.md?metric=Completeness%4010>): Higher is better; unit: PERCENT.

## Recorded results

| Method | nDCG@10 | Result date | Report paper |
| --- | --- | --- | --- |
| TOOLQP-FORMAT | 63.1 | Not recorded | 6965d1b66343fa78c8323967 |
| gte-Qwen/ContrastiveFT | 57.2 | Not recorded | 6965d1b66343fa78c8323967 |
| TOOLQP | 53.9 | Not recorded | 6965d1b66343fa78c8323967 |
| bge-gemma | 53 | Not recorded | 6965d1b66343fa78c8323967 |
| Q2D/ZS | 52 | Not recorded | 6965d1b66343fa78c8323967 |
| D2Q | 51.5 | Not recorded | 6965d1b66343fa78c8323967 |
| Re-Invoke | 51.5 | Not recorded | 6965d1b66343fa78c8323967 |
| bge-m3 | 49.4 | Not recorded | 6965d1b66343fa78c8323967 |
| HyDE/ZS | 47.9 | Not recorded | 6965d1b66343fa78c8323967 |
| Q2D/PRF | 46.9 | Not recorded | 6965d1b66343fa78c8323967 |
| Q2P/SFT | 46.6 | Not recorded | 6965d1b66343fa78c8323967 |
| Q2E/PRF | 45 | Not recorded | 6965d1b66343fa78c8323967 |
| Q2E/ZS | 44.6 | Not recorded | 6965d1b66343fa78c8323967 |
| HyDE/PRF | 43.5 | Not recorded | 6965d1b66343fa78c8323967 |
| Base Retriever (gte-Qwen) | 43.3 | Not recorded | 6965d1b66343fa78c8323967 |

### TOOLQP-FORMAT

nDCG@10: 63.1. Result ID: 69968b8c5698665ec4d43817.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

Recorded evaluation configuration: {"Method Category":"Fine-tuning","Training Data Size":"10k","Backbone Model":"1.7B"}. This record does not assert independent reproduction.

### gte-Qwen/ContrastiveFT

nDCG@10: 57.2. Result ID: 69968b8c5698665ec4d43816.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

Recorded evaluation configuration: {"Method Category":"Fine-tuning","Training Data Size":"10k","Backbone Model":"1.5B/1.7B models"}. This record does not assert independent reproduction.

### TOOLQP

nDCG@10: 53.9. Result ID: 69968b8c5698665ec4d43818.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

Recorded evaluation configuration: {"Method Category":"Fine-tuning","Training Data Size":"10k","Backbone Model":"1.7B"}. This record does not assert independent reproduction.

### bge-gemma

nDCG@10: 53. Result ID: 69968b8c5698665ec4d43814.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73d91e209131cea5e7ab.md>)

[Implementation](<https://github.com/FlagOpen/FlagEmbedding>)

Recorded evaluation configuration: {"Method Category":"Re-ranking with cross-encoder"}. This record does not assert independent reproduction.

### Q2D/ZS

nDCG@10: 52. Result ID: 69968b8c5698665ec4d4380c.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d93f.md>)

Recorded evaluation configuration: {"Method Category":"Prompting","Backbone Model":"Qwen3-30B-A3B-Instruct"}. This record does not assert independent reproduction.

### D2Q

nDCG@10: 51.5. Result ID: 69968b8c5698665ec4d4380e.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66791e209131cea10690.md>)

[Implementation](<https://github.com/nyu-dl/dl4ir-doc2query>)

Recorded evaluation configuration: {"Method Category":"Prompting","Backbone Model":"Qwen3-30B-A3B-Instruct"}. This record does not assert independent reproduction.

### Re-Invoke

nDCG@10: 51.5. Result ID: 69968b8c5698665ec4d4380f.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74e81e209131cea649ff.md>)

Recorded evaluation configuration: {"Method Category":"Prompting","Backbone Model":"Qwen3-30B-A3B-Instruct"}. This record does not assert independent reproduction.

### bge-m3

nDCG@10: 49.4. Result ID: 69968b8c5698665ec4d43813.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73d91e209131cea5e7ab.md>)

[Implementation](<https://github.com/FlagOpen/FlagEmbedding>)

Recorded evaluation configuration: {"Method Category":"Re-ranking with cross-encoder"}. This record does not assert independent reproduction.

### HyDE/ZS

nDCG@10: 47.9. Result ID: 69968b8c5698665ec4d4380d.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e3b1e209131cea3e835.md>)

[Implementation](<https://github.com/texttron/hyde>)

Recorded evaluation configuration: {"Method Category":"Prompting","Backbone Model":"Qwen3-30B-A3B-Instruct"}. This record does not assert independent reproduction.

### Q2D/PRF

nDCG@10: 46.9. Result ID: 69968b8c5698665ec4d43811.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d93f.md>)

Recorded evaluation configuration: {"Method Category":"Prompting","Backbone Model":"Qwen3-30B-A3B-Instruct"}. This record does not assert independent reproduction.

### Q2P/SFT

nDCG@10: 46.6. Result ID: 69968b8c5698665ec4d43815.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

Recorded evaluation configuration: {"Method Category":"Fine-tuning","Training Data Size":"10k","Backbone Model":"1.5B/1.7B models"}. This record does not assert independent reproduction.

### Q2E/PRF

nDCG@10: 45. Result ID: 69968b8c5698665ec4d43810.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f491e209131cea44ca0.md>)

Recorded evaluation configuration: {"Method Category":"Prompting","Backbone Model":"Qwen3-30B-A3B-Instruct"}. This record does not assert independent reproduction.

### Q2E/ZS

nDCG@10: 44.6. Result ID: 69968b8c5698665ec4d4380b.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f491e209131cea44ca0.md>)

Recorded evaluation configuration: {"Method Category":"Prompting","Backbone Model":"Qwen3-30B-A3B-Instruct"}. This record does not assert independent reproduction.

### HyDE/PRF

nDCG@10: 43.5. Result ID: 69968b8c5698665ec4d43812.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e3b1e209131cea3e835.md>)

[Implementation](<https://github.com/texttron/hyde>)

Recorded evaluation configuration: {"Method Category":"Prompting","Backbone Model":"Qwen3-30B-A3B-Instruct"}. This record does not assert independent reproduction.

### Base Retriever (gte-Qwen)

nDCG@10: 43.3. Result ID: 69968b8c5698665ec4d4380a.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b66343fa78c8323967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703b1e209131cea49c20.md>)

Recorded evaluation configuration: {"Method Category":"Base Retriever"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
