# Tool Use on Tool-Decathlon

Source: [Tool Use on Tool-Decathlon](<https://www.sota2.com/research/sota/tool-use-on-tool-decathlon>)

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

Data updated: 2026-02-26T05:57:26.330Z

Evaluation of model performance on general tool utilization capabilities using the Tool-Decathlon dataset, measured by the Pass@1 success rate.

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 |
| Dataset (including any stated split) | Tool-Decathlon |
| Metric | Pass@1 |
| 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

- [Pass@1](<https://www.sota2.com/research/sota/tool-use-on-tool-decathlon.md?metric=Pass%401>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@1 | Result date | Report paper |
| --- | --- | --- | --- |
| Claude-4.5-Sonnet | 38.6 | Not recorded | 692fc410d6b0dd33429332f4 |
| Gemini-3.0 Pro | 36.4 | Not recorded | 692fc410d6b0dd33429332f4 |
| DeepSeek-V3.2 | 35.2 | Not recorded | 692fc410d6b0dd33429332f4 |
| GPT-5 High | 29 | Not recorded | 692fc410d6b0dd33429332f4 |
| Kimi-K2 | 17.6 | Not recorded | 692fc410d6b0dd33429332f4 |
| MiniMax M2 | 16 | Not recorded | 692fc410d6b0dd33429332f4 |

### Claude-4.5-Sonnet

Pass@1: 38.6. Result ID: 6996d1c05698665ec41dee3a.

[Reporting paper](<https://www.sota2.com/research/paper/692fc410d6b0dd33429332f4.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Gemini-3.0 Pro

Pass@1: 36.4. Result ID: 6996d1c05698665ec41dee3c.

[Reporting paper](<https://www.sota2.com/research/paper/692fc410d6b0dd33429332f4.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DeepSeek-V3.2

Pass@1: 35.2. Result ID: 6996d1c05698665ec41dee3f.

[Reporting paper](<https://www.sota2.com/research/paper/692fc410d6b0dd33429332f4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692fc410d6b0dd33429332f4.md>)

Recorded evaluation configuration: {"thinking mode":true}. This record does not assert independent reproduction.

### GPT-5 High

Pass@1: 29. Result ID: 6996d1c05698665ec41dee3b.

[Reporting paper](<https://www.sota2.com/research/paper/692fc410d6b0dd33429332f4.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Kimi-K2

Pass@1: 17.6. Result ID: 6996d1c05698665ec41dee3d.

[Reporting paper](<https://www.sota2.com/research/paper/692fc410d6b0dd33429332f4.md>)

Recorded evaluation configuration: {"thinking mode":true}. This record does not assert independent reproduction.

### MiniMax M2

Pass@1: 16. Result ID: 6996d1c05698665ec41dee3e.

[Reporting paper](<https://www.sota2.com/research/paper/692fc410d6b0dd33429332f4.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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