# Agent Performance on VitaBench Delivery

Source: [Agent Performance on VitaBench Delivery](<https://www.sota2.com/research/sota/agent-performance-on-vitabench-delivery>)

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

Data updated: 2026-05-27T10:13:00.882Z

Evaluation of agent performance metrics (Avg@4, Pass@4) specifically on the Delivery subset of the VitaBench dataset.

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 | Agent Performance |
| Dataset (including any stated split) | VitaBench Delivery |
| Metric | Avg@4 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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](<https://www.sota2.com/research/sota/agent-performance-on-vitabench-delivery.md?metric=Avg%404>): Higher is better; unit: PERCENT.

- [Pass@4](<https://www.sota2.com/research/sota/agent-performance-on-vitabench-delivery.md?metric=Pass%404>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Avg@4 | Result date | Report paper |
| --- | --- | --- | --- |
| NoisyAgent | 29 | Not recorded | 6a167ad3dbd7150506f80299 |
| DAPO | 27.75 | Not recorded | 6a167ad3dbd7150506f80299 |
| GSPO | 27.25 | Not recorded | 6a167ad3dbd7150506f80299 |
| GRPO | 27 | Not recorded | 6a167ad3dbd7150506f80299 |
| Qwen3-32B | 23 | Not recorded | 6a167ad3dbd7150506f80299 |
| NoisyAgent | 22.25 | Not recorded | 6a167ad3dbd7150506f80299 |
| DAPO | 21.5 | Not recorded | 6a167ad3dbd7150506f80299 |
| GSPO | 21.25 | Not recorded | 6a167ad3dbd7150506f80299 |
| GRPO | 21 | Not recorded | 6a167ad3dbd7150506f80299 |
| Qwen3-8B | 13.75 | Not recorded | 6a167ad3dbd7150506f80299 |

### NoisyAgent

Avg@4: 29. Result ID: 6a16c399fbc373592c1080ee.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

Recorded evaluation configuration: {"backbone":"Qwen3-32B"}. This record does not assert independent reproduction.

### DAPO

Avg@4: 27.75. Result ID: 6a16c399fbc373592c1080ec.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78a81e209131cea79ac6.md>)

Recorded evaluation configuration: {"backbone":"Qwen3-32B"}. This record does not assert independent reproduction.

### GSPO

Avg@4: 27.25. Result ID: 6a16c399fbc373592c1080ed.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a481e209131cea8231d.md>)

Recorded evaluation configuration: {"backbone":"Qwen3-32B"}. This record does not assert independent reproduction.

### GRPO

Avg@4: 27. Result ID: 6a16c399fbc373592c1080eb.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"backbone":"Qwen3-32B"}. This record does not assert independent reproduction.

### Qwen3-32B

Avg@4: 23. Result ID: 6a16c399fbc373592c1080ea.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

Recorded evaluation configuration: {"backbone":"Qwen3-32B"}. This record does not assert independent reproduction.

### NoisyAgent

Avg@4: 22.25. Result ID: 6a16c399fbc373592c1080e9.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

Recorded evaluation configuration: {"backbone":"Qwen3-8B"}. This record does not assert independent reproduction.

### DAPO

Avg@4: 21.5. Result ID: 6a16c399fbc373592c1080e7.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78a81e209131cea79ac6.md>)

Recorded evaluation configuration: {"backbone":"Qwen3-8B"}. This record does not assert independent reproduction.

### GSPO

Avg@4: 21.25. Result ID: 6a16c399fbc373592c1080e8.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a481e209131cea8231d.md>)

Recorded evaluation configuration: {"backbone":"Qwen3-8B"}. This record does not assert independent reproduction.

### GRPO

Avg@4: 21. Result ID: 6a16c399fbc373592c1080e6.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"backbone":"Qwen3-8B"}. This record does not assert independent reproduction.

### Qwen3-8B

Avg@4: 13.75. Result ID: 6a16c399fbc373592c1080e5.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ad3dbd7150506f80299.md>)

Recorded evaluation configuration: {"backbone":"Qwen3-8B"}. This record does not assert independent reproduction.

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