# Data Science Task Automation on xBench-DS

Source: [Data Science Task Automation on xBench-DS](<https://www.sota2.com/research/sota/data-science-task-automation-on-xbench-ds>)

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

Data updated: 2026-02-26T06:03:53.569Z

Evaluation of model performance on the xBench-DS dataset for automating data science tasks, measured by the reported Score.

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 | Data Science Task Automation |
| Dataset (including any stated split) | xBench-DS |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [Score](<https://www.sota2.com/research/sota/data-science-task-automation-on-xbench-ds.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| MemEvolve + Flash-Searcher | 78 | Not recorded | 694a223d9eebe296e72aa99d |
| MemEvolve + Flash-Searcher | 77 | Not recorded | 694a223d9eebe296e72aa99d |
| MemEvolve + Flash-Searcher | 74 | Not recorded | 694a223d9eebe296e72aa99d |
| MemEvolve + Flash-Searcher | 70 | Not recorded | 694a223d9eebe296e72aa99d |
| Flash-Searcher | 69 | Not recorded | 694a223d9eebe296e72aa99d |
| Agent KB | 68 | Not recorded | 694a223d9eebe296e72aa99d |
| Flash-Searcher | 68 | Not recorded | 694a223d9eebe296e72aa99d |
| MemEvolve + SmolAgent | 68 | Not recorded | 694a223d9eebe296e72aa99d |
| MemEvolve + Flash-Searcher | 68 | Not recorded | 694a223d9eebe296e72aa99d |
| Flash-Searcher | 66 | Not recorded | 694a223d9eebe296e72aa99d |
| MemEvolve + SmolAgent | 63 | Not recorded | 694a223d9eebe296e72aa99d |
| Agent KB | 58 | Not recorded | 694a223d9eebe296e72aa99d |
| MemEvolve + SmolAgent | 57 | Not recorded | 694a223d9eebe296e72aa99d |
| Cognitive Kernel-Pro | 56 | Not recorded | 694a223d9eebe296e72aa99d |
| OWL Workforce | 55 | Not recorded | 694a223d9eebe296e72aa99d |
| Smolagents | 51 | Not recorded | 694a223d9eebe296e72aa99d |
| Agent KB | 48 | Not recorded | 694a223d9eebe296e72aa99d |
| OAgents | 47 | Not recorded | 694a223d9eebe296e72aa99d |

### MemEvolve + Flash-Searcher

Score: 78. Result ID: 6996b68a5698665ec40117e8.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"GPT-5-mini","pass@k":"3"}. This record does not assert independent reproduction.

### MemEvolve + Flash-Searcher

Score: 77. Result ID: 6996b68a5698665ec40117e7.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"GPT-5-mini","pass@k":"2"}. This record does not assert independent reproduction.

### MemEvolve + Flash-Searcher

Score: 74. Result ID: 6996b68a5698665ec40117e6.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"GPT-5-mini","pass@k":"1"}. This record does not assert independent reproduction.

### MemEvolve + Flash-Searcher

Score: 70. Result ID: 6996b68a5698665ec40117ea.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"DeepSeek V3.2","pass@k":"1"}. This record does not assert independent reproduction.

### Flash-Searcher

Score: 69. Result ID: 6996b68a5698665ec40117e0.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb01e209131cea89ea1.md>)

Recorded evaluation configuration: {"Model Family":"GPT-5-mini","pass@k":"1"}. This record does not assert independent reproduction.

### Agent KB

Score: 68. Result ID: 6996b68a5698665ec40117df.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"GPT-4.1","pass@k":"3"}. This record does not assert independent reproduction.

### Flash-Searcher

Score: 68. Result ID: 6996b68a5698665ec40117e2.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb01e209131cea89ea1.md>)

Recorded evaluation configuration: {"Model Family":"DeepSeek V3.2","pass@k":"1"}. This record does not assert independent reproduction.

### MemEvolve + SmolAgent

Score: 68. Result ID: 6996b68a5698665ec40117e5.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"GPT-5-mini","pass@k":"3"}. This record does not assert independent reproduction.

### MemEvolve + Flash-Searcher

Score: 68. Result ID: 6996b68a5698665ec40117e9.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"Kimi K2","pass@k":"1"}. This record does not assert independent reproduction.

### Flash-Searcher

Score: 66. Result ID: 6996b68a5698665ec40117e1.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb01e209131cea89ea1.md>)

Recorded evaluation configuration: {"Model Family":"Kimi K2","pass@k":"1"}. This record does not assert independent reproduction.

### MemEvolve + SmolAgent

Score: 63. Result ID: 6996b68a5698665ec40117e4.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"GPT-5-mini","pass@k":"2"}. This record does not assert independent reproduction.

### Agent KB

Score: 58. Result ID: 6996b68a5698665ec40117de.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"GPT-4.1","pass@k":"2"}. This record does not assert independent reproduction.

### MemEvolve + SmolAgent

Score: 57. Result ID: 6996b68a5698665ec40117e3.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"GPT-5-mini","pass@k":"1"}. This record does not assert independent reproduction.

### Cognitive Kernel-Pro

Score: 56. Result ID: 6996b68a5698665ec40117db.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a941e209131cea84031.md>)

Recorded evaluation configuration: {"Model Family":"Claude-3.7 etc.","pass@k":"1"}. This record does not assert independent reproduction.

### OWL Workforce

Score: 55. Result ID: 6996b68a5698665ec40117d9.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795f1e209131cea7d500.md>)

Recorded evaluation configuration: {"Model Family":"GPT-4o+o3-mini","pass@k":"3"}. This record does not assert independent reproduction.

### Smolagents

Score: 51. Result ID: 6996b68a5698665ec40117da.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"GPT-5-mini"}. This record does not assert independent reproduction.

### Agent KB

Score: 48. Result ID: 6996b68a5698665ec40117dd.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"GPT-4.1","pass@k":"1"}. This record does not assert independent reproduction.

### OAgents

Score: 47. Result ID: 6996b68a5698665ec40117dc.

[Reporting paper](<https://www.sota2.com/research/paper/694a223d9eebe296e72aa99d.md>)

Recorded evaluation configuration: {"Model Family":"Claude-3.7 etc."}. This record does not assert independent reproduction.

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