# Code Generation on xCodeEval (sample 500)

Source: [Code Generation on xCodeEval (sample 500)](<https://www.sota2.com/research/sota/code-generation-on-xcodeeval-sample-500>)

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

Data updated: 2026-02-26T05:34:14.980Z

Evaluation of model performance on the specific 500-sample subset of the xCodeEval dataset for code generation, typically broken down by difficulty levels (Easy, Mid, Hard, Expert).

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 | Code Generation |
| Dataset (including any stated split) | xCodeEval (sample 500) |
| Metric | Accuracy (Easy) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [Accuracy (Easy)](<https://www.sota2.com/research/sota/code-generation-on-xcodeeval-sample-500.md?metric=Accuracy%20(Easy)>): Higher is better; unit: PERCENT.

- [Accuracy (Mid)](<https://www.sota2.com/research/sota/code-generation-on-xcodeeval-sample-500.md?metric=Accuracy%20(Mid)>): Higher is better; unit: PERCENT.

- [Accuracy (Hard)](<https://www.sota2.com/research/sota/code-generation-on-xcodeeval-sample-500.md?metric=Accuracy%20(Hard)>): Higher is better; unit: PERCENT.

- [Accuracy (Expert)](<https://www.sota2.com/research/sota/code-generation-on-xcodeeval-sample-500.md?metric=Accuracy%20(Expert)>): Higher is better; unit: PERCENT.

- [Accuracy (Overall)](<https://www.sota2.com/research/sota/code-generation-on-xcodeeval-sample-500.md?metric=Accuracy%20(Overall)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Easy) | Result date | Report paper |
| --- | --- | --- | --- |
| FUNCODER | 0.831 | Not recorded | 68fa75901e209131cea68a73 |
| CodeT | 0.764 | Not recorded | 68fa75901e209131cea68a73 |
| Reflexion | 0.713 | Not recorded | 68fa75901e209131cea68a73 |
| Standard | 0.685 | Not recorded | 68fa75901e209131cea68a73 |
| FUNCODER | 0.624 | Not recorded | 68fa75901e209131cea68a73 |
| CodeT | 0.506 | Not recorded | 68fa75901e209131cea68a73 |
| Standard | 0.444 | Not recorded | 68fa75901e209131cea68a73 |
| Reflexion | 0.444 | Not recorded | 68fa75901e209131cea68a73 |
| FUNCODER | 0.22 | Not recorded | 68fa75901e209131cea68a73 |
| FUNCODER | 0.135 | Not recorded | 68fa75901e209131cea68a73 |
| CodeT | 0.124 | Not recorded | 68fa75901e209131cea68a73 |
| CodeT | 0.112 | Not recorded | 68fa75901e209131cea68a73 |
| FUNCODER | 0.102 | Not recorded | 68fa75901e209131cea68a73 |
| CodeT | 0.101 | Not recorded | 68fa75901e209131cea68a73 |
| Standard | 0.09 | Not recorded | 68fa75901e209131cea68a73 |
| Standard | 0.073 | Not recorded | 68fa75901e209131cea68a73 |
| Standard | 0.023 | Not recorded | 68fa75901e209131cea68a73 |

### FUNCODER

Accuracy (Easy): 0.831. Result ID: 6993d44e3a6c31484918d585.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Implementation](<https://github.com/cometeme/funcoder>)

Recorded evaluation configuration: {"Model":"GPT-4"}. This record does not assert independent reproduction.

### CodeT

Accuracy (Easy): 0.764. Result ID: 6993d44e3a6c31484918d583.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfd1e209131cea3d39a.md>)

[Implementation](<https://github.com/microsoft/CodeT>)

Recorded evaluation configuration: {"Model":"GPT-4"}. This record does not assert independent reproduction.

### Reflexion

Accuracy (Easy): 0.713. Result ID: 6993d44e3a6c31484918d584.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70cc1e209131cea4d38e.md>)

[Implementation](<https://github.com/noahshinn024/reflexion>)

Recorded evaluation configuration: {"Model":"GPT-4"}. This record does not assert independent reproduction.

### Standard

Accuracy (Easy): 0.685. Result ID: 6993d44e3a6c31484918d582.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"GPT-4"}. This record does not assert independent reproduction.

### FUNCODER

Accuracy (Easy): 0.624. Result ID: 6993d44e3a6c31484918d581.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Implementation](<https://github.com/cometeme/funcoder>)

Recorded evaluation configuration: {"Model":"GPT-3.5"}. This record does not assert independent reproduction.

### CodeT

Accuracy (Easy): 0.506. Result ID: 6993d44e3a6c31484918d57f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfd1e209131cea3d39a.md>)

[Implementation](<https://github.com/microsoft/CodeT>)

Recorded evaluation configuration: {"Model":"GPT-3.5"}. This record does not assert independent reproduction.

### Standard

Accuracy (Easy): 0.444. Result ID: 6993d44e3a6c31484918d57e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"GPT-3.5"}. This record does not assert independent reproduction.

### Reflexion

Accuracy (Easy): 0.444. Result ID: 6993d44e3a6c31484918d580.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70cc1e209131cea4d38e.md>)

[Implementation](<https://github.com/noahshinn024/reflexion>)

Recorded evaluation configuration: {"Model":"GPT-3.5"}. This record does not assert independent reproduction.

### FUNCODER

Accuracy (Easy): 0.22. Result ID: 6993d44e3a6c31484918d588.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Implementation](<https://github.com/cometeme/funcoder>)

Recorded evaluation configuration: {"Model":"Llama3-8b"}. This record does not assert independent reproduction.

### FUNCODER

Accuracy (Easy): 0.135. Result ID: 6993d44e3a6c31484918d58b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Implementation](<https://github.com/cometeme/funcoder>)

Recorded evaluation configuration: {"Model":"StableCode-3b"}. This record does not assert independent reproduction.

### CodeT

Accuracy (Easy): 0.124. Result ID: 6993d44e3a6c31484918d587.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfd1e209131cea3d39a.md>)

[Implementation](<https://github.com/microsoft/CodeT>)

Recorded evaluation configuration: {"Model":"Llama3-8b"}. This record does not assert independent reproduction.

### CodeT

Accuracy (Easy): 0.112. Result ID: 6993d44e3a6c31484918d58a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfd1e209131cea3d39a.md>)

[Implementation](<https://github.com/microsoft/CodeT>)

Recorded evaluation configuration: {"Model":"StableCode-3b"}. This record does not assert independent reproduction.

### FUNCODER

Accuracy (Easy): 0.102. Result ID: 6993d44e3a6c31484918d58e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Implementation](<https://github.com/cometeme/funcoder>)

Recorded evaluation configuration: {"Model":"CodeLlama-34b"}. This record does not assert independent reproduction.

### CodeT

Accuracy (Easy): 0.101. Result ID: 6993d44e3a6c31484918d58d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfd1e209131cea3d39a.md>)

[Implementation](<https://github.com/microsoft/CodeT>)

Recorded evaluation configuration: {"Model":"CodeLlama-34b"}. This record does not assert independent reproduction.

### Standard

Accuracy (Easy): 0.09. Result ID: 6993d44e3a6c31484918d586.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"Llama3-8b"}. This record does not assert independent reproduction.

### Standard

Accuracy (Easy): 0.073. Result ID: 6993d44e3a6c31484918d589.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"StableCode-3b"}. This record does not assert independent reproduction.

### Standard

Accuracy (Easy): 0.023. Result ID: 6993d44e3a6c31484918d58c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"CodeLlama-34b"}. This record does not assert independent reproduction.

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