# Machine Translation on Seen Dataset en-ta 1.0

Source: [Machine Translation on Seen Dataset en-ta 1.0](<https://www.sota2.com/research/sota/machine-translation-on-seen-dataset-en-ta-1-0>)

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

Data updated: 2026-02-26T05:45:46.385Z

Evaluation of Machine Translation performance using the 'Seen Dataset en-ta 1.0', reporting metrics derived from GPT-4 evaluations and COMET scores.

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 | Machine Translation |
| Dataset (including any stated split) | Seen Dataset en-ta 1.0 |
| Metric | GPT-4 Score |
| Unit | SCALAR |
| 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

- [GPT-4 Score](<https://www.sota2.com/research/sota/machine-translation-on-seen-dataset-en-ta-1-0.md?metric=GPT-4%20Score>): Higher is better; unit: SCALAR.

- [COMET Score](<https://www.sota2.com/research/sota/machine-translation-on-seen-dataset-en-ta-1-0.md?metric=COMET%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | GPT-4 Score | Result date | Report paper |
| --- | --- | --- | --- |
| IdiomCE | 1.76 | Not recorded | 68fa78d71e209131cea7ab80 |
| IdiomKB | 1.65 | Not recorded | 68fa78d71e209131cea7ab80 |
| Direct | 1.6 | Not recorded | 68fa78d71e209131cea7ab80 |
| SIA | 1.6 | Not recorded | 68fa78d71e209131cea7ab80 |
| LIA | 1.42 | Not recorded | 68fa78d71e209131cea7ab80 |
| IdiomCE | 1.29 | Not recorded | 68fa78d71e209131cea7ab80 |
| Indictrans2 | 1.26 | Not recorded | 68fa78d71e209131cea7ab80 |
| SIA | 1.23 | Not recorded | 68fa78d71e209131cea7ab80 |
| NLLB-200 | 1.21 | Not recorded | 68fa78d71e209131cea7ab80 |
| IdiomKB | 1.2 | Not recorded | 68fa78d71e209131cea7ab80 |
| LIA | 1.184 | Not recorded | 68fa78d71e209131cea7ab80 |
| Direct | 1.16 | Not recorded | 68fa78d71e209131cea7ab80 |
| IdiomCE | 1.15 | Not recorded | 68fa78d71e209131cea7ab80 |
| SIA | 1.1 | Not recorded | 68fa78d71e209131cea7ab80 |
| IdiomKB | 1.07 | Not recorded | 68fa78d71e209131cea7ab80 |
| Direct | 1.03 | Not recorded | 68fa78d71e209131cea7ab80 |
| LIA | 0.97 | Not recorded | 68fa78d71e209131cea7ab80 |

### IdiomCE

GPT-4 Score: 1.76. Result ID: 6995a6513badfaffe6a3f610.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

Recorded evaluation configuration: {"Backbone":"Gemma2-9b-it"}. This record does not assert independent reproduction.

### IdiomKB

GPT-4 Score: 1.65. Result ID: 6995a6513badfaffe6a3f612.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ab1e209131cea52711.md>)

Recorded evaluation configuration: {"Backbone":"Gemma2-9b-it"}. This record does not assert independent reproduction.

### Direct

GPT-4 Score: 1.6. Result ID: 6995a6513badfaffe6a3f611.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

Recorded evaluation configuration: {"Backbone":"Gemma2-9b-it"}. This record does not assert independent reproduction.

### SIA

GPT-4 Score: 1.6. Result ID: 6995a6513badfaffe6a3f619.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e458.md>)

Recorded evaluation configuration: {"Backbone":"LLama-3.1-8B"}. This record does not assert independent reproduction.

### LIA

GPT-4 Score: 1.42. Result ID: 6995a6513badfaffe6a3f618.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e458.md>)

Recorded evaluation configuration: {"Backbone":"LLama-3.1-8B"}. This record does not assert independent reproduction.

### IdiomCE

GPT-4 Score: 1.29. Result ID: 6995a6513badfaffe6a3f615.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

Recorded evaluation configuration: {"Backbone":"LLama-3.1-8B"}. This record does not assert independent reproduction.

### Indictrans2

GPT-4 Score: 1.26. Result ID: 6995a6513badfaffe6a3f60a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71911e209131cea52070.md>)

Recorded evaluation configuration: {"Methods":"Direct"}. This record does not assert independent reproduction.

### SIA

GPT-4 Score: 1.23. Result ID: 6995a6513badfaffe6a3f614.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e458.md>)

Recorded evaluation configuration: {"Backbone":"Gemma2-9b-it"}. This record does not assert independent reproduction.

### NLLB-200

GPT-4 Score: 1.21. Result ID: 6995a6513badfaffe6a3f609.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d511e209131cea39201.md>)

Recorded evaluation configuration: {"Methods":"Direct"}. This record does not assert independent reproduction.

### IdiomKB

GPT-4 Score: 1.2. Result ID: 6995a6513badfaffe6a3f617.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ab1e209131cea52711.md>)

Recorded evaluation configuration: {"Backbone":"LLama-3.1-8B"}. This record does not assert independent reproduction.

### LIA

GPT-4 Score: 1.184. Result ID: 6995a6513badfaffe6a3f613.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e458.md>)

Recorded evaluation configuration: {"Backbone":"Gemma2-9b-it"}. This record does not assert independent reproduction.

### Direct

GPT-4 Score: 1.16. Result ID: 6995a6513badfaffe6a3f616.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

Recorded evaluation configuration: {"Backbone":"LLama-3.1-8B"}. This record does not assert independent reproduction.

### IdiomCE

GPT-4 Score: 1.15. Result ID: 6995a6513badfaffe6a3f60b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

Recorded evaluation configuration: {"Backbone":"LLama-3.2-3B"}. This record does not assert independent reproduction.

### SIA

GPT-4 Score: 1.1. Result ID: 6995a6513badfaffe6a3f60f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e458.md>)

Recorded evaluation configuration: {"Backbone":"LLama-3.2-3B"}. This record does not assert independent reproduction.

### IdiomKB

GPT-4 Score: 1.07. Result ID: 6995a6513badfaffe6a3f60d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ab1e209131cea52711.md>)

Recorded evaluation configuration: {"Backbone":"LLama-3.2-3B"}. This record does not assert independent reproduction.

### Direct

GPT-4 Score: 1.03. Result ID: 6995a6513badfaffe6a3f60c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

Recorded evaluation configuration: {"Backbone":"LLama-3.2-3B"}. This record does not assert independent reproduction.

### LIA

GPT-4 Score: 0.97. Result ID: 6995a6513badfaffe6a3f60e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78d71e209131cea7ab80.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e458.md>)

Recorded evaluation configuration: {"Backbone":"LLama-3.2-3B"}. This record does not assert independent reproduction.

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