# Idiomatic Translation on Mixed Dataset en-hi

Source: [Idiomatic Translation on Mixed Dataset en-hi](<https://www.sota2.com/research/sota/idiomatic-translation-on-mixed-dataset-en-hi>)

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

Data updated: 2026-02-26T05:48:09.928Z

Evaluation of Idiomatic Translation performance using the Mixed Dataset en-hi, reporting LLM-eval 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 | Idiomatic Translation |
| Dataset (including any stated split) | Mixed Dataset en-hi |
| Metric | LLM-eval Score |
| Unit | SCALAR |
| 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

- [LLM-eval Score](<https://www.sota2.com/research/sota/idiomatic-translation-on-mixed-dataset-en-hi.md?metric=LLM-eval%20Score>): Higher is better; unit: SCALAR.

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

## Recorded results

| Method | LLM-eval Score | Result date | Report paper |
| --- | --- | --- | --- |
| IdiomCE | 2.39 | Not recorded | 68fa78d71e209131cea7ab80 |
| Direct | 2.14 | Not recorded | 68fa78d71e209131cea7ab80 |
| IdiomCE | 1.88 | Not recorded | 68fa78d71e209131cea7ab80 |
| IdiomCE | 1.655 | Not recorded | 68fa78d71e209131cea7ab80 |
| Direct | 1.6 | Not recorded | 68fa78d71e209131cea7ab80 |
| IdiomCE | 1.34 | Not recorded | 68fa78d71e209131cea7ab80 |
| Direct | 1.3 | Not recorded | 68fa78d71e209131cea7ab80 |
| Direct | 1.27 | Not recorded | 68fa78d71e209131cea7ab80 |
| Direct | 1.247 | Not recorded | 68fa78d71e209131cea7ab80 |
| Direct | 1.12 | Not recorded | 68fa78d71e209131cea7ab80 |

### IdiomCE

LLM-eval Score: 2.39. Result ID: 6995a6513badfaffe6a3f59e.

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

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

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

### Direct

LLM-eval Score: 2.14. Result ID: 6995a6513badfaffe6a3f59f.

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

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

### IdiomCE

LLM-eval Score: 1.88. Result ID: 6995a6513badfaffe6a3f59a.

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

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

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

### IdiomCE

LLM-eval Score: 1.655. Result ID: 6995a6513badfaffe6a3f59c.

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

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

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

### Direct

LLM-eval Score: 1.6. Result ID: 6995a6513badfaffe6a3f59b.

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

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

### IdiomCE

LLM-eval Score: 1.34. Result ID: 6995a6513badfaffe6a3f598.

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

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

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

### Direct

LLM-eval Score: 1.3. Result ID: 6995a6513badfaffe6a3f596.

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

Recorded evaluation configuration: {"Model":"NLLB-200"}. This record does not assert independent reproduction.

### Direct

LLM-eval Score: 1.27. Result ID: 6995a6513badfaffe6a3f59d.

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

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

### Direct

LLM-eval Score: 1.247. Result ID: 6995a6513badfaffe6a3f597.

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

Recorded evaluation configuration: {"Model":"Indictrans2"}. This record does not assert independent reproduction.

### Direct

LLM-eval Score: 1.12. Result ID: 6995a6513badfaffe6a3f599.

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

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

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