# Narrative Generation on vessel trip descriptions (test)

Source: [Narrative Generation on vessel trip descriptions (test)](<https://www.sota2.com/research/sota/narrative-generation-on-vessel-trip-descriptions-test>)

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

Data updated: 2026-03-16T08:39:39.316Z

Evaluation of narrative generation models on the test split of the vessel trip descriptions dataset, assessed using metrics such as relevance, faithfulness, and correctness.

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 | Narrative Generation |
| Dataset (including any stated split) | vessel trip descriptions (test) |
| Metric | Relevance |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Relevance](<https://www.sota2.com/research/sota/narrative-generation-on-vessel-trip-descriptions-test.md?metric=Relevance>): Higher is better; unit: SCALAR.

- [Faithfulness](<https://www.sota2.com/research/sota/narrative-generation-on-vessel-trip-descriptions-test.md?metric=Faithfulness>): Higher is better; unit: SCALAR.

- [Correctness](<https://www.sota2.com/research/sota/narrative-generation-on-vessel-trip-descriptions-test.md?metric=Correctness>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Relevance | Result date | Report paper |
| --- | --- | --- | --- |
| openai/gpt-oss-120b | 4.91 | Not recorded | 69b78e8f0636e5bf4afbdbe0 |
| openai/gpt-oss-20b | 4.69 | Not recorded | 69b78e8f0636e5bf4afbdbe0 |
| llama-3.3-70b-versatile | 4.47 | Not recorded | 69b78e8f0636e5bf4afbdbe0 |
| qwen/qwen3-32b | 4.42 | Not recorded | 69b78e8f0636e5bf4afbdbe0 |
| llama-3.1-8b-instant | 3.9 | Not recorded | 69b78e8f0636e5bf4afbdbe0 |

### openai/gpt-oss-120b

Relevance: 4.91. Result ID: 69b7c1b547f34ce9249f6aac.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e8f0636e5bf4afbdbe0.md>)

Recorded evaluation configuration: {"LLM Model":"openai/gpt-oss-120b"}. This record does not assert independent reproduction.

### openai/gpt-oss-20b

Relevance: 4.69. Result ID: 69b7c1b547f34ce9249f6aab.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e8f0636e5bf4afbdbe0.md>)

Recorded evaluation configuration: {"LLM Model":"openai/gpt-oss-20b"}. This record does not assert independent reproduction.

### llama-3.3-70b-versatile

Relevance: 4.47. Result ID: 69b7c1b547f34ce9249f6aa9.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e8f0636e5bf4afbdbe0.md>)

Recorded evaluation configuration: {"LLM Model":"llama-3.3-70b-versatile"}. This record does not assert independent reproduction.

### qwen/qwen3-32b

Relevance: 4.42. Result ID: 69b7c1b547f34ce9249f6aaa.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e8f0636e5bf4afbdbe0.md>)

Recorded evaluation configuration: {"LLM Model":"qwen/qwen3-32b"}. This record does not assert independent reproduction.

### llama-3.1-8b-instant

Relevance: 3.9. Result ID: 69b7c1b547f34ce9249f6aa8.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e8f0636e5bf4afbdbe0.md>)

Recorded evaluation configuration: {"LLM Model":"llama-3.1-8b-instant"}. This record does not assert independent reproduction.

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