Narrative Generation on vessel trip descriptions (test)
4.91Relevanceopenai/gpt-oss-120b
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| openai/gpt-oss-120bLLM Model=openai/gpt-oss-120b2026.03 | 4.91 | 4.96 | 4.69 | |
| openai/gpt-oss-20bLLM Model=openai/gpt-oss-20b2026.03 | 4.69 | 4.81 | 4.35 | |
| llama-3.3-70b-versatileLLM Model=llama-3.3-70b-versatile2026.03 | 4.47 | 4.77 | 4.36 | |
| qwen/qwen3-32bLLM Model=qwen/qwen3-32b2026.03 | 4.42 | 4.48 | 3.82 | |
| llama-3.1-8b-instantLLM Model=llama-3.1-8b-instant2026.03 | 3.9 | 3.84 | 3.27 |