| Paper | Code | Prometheus-2 Answer Correctness | Rouge-L | AlignScore | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| GPT-4 Technical Report | ✓ Link | 3.4612 | 0.2266 | 0.1224 | GPT-4o-2024-08-06-128k | 2023-03-15 |
| Mistral 7B | ✓ Link | 3.4245 | 0.1922 | 0.0827 | Mistral-v02-7B-32k | 2023-10-10 |
| The Llama 3 Herd of Models | ✓ Link | 3.1673 | 0.2286 | 0.1016 | Llama-3-IT-8B-32k | 2024-07-31 |
| The Llama 3 Herd of Models | ✓ Link | 3.1102 | 0.2295 | 0.1098 | Llama-3-IT-8B-8k | 2024-07-31 |
| []() | 3.0571 | 0.2294 | 0.1362 | Command-R-v01-34B | ||
| Language Models are Few-Shot Learners | ✓ Link | 3.0408 | 0.2414 | 0.1378 | GPT-3.5-Turbo-0613-16k | 2020-05-28 |