Question Answering On Peerqa
Metrics
AlignScore
Prometheus-2 Answer Correctness
Rouge-L
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | AlignScore | Prometheus-2 Answer Correctness | Rouge-L |
|---|---|---|---|
| language-models-are-few-shot-learners | 0.1378 | 3.0408 | 0.2414 |
| mistral-7b | 0.0827 | 3.4245 | 0.1922 |
| Model 3 | 0.1362 | 3.0571 | 0.2294 |
| gpt-4-technical-report-1 | 0.1224 | 3.4612 | 0.2266 |
| the-llama-3-herd-of-models | 0.1098 | 3.1102 | 0.2295 |
| the-llama-3-herd-of-models | 0.1016 | 3.1673 | 0.2286 |