| Benchmark | Model | Rank | Results |
|---|---|---|---|
| question-answering-on-natural-questions | ChatQA-1.5-llama3-70b (Zero-Shot, KILT) | – | EM: 47.0 |
| question-answering-on-natural-questions | ChatQA-1.5-llama3-8b (Zero-Shot, KILT) | – | EM: 42.7 |
| question-answering-on-triviaqa | ChatQA-1.5-llama3-70b (Zero-Shot, DPR) | – | EM: 69.0 |
| question-answering-on-triviaqa | ChatQA-1.5-llama3-70b (Zero-Shot, KILT) | – | EM: 85.6 |
| question-answering-on-triviaqa | ChatQA-1.5-llama3-8B (Zero-Shot, KILT) | – | EM: 81.0 |