Long-context Question Answering on MultifieldQA
88.6C ScoreClaude-3-sonnet
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Claude-3-sonnetCitation Strategy=LAC-S2024.09 | 88.6 | 88.1 | 101 | |
| Mistral-Large-InstructCitation Strategy=LAC-S2024.09 | 88 | 85.3 | 103 | |
| GLM-4Citation Strategy=LAC-S2024.09 | 87.6 | 88.1 | 99 | |
| LongCite-8BCitation Strategy=LAC-S2024.09 | 87 | 83.6 | 104 | |
| LongCite-9BCitation Strategy=LAC-S2024.09 | 84.1 | 83.3 | 101 | |
| GPT-4oCitation Strategy=LAC-S2024.09 | 84 | 88.3 | 95 | |
| Llama-3.1-70B-InstructCitation Strategy=LAC-S2024.09 | 78.4 | 78.3 | 100 | |
| GLM-4-9B-chatCitation Strategy=LAC-S2024.09 | 74.2 | 84.9 | 87 | |
| Llama-3.1-8B-InstructCitation Strategy=LAC-S2024.09 | 63.9 | 73.3 | 87 |