Long-Context Understanding on LongBench
Metric: Average Score (higher is better)
Metric: Average Score (higher is better)
| # | Model↕ | Average Score▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GALI(Llama3-8b-ins-4k-to-16k) | 46.22 | No | A Training-Free Length Extrapolation Approach fo... | 2025-02-04 | Code |
| 2 | GALI(Llama3-8b-ins-8k-to-32k) | 45.38 | No | A Training-Free Length Extrapolation Approach fo... | 2025-02-04 | Code |
| 3 | GALI(Llama3-8b-ins-8k-to-16k) | 45.17 | No | A Training-Free Length Extrapolation Approach fo... | 2025-02-04 | Code |