LongBench-v2 longbench-v2 Leaderboard
Auto-discovered from papers reporting LongBench-v2 (accuracy). · Metric: accuracy (higher is better) · 🟢 Updated 2h ago
| # | Model | accuracy | Paper |
|---|---|---|---|
| 1 | Self-Guided Test-Time Training for Long-Context LLMs | 15.00 | link |
| 2 | FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention | 0.60 | link |