Long-context understanding on RULER (Delta Accuracy)
0.015Delta AccuracyRuntime-Certified Bounded-Error Quantized Attention
Evaluation results
| Method | Links | |
|---|---|---|
| Runtime-Certified Bounded-Error Quantized AttentionContext Length=64K2026.05 | 0.015 | |
| Runtime-Certified Bounded-Error Quantized AttentionContext Length=128K2026.05 | 0.004 | |
| Runtime-Certified Bounded-Error Quantized AttentionContext Length=32K2026.05 | -0.019 | |
| Runtime-Certified Bounded-Error Quantized AttentionContext Length=8K2026.05 | -0.069 |