Large Language Model Inference on 8K context (test)
81.35Q ScoreDense
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| DenseModel=Qwen2.5-14B2026.05 | 81.35 | — | 151.6 | — | 1,690.9 | — | 0.014 | |
| SphKV (rep)Model=Qwen2.5-14B2026.05 | 81.01 | 34 | 239.4 | 1.58 | 1,083.7 | 35.9 | 0.009 | |
| DenseModel=GPT-oss2026.05 | 79.71 | — | 163.7 | — | 1,717.1 | — | 0.014 | |
| SphKV (rep)Model=GPT-oss2026.05 | 79.19 | 52 | 261.2 | 1.6 | 1,220.3 | 28.9 | 0.01 | |
| DenseModel=Llama-3.1-8B2026.05 | 74.2 | — | 173.4 | — | 1,658.3 | — | 0.013 | |
| SphKV (rep)Model=Llama-3.1-8B2026.05 | 73.84 | 37 | 268.5 | 1.55 | 1,262.3 | 23.9 | 0.01 |