KV Cache Study Native QA - HotpotQA: leaderboard
KV Cache Study Native QA - HotpotQA: Token F1 over 100 examples (%). KV cache updates arXiv 2611.14051v1: native Source and Target use each checkpoint for both prefix and continuation; cross-cache Reuse/Mapper are not native model observations. Six NIAH prefix lengths each have eight histories x24 queries=192. Native unmodified GLM-5.2/5.3, DeepSeek V4.1 Flash/1017, DeepSeek V4 Flash/0731 and Qwen3-30B-A3B/Instruct-2507 remain distinct checkpoints. Free generation greedy. Table 8 is the separate 585-example BABILong/QA cohort. No base/instruct merge and no reuse accuracy attributed to native model.
Metric: Token F1 over 100 examples (%). Source: arxiv.org. Saturation forecast: Around February 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V4 Flash | 69.4 | #254 |
| 2 | DeepSeek V4 Flash (0731) | 69.3 | #136 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=kv-cache-study-native-qa-hotpotqa · How It Works · Data refreshed daily, snapshot 2026-11-12.