CISA Dense - LongBench v2 (<32K): leaderboard
CISA v1 AppendixA, original Nemotron3Ultra550B-A55B dense attention on LongBench v2, dense-reference input-length cohort <32K; fixed cohorts across precision arms, four repeats per task. BF16 and NVFP4 weights remain distinct model configurations. Zero-prompt GraphWalks cohorts remain missing, never zero-valued scores. Reported metric: Native percentage score.
Metric: Native percentage score. Source: arxiv.org. Saturation forecast: Around February 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Nemotron 3 Ultra | 61.95 | #245 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=cisa-dense-longbench-v2-under-32k · How It Works · Data refreshed daily, snapshot 2026-11-05.