Silent Cue Loss - Untyped: leaderboard
Silent Cue Loss:cross-model appendix, 76–79 documents per model, formatting-aware document QA; Untyped serialization, temperature 0. Corpus size differs slightly by completed run; reported micro F1 retained,per-document significance is not a capability score. Micro F1 (0–1).
Metric: Micro F1 (0–1). Source: arxiv.org. Saturation forecast: Not forecast. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 0.61 | #63 |
| 2 | Claude Sonnet 4.6 | 0.58 | #92 |
| 3 | Claude Haiku 4.5 | 0.53 | #282 |
| 4 | GPT-5.6 Terra | 0.47 | #40 |
| 5 | Claude Opus 5 | 0.35 | #12 |
| 6 | Claude Sonnet 5 | 0.17 | #57 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=silent-cue-loss-untyped · How It Works · Data refreshed daily, snapshot 2026-10-23.