LongListBench - Agentic CLI - Weighted F1: leaderboard
Models extract structured records from the same released OCR transcripts through agentic command-line tools. Exact-record F1 and weighted F1 measure extraction fidelity across the document corpus. The Agentic CLI track keeps a shared input protocol separate from raw-PDF extraction products and page-level pipelines. This board reports LongListBench - Agentic CLI - Weighted F1 using Weighted F1 (%).
Metric: Weighted F1 (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 99.73 | #22 |
| 2 | Claude Opus 4.8 | 99.42 | #39 |
| 3 | GPT-5.5 | 99.25 | #33 |
| 4 | GPT-5.6 Terra | 99.23 | #40 |
| 5 | GPT-5.6 Luna | 98.66 | #79 |
| 6 | Claude Fable 5 | 96.76 | #20 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=longlistbench-agentic-cli-weighted-f1 · How It Works · Data refreshed daily, snapshot 2026-11-05.