LongCat 2.5 Release - SpreadsheetBench 2: leaderboard
LongCat-2.5 final release detailed native result table, November 2026. External:true cells are explicitly cited other-evaluator results and excluded from this component; self-run numeric cells retained. No Preview/final or release-generation aliases. Detailed table used instead of inconsistent rounded headline charts. SpreadsheetBench 2: Claude Code harness (v 2.1.116), scoring follows the benchmark's official protocol; the Visualization subset is judged by gemini-3.6-flash, with charts rendered on Linux via headless LibreOffice (UNO object-level export) and a pure-Python OOXML/Pillow renderer as fallback. Metric: Score (%).
Metric: Score (%). Source: longcat.ai. Saturation forecast: Around 2030. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5.3 | 35.8 | #44 |
| 2 | GPT-5.6 Sol | 33.3 | #22 |
| 3 | Claude Opus 5 | 33 | #16 |
| 4 | DeepSeek V4.1 Flash | 33 | #37 |
| 5 | GPT-5.5 | 30.2 | #33 |
| 6 | LongCat 2.0 | 24.1 | #220 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=longcat-2-5-release-spreadsheetbench-2 · How It Works · Data refreshed daily, snapshot 2026-11-05.