BlueFin - Manipulation: leaderboard
Metric: Criteria-weighted rubric score (%; points met over maximum points of expert rubrics checked by an agentic GPT-5.4 judge for synthesis and manipulation workbooks, answer correctness for interrogation, non-completions count as zero; 20-tool spreadsheet harness, high reasoning effort; 75 held-out tasks modifying an existing financial model). Source: arxiv.org. Saturation forecast: Around May 2028. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 (High) | 49.4 |
| 2 | GPT-5.5 (High) | 48.2 |
| 3 | Gemini 3.1 Pro (Preview) (High) | 46.1 |
| 4 | Claude Sonnet 4.6 (High) | 43 |
Interactive version: theaggregate.ai/benchmark?slug=bluefin-manipulation · How It Works · Data refreshed daily, snapshot 2026-09-26.