FinPerMA: leaderboard
FinPerMA (Wang et al., 2026) tests whether an LLM agent keeps and updates a personalized model of an investor over long, event-driven advisory dialogues, including checkpoints after material events that should change the preferences of the investor. Accuracy in percent over 2,994 questions, 2,494 six-option multiple-choice and 500 open-ended ones judged by a three-judge ensemble, with the full dialogue history supplied; higher is better.
Metric: Accuracy (%; share of the 2,494 six-option multiple-choice questions answered with the gold option and the 500 open-ended questions judged correct by majority vote of a three-judge cross-vendor ensemble; full_context setting: the model receives every prior dialogue turn of the investor persona verbatim; 2,994 questions from 276 synthetic investor personas with frozen event timelines, including Post-Shock checkpoints after material events; provider-default system prompt, single seed). Source: arxiv.org. Saturation forecast: Around September 2028. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 46.6 | #56 |
| 2 | GLM-5.2 | 45.6 | #138 |
| 3 | Gemini 3.1 Pro (Preview) | 44.9 | #94 |
| 4 | DeepSeek V4 Pro | 44.5 | #188 |
| 5 | Qwen 3.7 Max | 43.6 | #145 |
| 6 | GPT-5.6 Sol | 40.1 | #30 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=finperma · How It Works · Data refreshed daily, snapshot 2026-11-13.