FinPerMA - Multiple Choice: leaderboard
Metric: Accuracy (%; share of the 2,494 six-option multiple-choice questions whose selected option content matches the gold option, scored deterministically; chance 16.7%; 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 2030. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 | 39.1 |
| 2 | GLM-5.2 | 39 |
| 3 | Gemini 3.1 Pro (Preview) | 38.7 |
| 4 | Qwen 3.7 Max | 38.3 |
| 5 | DeepSeek V4 Pro | 37.9 |
| 6 | GPT-5.6 Sol | 31 |
Interactive version: theaggregate.ai/benchmark?slug=finperma-multiple-choice · How It Works · Data refreshed daily, snapshot 2026-09-29.