FinPerMA: leaderboard

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 2029. 7 models tracked.

Top models

#ModelScore
1Claude Opus 4.846.6
2GLM-5.245.6
3Gemini 3.1 Pro (Preview)44.9
4DeepSeek V4 Pro44.5
5Qwen 3.7 Max43.6
6GPT-5.6 Sol40.1

Interactive version: theaggregate.ai/benchmark?slug=finperma · How It Works · Data refreshed daily, snapshot 2026-09-29.