ShiJianBench - Investor Outcome: leaderboard
ShiJianBench (2026) places an LLM investment advisor in conversation with 27 simulated investors, a multi-agent simulator calibrated on 7,199 real users, while Chinese public-fund history from 2021 to 2026 replays, and scores each advisor against a matched rollout without advice. This component scores the uplift in returns and drawdown control of the advised investors over the full horizon, on a 0-100 scale; higher is better.
Metric: Investment score (0-100): 0.6 x return-uplift + 0.4 x drawdown-reduction scores of the advised investors against the matched no-advisor rollout, full horizon, over five matched runs of 27 simulated investors (risk profile x financial literacy x asset tier, weighted by 7,199 real users) in an LLM investor simulator replaying Chinese public-fund market traces, with GPT-4o judging advisor messages. Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 64.1 | #167 |
| 2 | DeepSeek V4 Flash | 64.09 | #258 |
| 3 | Claude Sonnet 4.6 | 64.08 | #161 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=shijianbench-investor-outcome · How It Works · Data refreshed daily, snapshot 2026-11-13.