PortBench-QA - Max-Sharpe Allocation: leaderboard
Metric: Item score (%; long-only maximum-Sharpe weights for three or more assets with supplied means and covariances, 50 test questions per model). Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Pro (Thinking) | 99.2 |
| 2 | Qwen 3.7 Max (Thinking) | 95.4 |
| 3 | DeepSeek V4 Flash (Thinking) | 93.2 |
| 4 | Qwen 3.6 Plus (Thinking) | 80.4 |
| 5 | GLM-5.1 (Thinking) | 42.1 |
| 6 | Kimi K2.6 (Thinking) | 28 |
| 7 | Qwen 3.6 35B A3B (Thinking) | 23 |
Interactive version: theaggregate.ai/benchmark?slug=portbench-qa-max-sharpe-allocation · How It Works · Data refreshed daily, snapshot 2026-09-26.