PyPortfolioOpt
Task 30 / 47
robust_mvo_rebalance
Robust mean-variance portfolio rebalancing under estimation uncertainty plus sector/factor/turnover constraints to improve out-of-sample or worst-case risk-return trade-offs. Convex robustification meets practical trading limits; scoring uses benchmark return/covariance data and constraint slacks.
Model leaderboard
Updated v1 results · 2026-09-15 · raw score, higher is better.
| # | Participant | Raw score | Medal |
|---|---|---|---|
| 1 | GPT-5.4 | 99.994604 | Gold |
| 2 | Claude Opus 4.6 | 99.9946 | Silver |
| 3 | Grok 4.20 | 99.983 | Bronze |
| 4 | Qwen3 Coder Next | 85.5194 | — |
| 5 | DeepSeek V3.2 | 84.941 | — |
| 6 | Seed 2.0 Pro | 83.0681 | — |
| 7 | GLM-5 | 82.8015 | — |
| 8 | Gemini 3.1 Pro Preview | 77.165 | — |
Framework results · original paper
Historical results from the original evaluators · normalized score (0–100).
| # | Participant | Score |
|---|---|---|
| 1 | Claude Opus 4.6 + OpenEvolve | 100.0 |
| 2 | Claude Opus 4.6 + ShinkaiEvolve | 100.0 |
| 3 | Claude Opus 4.6 + ABMCTS | 100.0 |
| 4 | GPT-OSS + OpenEvolve | 100.0 |
| 5 | GPT-OSS + ShinkaiEvolve | 40.0 |
| 6 | GPT-OSS + ABMCTS | 0.0 |
Model results use the updated scores and medal thresholds. No valid score earns zero medal credit. Historical framework scores use the original evaluators and have not been updated alongside the model results.