QuantumComputing
Task 33 / 47
task_03_cross_target_qaoa
Cross-target robust optimization for QAOA-style variational parameters across instances or perturbations, improving mean or worst-case objective values. It captures robustness needs for VQAs when problem instances or noise conditions shift—an engineering angle on quantum heuristic performance.
Model leaderboard
Updated v1 results · 2026-09-15 · raw score, higher is better.
| # | Participant | Raw score | Medal |
|---|---|---|---|
| 1 | Gemini 3.1 Pro Preview | 1.680392 | Gold |
| — | Claude Opus 4.6 | No valid score | — |
| — | DeepSeek V3.2 | No valid score | — |
| — | GLM-5 | No valid score | — |
| — | GPT-5.4 | No valid score | — |
| — | Grok 4.20 | No valid score | — |
| — | Qwen3 Coder Next | No valid score | — |
| — | Seed 2.0 Pro | No valid score | — |
Framework results · original paper
Historical results from the original evaluators · normalized score (0–100).
| # | Participant | Score |
|---|---|---|
| 1 | GPT-OSS + OpenEvolve | 100.0 |
| 2 | GPT-OSS + ShinkaiEvolve | 99.8 |
| 3 | GPT-OSS + ABMCTS | 99.7 |
| 4 | Claude Opus 4.6 + ShinkaiEvolve | 18.4 |
| 5 | Claude Opus 4.6 + ABMCTS | 0.0 |
| 6 | Claude Opus 4.6 + OpenEvolve | 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.