Aerodynamics
Task 1 / 47
CarAerodynamicsSensing
Optimize pressure-sensor locations on a 3D car surface to reconstruct the pressure field or aerodynamic coefficients from sparse measurements. CFD-backed or precomputed fields link to optimal experimental design; scoring quantifies reconstruction error under a sensor budget—sparse sensing for automotive aerodynamics.
Model leaderboard
Updated v1 results · 2026-09-15 · raw score, higher is better.
| # | Participant | Raw score | Medal |
|---|---|---|---|
| 1 | DeepSeek V3.2 | 0.9632 | Gold |
| 1 | Gemini 3.1 Pro Preview | 0.9632 | Gold |
| 1 | Qwen3 Coder Next | 0.9632 | Gold |
| 4 | GPT-5.4 | 0.96306958 | — |
| 5 | GLM-5 | 0.9628 | — |
| 6 | Claude Opus 4.6 | 0.9624 | — |
| 6 | Grok 4.20 | 0.9624 | — |
| 6 | Seed 2.0 Pro | 0.9624 | — |
Framework results · original paper
Historical results from the original evaluators · normalized score (0–100).
| # | Participant | Score |
|---|---|---|
| 1 | GPT-OSS + ABMCTS | 100.0 |
| 2 | GPT-OSS + ShinkaiEvolve | 99.6 |
| 3 | GPT-OSS + OpenEvolve | 97.4 |
| 4 | Claude Opus 4.6 + OpenEvolve | 97.0 |
| 5 | Claude Opus 4.6 + ShinkaiEvolve | 94.4 |
| 6 | Claude Opus 4.6 + 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.