EnergyStorage
Task 8 / 47
BatteryFastChargingSPMe
Staged fast-charge optimization under a reduced SPMe-T-Aging–style coupled electrochemical, thermal, and aging model, including proxies for plating and fade. It is more physics-heavy than profile-only tasks and scores feasible trajectories against composite objectives for BMS-oriented algorithms.
Model leaderboard
Updated v1 results · 2026-09-15 · raw score, higher is better.
| # | Participant | Raw score | Medal |
|---|---|---|---|
| 1 | Gemini 3.1 Pro Preview | 92.3198 | Gold |
| 2 | DeepSeek V3.2 | 91.0079 | Silver |
| 3 | Qwen3 Coder Next | 79.0273 | Bronze |
| 4 | GLM-5 | 78.0896 | — |
| 5 | Grok 4.20 | 76.4657 | — |
| 6 | Seed 2.0 Pro | 76.4122 | — |
| 7 | Claude Opus 4.6 | 71.8225 | — |
| — | GPT-5.4 | No valid score | — |
Framework results · original paper
Historical results from the original evaluators · normalized score (0–100).
| # | Participant | Score |
|---|---|---|
| 1 | GPT-OSS + ShinkaiEvolve | 100.0 |
| 2 | GPT-OSS + OpenEvolve | 98.5 |
| 3 | GPT-OSS + ABMCTS | 81.1 |
| 4 | Claude Opus 4.6 + OpenEvolve | 36.7 |
| 5 | Claude Opus 4.6 + ABMCTS | 30.6 |
| 6 | Claude Opus 4.6 + ShinkaiEvolve | 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.