EnergyStorage
Task 7 / 47
BatteryFastChargingProfile
Optimize time-varying fast-charge current profiles for a Li-ion cell under voltage, thermal, and degradation-style constraints to reduce charge time while limiting aging risk. It couples optimal control with reduced electrochemical models and scores constraint slack versus charging objectives.
Model leaderboard
Updated v1 results · 2026-09-15 · raw score, higher is better.
| # | Participant | Raw score | Medal |
|---|---|---|---|
| 1 | GPT-5.4 | 121.8416 | Gold |
| 2 | Claude Opus 4.6 | 120.8025 | Silver |
| 3 | GLM-5 | 118.7678 | Bronze |
| 4 | Gemini 3.1 Pro Preview | 116.6532 | — |
| 5 | Seed 2.0 Pro | 115.6882 | — |
| 6 | DeepSeek V3.2 | 111.4518 | — |
| 7 | Grok 4.20 | 99.6875 | — |
| 8 | Qwen3 Coder Next | 89.8416 | — |
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 + ABMCTS | 78.1 |
| 3 | GPT-OSS + OpenEvolve | 77.3 |
| 4 | GPT-OSS + ABMCTS | 54.6 |
| 5 | GPT-OSS + ShinkaiEvolve | 30.9 |
| 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.