Grid Studies Base Models - PowerCodeBench: leaderboard
Grid Studies AppendixC Table 8:519 power-system tasks, native end-to-end score E, original units and equal source protocol. Only standalone no-tool completions are selected from the explicitly labelled base-model sections; base here means no tools, not pretrained checkpoint. Framework/tool-system rows are distinct and not attributed to their backend models. Scores verify required work against deterministic benchmark targets; timing excluded. Metric: End-to-end score E (%).
Metric: End-to-end score E (%). Source: arxiv.org. Saturation forecast: Around 2032. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol | 42.9 | #7 |
| 2 | GPT-5.6 Sol | 35 | #22 |
| 3 | Claude Sonnet 5.5 | 24.2 | #14 |
| 4 | DeepSeek V3.2 | 20.3 | #210 |
| 5 | GPT-OSS-120B | 20 | #346 |
| 6 | Kimi K2.5 | 18.7 | #152 |
| 7 | GLM-4.7 | 18.6 | #202 |
| 8 | Qwen3 Coder Next | 18 | #331 |
| 9 | Mistral Large 3 | 17.4 | #410 |
| 10 | Claude Fable 5.1 | 14.8 | #10 |
| 11 | Nova Pro | 14.3 | #594 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=grid-studies-base-models-powercodebench · How It Works · Data refreshed daily, snapshot 2026-11-05.