Grid Studies Base Models - PFBench: 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 2030. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol | 45.5 | #7 |
| 2 | GPT-5.6 Sol | 36.5 | #22 |
| 3 | Claude Sonnet 5.5 | 29.3 | #14 |
| 4 | Claude Fable 5.1 | 24.4 | #10 |
| 5 | Kimi K2.5 | 21.2 | #152 |
| 6 | Qwen3 Coder Next | 18.7 | #331 |
| 7 | DeepSeek V3.2 | 17.7 | #210 |
| 8 | GPT-OSS-120B | 17.5 | #346 |
| 9 | Mistral Large 3 | 16.8 | #410 |
| 10 | GLM-4.7 | 16.1 | #202 |
| 11 | Nova Pro | 14.1 | #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-pfbench · How It Works · Data refreshed daily, snapshot 2026-11-05.