Modelica Agent Workflow Benchmark - Model Generation: leaderboard
Metric: Tasks passed (%; 50 Model Generation tasks: build a Modelica model from an engineering brief that must pass interface, model-check and simulation gates and a private behavioural contract; one fresh isolated run per task and harness-backend pair, the agent's explicit submission scored outside the loop; OpenModelica 1.26.1). Source: arxiv.org. Saturation forecast: Around April 2027. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Flash (0731) | 54 |
| 2 | Claude Sonnet 5 (Medium) | 52 |
Interactive version: theaggregate.ai/benchmark?slug=modelica-agent-workflow-benchmark-model-generation · How It Works · Data refreshed daily, snapshot 2026-09-29.