DSM-to-CLI: leaderboard
Metric: Mean judge votes (0-3): the average number of the three panel judges rating the DSM-to-CLI translation semantically correct, over 75 configuration cells; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 2.99 |
| 2 | Grok 4.1 Fast (Reasoning) | 2.66 |
| 3 | Gemini 2.5 Pro | 2.52 |
| 4 | GPT-5 | 2.51 |
| 5 | DeepSeek V3 Chat | 2.46 |
Interactive version: theaggregate.ai/benchmark?slug=dsm-to-cli · How It Works · Data refreshed daily, snapshot 2026-09-29.