SIMMER - Failures per Plan: leaderboard
Metric: Mean number of failures of any kind per plan (count, unbounded above); each model writes a complete cooking plan for 100 kitchen tasks with the baseline prompt (no refinement), and the plan is executed step by step in a human-curated symbolic world model (77 actions, 262 objects) whose state machine flags immediate failures (violated preconditions) and latent failures (valid steps that leave hazardous or corrupted state); lower is better. Source: arxiv.org. Saturation forecast: Around June 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 2.47 |
| 2 | GPT-5.4 (Low) | 2.86 |
| 3 | Claude Opus 4.6 | 3.7 |
| 4 | Qwen 3.5 27B (Non-reasoning) | 6.15 |
| 5 | Llama 3.3 70B Instruct | 6.53 |
| 6 | DeepSeek V3.2 (Non-reasoning) | 6.54 |
Interactive version: theaggregate.ai/benchmark?slug=simmer-failures-per-plan · How It Works · Data refreshed daily, snapshot 2026-09-29.