CEO-Bench - Mean Survival Days: leaderboard
Metric: Mean days survived before bankruptcy (out of 500) over three 500-day CEO-Bench simulations of a startup starting with $1M cash (seed 42), the agent writing code against 34 tools and a 19-table business database at the maximum reasoning effort the model provides; a run that avoids bankruptcy counts 500; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.5 Flash (High) | 500 |
| 2 | Qwen 3.7 Max (Thinking) | 500 |
| 3 | Claude Sonnet 5 (Max) | 470.7 |
| 4 | Claude Fable 5 (Max) | 461.7 |
| 5 | Claude Sonnet 4.6 (Max) | 419.3 |
| 6 | Claude Opus 4.7 (Max) | 414.3 |
| 7 | GPT-5.5 (xHigh) | 401 |
| 8 | Claude Opus 4.8 (Max) | 378 |
| 9 | GLM-5.2 (Max) | 376.7 |
| 10 | GPT-5.6 Sol (Max) | 294 |
| 11 | Claude Haiku 4.5 (Thinking) | 286.3 |
| 12 | Gemini 3 Flash (High) | 137 |
| 13 | DeepSeek V4 Pro (Max) | 136.3 |
| 14 | Grok 4.20 (Reasoning) | 36 |
Interactive version: theaggregate.ai/benchmark?slug=ceo-bench-mean-survival-days · How It Works · Data refreshed daily, snapshot 2026-09-29.