CEO-Bench: leaderboard
Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real-world challenges require a combination of sophisticated skills that remain largely untested in agents: (1) navigating long horizons amid uncertainty; (2) acquiring information in noisy environments; (3) adapting to a changing world; (4) orchestrating
Metric: Max final cash ($) (self-reported). Source: benchmarklist.com. Saturation forecast: Around June 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 27776973 | #37 |
| 2 | GPT-5.5 | 21297707 | #31 |
| 3 | Claude Opus 4.7 | 389959 | #49 |
| 4 | Kimi K2.6 | 98050 | #104 |
| 5 | Claude Sonnet 4.6 | 69766 | #90 |
| 6 | Claude Haiku 4.5 | 0 | #280 |
| 7 | Gemini 3 Flash | 0 | #99 |
| 8 | DeepSeek V4 Pro | 0 | #102 |
| 9 | GLM-5.1 | 0 | #97 |
| 10 | Grok 4.20 | 0 | #175 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=ceo-bench · How It Works · Data refreshed daily, snapshot 2026-10-20.