CEO-Bench — leaderboard
Metric: Best run API cost (self-reported). Source: benchmarklist.com. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 | 213.41 |
| 2 | GPT-5.5 | 200.49 |
| 3 | Claude Opus 4.7 | 128.72 |
| 4 | Claude Sonnet 4.6 | 82.84 |
| 5 | Claude Haiku 4.5 | 6.68 |
| 6 | Gemini 3 Flash (Preview) | 2.98 |
| 7 | Grok 4.20 | 0.75 |
| 8 | GLM-5.1 | 0 |
| 9 | DeepSeek V4 Pro | 0 |
Interactive version: theaggregate.ai/benchmark?slug=ceo-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.