CUA-bench — eFootball
Agents · 2026-09-18
Ordered-milestone progress on eFootball within three hours.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5.1 | 30.0 |
| GPT-6 Astra | 30.0 |
| Claude Opus 5.5 | 0.0 |
| Claude Opus 5 | 0.0 |
| Gemini 3.8 Flash | 0.0 |
| Gemini 4 Argon | 0.0 |
| GPT-5.6 Sol | 0.0 |
| Muse Spark 1.3 | 0.0 |
| Muse Wonder | 0.0 |