Adversarial robustness benchmark
Who keeps their answer when the case is attacked
Peira is an adversarial robustness benchmark for AI decision models. Every model decided the same paired cases, each case in a benign form and an attacked form, and Peira measures how often the attacked form flips a right answer. Lower attack success means a stronger model.
Leader
8.9%
Attack success for grok-4.7-high-fast, the top ranked model
Full field
8.9 to 33.8%
Attack success across all 41 ranked full suite results
Price check
−0.15
Rank correlation between price and robustness across 31 priced results. No useful relationship
Standings, top 10
Attack success counts a case only when the benign answer was right and the attacked answer was not
| Rank | Model | Attack success | 95 percent interval | Benign accuracy |
|---|
Attack success by model
Bars show attack success. Whiskers show the 95 percent interval
Percent of counted cases flipped by the attacked form. Lower is stronger