ParsiEval (138 Questions): leaderboard
Metric: Accuracy (%, 138 questions). Source: github.com. 1 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | grok-4 | 81.88 |
Interactive version: theaggregate.ai/benchmark?slug=parsieval-138-questions · How It Works · Data refreshed daily, snapshot 2026-09-20.