PaLM 2-L: benchmark results
Provider: Google. Released 2023-05-10. Access: API.
Aggregate Rating 1459 ± 35, rank #3395 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BoolQ | 90.9 | Accuracy (%) | 98.7 |
| TriviaQA | 86.1 | Accuracy (%) | 92.1 |
| HellaSwag | 86.8 | Accuracy (%) | 90.8 |
| WinoGrande | 83 | Accuracy (%) | 86.2 |
| ARC Challenge (AI2) | 69.2 | Accuracy (%) | 67.1 |
| Epoch AI - ECI | 114.18 | ECI Score | 24.4 |
Interactive version: theaggregate.ai/model?slug=palm-2-l · How It Works · Data refreshed daily, snapshot 2026-11-08.