PaLM 2-M: benchmark results
Provider: Google. Access: API.
Aggregate Rating 1344 ± 31, rank #7854 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BoolQ | 88.6 | Accuracy (%) | 87.7 |
| HellaSwag | 84 | Accuracy (%) | 80.3 |
| WinoGrande | 79.2 | Accuracy (%) | 74.4 |
| TriviaQA | 81.7 | Accuracy (%) | 68.4 |
| ARC Challenge (AI2) | 64.9 | Accuracy (%) | 61.8 |
| OpenBookQA | 57.4 | Accuracy (%) | 54.8 |
| Epoch AI - ECI | 98.61 | ECI Score | 14.8 |
Interactive version: theaggregate.ai/model?slug=palm-2-m · How It Works · Data refreshed daily, snapshot 2026-11-08.