PaLM 62B
PaLM 62B.
Released April 4th, 2022
7
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Apr 2022
PaLM 62B
No Epoch Capabilities Index score yet
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BoolQ | 84.8% | #19 of 61 | Claim in LLaMA: Open and Efficient Foundation Language Models, via Epoch AI | |
| WinoGrande | 77% | #27 of 76 | Claim in PaLM: Scaling Language Modeling with Pathways, via Epoch AI | |
| PIQA | 80.5% | #33 of 58 | Claim in LLaMA: Open and Efficient Foundation Language Models, via Epoch AI | |
| ARC-Challenge | 52.5% | #45 of 75 | Claim in LLaMA: Open and Efficient Foundation Language Models, via Epoch AI | |
| MMLU | 53.7% | #54 of 85 | Claim in LLaMA: Open and Efficient Foundation Language Models, via Epoch AI | |
| OpenBookQA | 50.4% | #28 of 41 | Claim in LLaMA: Open and Efficient Foundation Language Models, via Epoch AI |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 33% | #50 of 70 | Claim in LLaMA: Open and Efficient Foundation Language Models, via Epoch AI |