Megatron-Turing NLG 530B
Megatron-Turing NLG 530B ranks first on LAMBADA.
6
Benchmarks with a score
1
Ranked first, out of five or more models
1
In the top three
Megatron-Turing NLG 530B
Closed weights
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 | |
|---|---|---|---|---|
| LAMBADA | 87.2% | #1 of 26 | Claim in Using DeepSpeed and Megatron to Train Megatron-Turing NLG…, via Epoch AI | |
| PIQA | 83.2% | #13 of 58 | Claim in Using DeepSpeed and Megatron to Train Megatron-Turing NLG…, via Epoch AI | |
| WinoGrande | 78.9% | #21 of 76 | Claim in GLaM: Efficient Scaling of Language Models with Mixture-o…, via Epoch AI | |
| BoolQ | 84.8% | #18 of 61 | Claim in Using DeepSpeed and Megatron to Train Megatron-Turing NLG…, via Epoch AI | |
| HellaSwag | 82.4% | #19 of 63 | Claim in GLaM: Efficient Scaling of Language Models with Mixture-o…, via Epoch AI | |
| ANLI | 39.7% | #10 of 11 | Claim in Using DeepSpeed and Megatron to Train Megatron-Turing NLG…, via Epoch AI |