Back to BenchmarksEasy
LAMBADA
Language modeling and broad context understanding
Leaderboard
(5 models)| Rank | Model | Score | Stderr |
|---|---|---|---|
| 1 | falcon-180B | 79.80 | — |
| 2 | Llama-2-70b-hf | 78.90 | — |
| 3 | Llama 3.1 405B | 77.70 | — |
| 4 | Llama-2-7b | 76.50 | — |
| 5 | Qwen 3 235B | 71.10 | — |
Data source: Epoch AI, “Data on AI Benchmarking”. Published at epoch.ai
Licensed under CC-BY 4.0