LAMBADA: leaderboard
Language modeling benchmark for broad context understanding and last-word prediction.
Metric: Score (%). Source: neosignal.io. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 2 70B Base | 78.9 | #1025 |
| 2 | Llama 3.1 405B | 77.7 | #466 |
| 3 | Llama 2 7B | 76.5 | #1520 |
| 4 | Qwen 3 235B A22B | 71.1 | #313 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=lambada · How It Works · Data refreshed daily, snapshot 2026-10-20.