LAMBADA
Rank #51 of 51 · 20 models scored · top score 79.8
unknown
Strongest on saturation headroom, weakest on contamination resistance. Caveat: scores come from mixed harnesses, so a head-to-head is not apples-to-apples.
Weighted composite. Each signal is computed from the source-backed leaderboard below.
Does it still separate models?
How far from ceiling / clustered at the top?
Public vs held-out; training-leak risk.
Apples-to-apples, or mixed / vendor-optimized?
How old is the benchmark?
| # | Model | Score | Evidence | Measured |
|---|---|---|---|---|
| 1 | Falcon-180B | 79.8 | unverified· optimized | 2023-09-06 |
| 2 | Llama 2-70B | 78.9 | self-reported· optimized | 2023-07-18 |
| 3 | LLaMA-65B | 77.7 | self-reported· optimized | 2023-02-24 |
| 4 | Falcon-40B | 77.3 | unverified· optimized | 2023-03-15 |
| 5 | LLaMA-33B | 77.2 | self-reported· optimized | 2023-02-27 |
| 6 | Llama 2-13B | 76.5 | self-reported· optimized | 2023-07-18 |
| 7 | LLaMA-13B | 75.2 | self-reported· optimized | 2023-02-27 |
| 8 | Falcon-7B | 74.9 | unverified· optimized | 2023-04-24 |
| 9 | Baichuan2-13B | 74 | self-reported· optimized | 2023-09-06 |
| 10 | LLaMA-7B | 73.3 | self-reported· optimized | 2023-02-24 |
| 11 | Llama 2-7B | 73.3 | self-reported· optimized | 2023-07-18 |
| 12 | Baichuan 2-7B | 73.3 | self-reported· optimized | 2023-09-20 |
| 13 | internlm-20b | 71.8 | self-reported· optimized | 2023-09-18 |
| 14 | Stable Beluga 2 | 71.3 | self-reported· optimized | 2023-07-20 |
| 15 | Qwen-14B | 71.1 | self-reported· optimized | 2023-09-24 |
| 16 | MPT-7B | 70 | self-reported· optimized | 2023-05-05 |
| 17 | Qwen-7B | 67.9 | self-reported· optimized | 2023-09-28 |
| 18 | internlm-7b | 67 | self-reported· optimized | 2023-07-05 |
| 19 | Qwen-1_8B | 58.4 | self-reported· optimized | 2023-11-30 |
| 20 | chatglm2-6b | 54.3 | self-reported· optimized | 2023-06-24 |