ANLI
ANLI (Adversarial NLI) · adversarially constructed natural language inference dataset where each round targets weaknesses found in previous model generations.
The Frontier
Best score over time · one chart, every benchmark
完整排名
9 已测试模型 · 按分数排序
| # | 模型 | 分数 |
|---|---|---|
| 1 | 37.1 | |
| 2 | 37.1 | |
| 3 | 36.0 | |
| 4 | 33.7 | |
| 5 | 32.8 | |
| 6 | 29.2 | |
| 7 | 23.1 | |
| 8 | 20.6 | |
| 9 | 13.8 |
分数分布
模型聚集位置
关联基准测试
Pearson r · 原创研究
Benchmarks that track with ANLI
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
常见问题
About ANLI
What does ANLI measure?
ANLI (Adversarial NLI) · adversarially constructed natural language inference dataset where each round targets weaknesses found in previous model generations. 9 AI models have been tested on it. Scores range from 13.8 to 37.1 out of 100.
Which model leads on ANLI?
GPT-3.5 Turbo (older v0613) from OpenAI leads ANLI with a score of 37.1. The median score across 9 tested models is 32.8.
Is ANLI saturated?
No · the top score is 37.1 out of 100 (37%). There is still meaningful room for improvement on ANLI.
Does ANLI predict performance on other benchmarks?
Yes · ANLI scores correlate 0.87 with Winogrande across 9 shared models. Models that do well on ANLI tend to do well on Winogrande.
How often is ANLI data refreshed?
BenchGecko pulls updates daily. New model scores on ANLI appear as soon as they are published by Epoch AI or the model provider.
- 类别
- Reasoning
- 最高分
- 100
- 模型
- 9
- 已更新
- 2024-04-18
更多 reasoning 基准测试
同类别 · 相关评测