RLTasksby ulam.ai
Models / Stability AI

Stability AI / MODEL EVIDENCE

Stable Beluga 2

9 benchmarks · 10 observations · 3 sources · released 2023-07-20

Scores at a glance

9 benchmarks · large dot: Stable Beluga 2; small dots: closest models where reported

ARC AI2 ↗86.1%
32.586.1

Stable Beluga 2 · ARC AI2 · Challenge score · % ↗

GSM8K ↗69.6%
6.891.4

Stable Beluga 2 · GSM8K · EM · % ↗

HellaSwag ↗84.1%
5785.3

Stable Beluga 2 · HellaSwag · Overall accuracy · % ↗

MMLU ↗68.6%
26.269.8

Stable Beluga 2 · MMLU · EM · % ↗

PIQA ↗83.3%
69.683.3

Stable Beluga 2 · PIQA · Score · % ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

14.5 percentile-point gap

8 of 8 shared benchmark comparisons

18.8 percentile-point gap

7 of 8 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. Qwen Technical Report ↗

    Bai, Jinze, Bai, Shuai, Chu, Yunfei, Cui, Zeyu, Dang, Kai, Deng, Xiaodong et al. · 2023

    All 48 authors

    Bai, Jinze, Bai, Shuai, Chu, Yunfei, Cui, Zeyu, Dang, Kai, Deng, Xiaodong, Fan, Yang, Ge, Wenbin, Han, Yu, Huang, Fei, Hui, Binyuan, Ji, Luo, Li, Mei, Lin, Junyang, Lin, Runji, Liu, Dayiheng, Liu, Gao, Lu, Chengqiang, Lu, Keming, Ma, Jianxin, Men, Rui, Ren, Xingzhang, Ren, Xuancheng, Tan, Chuanqi, Tan, Sinan, Tu, Jianhong, Wang, Peng, Wang, Shijie, Wang, Wei, Wu, Shengguang, Xu, Benfeng, Xu, Jin, Yang, An, Yang, Hao, Yang, Jian, Yang, Shusheng, Yao, Yang, Yu, Bowen, Yuan, Hongyi, Yuan, Zheng, Zhang, Jianwei, Zhang, Xingxuan, Zhang, Yichang, Zhang, Zhenru, Zhou, Chang, Zhou, Jingren, Zhou, Xiaohuan, Zhu, Tianhang

  2. Qwen Technical Report ↗

    Bai, Jinze, Bai, Shuai, Chu, Yunfei, Cui, Zeyu, Dang, Kai, Deng, Xiaodong et al. · 2023

    All 48 authors

    Bai, Jinze, Bai, Shuai, Chu, Yunfei, Cui, Zeyu, Dang, Kai, Deng, Xiaodong, Fan, Yang, Ge, Wenbin, Han, Yu, Huang, Fei, Hui, Binyuan, Ji, Luo, Li, Mei, Lin, Junyang, Lin, Runji, Liu, Dayiheng, Liu, Gao, Lu, Chengqiang, Lu, Keming, Ma, Jianxin, Men, Rui, Ren, Xingzhang, Ren, Xuancheng, Tan, Chuanqi, Tan, Sinan, Tu, Jianhong, Wang, Peng, Wang, Shijie, Wang, Wei, Wu, Shengguang, Xu, Benfeng, Xu, Jin, Yang, An, Yang, Hao, Yang, Jian, Yang, Shusheng, Yao, Yang, Yu, Bowen, Yuan, Hongyi, Yuan, Zheng, Zhang, Jianwei, Zhang, Xingxuan, Zhang, Yichang, Zhang, Zhenru, Zhou, Chang, Zhou, Jingren, Zhou, Xiaohuan, Zhu, Tianhang

  3. AI benchmarks & capabilities ↗

    Epoch AI

Names used in source tables

Stable Beluga 2