RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-NeoX-20B

8 benchmarks · 10 observations · 5 sources · released 2022-04-07

Scores at a glance

8 benchmarks · large dot: GPT-NeoX-20B; small dots: closest models where reported

ARC AI2 ↗41.1%
2744.8

GPT-NeoX-20B · ARC AI2 · Challenge score · % ↗

MMLU ↗33.6%
25.469.3

GPT-NeoX 20B · MMLU · EM · % ↗

PIQA ↗76.7%
65.879.4

GPT-NeoX-20B · PIQA · Score · % ↗

Closest models by score

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

30.2 percentile-point gap

5 of 8 shared benchmark comparisons

30.8 percentile-point gap

6 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. LLaMA: Open and Efficient Foundation Language Models ↗

    Touvron, Hugo, Lavril, Thibaut, Izacard, Gautier, Martinet, Xavier, Lachaux, Marie-Anne, Lacroix, Timothée et al. · 2023

    All 14 authors

    Touvron, Hugo, Lavril, Thibaut, Izacard, Gautier, Martinet, Xavier, Lachaux, Marie-Anne, Lacroix, Timothée, Rozière, Baptiste, Goyal, Naman, Hambro, Eric, Azhar, Faisal, Rodriguez, Aurelien, Joulin, Armand, Grave, Edouard, Lample, Guillaume

  2. XGen-7B Technical Report ↗

    Nijkamp, Erik, Xie, Tian, Hayashi, Hiroaki, Pang, Bo, Xia, Congying, Xing, Chen et al. · 2023

    All 25 authors

    Nijkamp, Erik, Xie, Tian, Hayashi, Hiroaki, Pang, Bo, Xia, Congying, Xing, Chen, Vig, Jesse, Yavuz, Semih, Laban, Philippe, Krause, Ben, Purushwalkam, Senthil, Niu, Tong, Kryściński, Wojciech, Murakhovs'ka, Lidiya, Choubey, Prafulla Kumar, Fabbri, Alex, Liu, Ye, Meng, Rui, Tu, Lifu, Bhat, Meghana, Wu, Chien-Sheng, Savarese, Silvio, Zhou, Yingbo, Joty, Shafiq, Xiong, Caiming

  3. Holistic Evaluation of Language Models (HELM) ↗

    Stanford Center for Research on Foundation Models

  4. Holistic Evaluation of Language Models (HELM) ↗

    Stanford Center for Research on Foundation Models

  5. Holistic Evaluation of Language Models (HELM) ↗

    Stanford Center for Research on Foundation Models

Names used in source tables

GPT-NeoX (20B) · GPT-NeoX 20B · GPT-NeoX-20B · GPT-neox-20B