RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-Neo-2.7B

8 benchmarks · 8 observations · 2 sources · released 2021-03-30

Scores at a glance

8 benchmarks · large dot: GPT-Neo-2.7B; small dots: closest models where reported

ARC AI2 ↗27.4%
23.244.9

GPT-Neo-2.7B · ARC AI2 · Challenge score · % ↗

PIQA ↗72.9%
6979.4

GPT-Neo-2.7B · PIQA · Score · % ↗

HumanEval+ ↗6.7%
1.889

GPT-Neo-2.7B · HumanEval+ · Pass@1 · EvalPlus · official result data ↗

HumanEval ↗7.9%
2.496.3

GPT-Neo-2.7B · HumanEval · Pass@1 · EvalPlus · official result data ↗

Closest models by score

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

12.8 percentile-point gap

5 of 8 shared benchmark comparisons

19.2 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. Textbooks Are All You Need II: phi-1.5 technical report ↗

    Li, Yuanzhi, Bubeck, Sébastien, Eldan, Ronen, Del Giorno, Allie, Gunasekar, Suriya, Lee, Yin Tat · 2023

  2. Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation — published result table ↗

    Liu, Jiawei, Xia, Chunqiu Steven, Wang, Yuyao, Zhang, Lingming · 2023

Names used in source tables

GPT-Neo-2.7B