Benchmark

NanoGPT

NanoGPT is an OpenAI AI-self-improvement evaluation that measures whether models can optimize training recipes for small GPT-style models, part of the…

Modality
text
Categories
agents, code, systems
Openness
unknown
Source
llm_stats
Reported scores
3

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
GPT-5.6 LunaOpenAI0.01662026-07-09evidence
GPT-5.6 SolOpenAI0.09692026-07-09evidence
GPT-5.6 TerraOpenAI0.1452026-07-09evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.