New: GPT-6.2 benchmark report is here.Read the report ↗

Best LLMs on NanoGPT

NanoGPT

Reduces the time needed to train a small language model to a specified prediction-accuracy target.

Updated: Data as of:
Limited reportingNot saturated
Official benchmark
NanoGPT results. Each row identifies its benchmark version and evaluation track. Scores from different versions are not directly comparable. Best effort from the latest stored report date per model and version.
Model / creatorVersionReported score
GPT-6.2 AstraOpenAI · ProprietaryGPT-6.2 system card42.87%
GPT-6.2 SolOpenAI · ProprietaryGPT-6.2 system card14.59%
View all 2 published reports
GPT-6.2 system card

development time hours: 2 · gpu: 1× H100 · note: The system card states the two Astra models use slightly different evaluation versions. · stage: Secondary Stage

OpenAI ↗
GPT-6.2 system card

development time hours: 2 · gpu: 1× H100 · note: The system card states the two Astra models use slightly different evaluation versions. · stage: Secondary Stage

OpenAI ↗