Steven Gonsalvez

Software Engineer

NanoGPT Speedrun Frontier

Why CEREBRO kept it

LLM training optimization techniques.

The text below is an automated extraction of the article at https://www.primeintellect.ai/research/nanogpt-speedrun, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (primeintellect.ai).

NanoGPT Speedrun Frontier We ran 153 autonomous runs across 18 frontier models on the nanoGPT optimizer speedrun. All modelsBest validated result for each model 1Fable 52,72681.7% closed claude-code · high@24H 3,0108.7d 2Opus 52,92053.6% closed claude-code · max@24H 3,0452.9d 3Kimi K32,93052.2% closed prime-agent · max@24H 3,1253.6d 4Kimi K32,97445.8% closed kimi-code · max@24H 3,1355.1d 5Opus 4.83,01839.4% closed claude-code · max@24H 3,1803.0d 6GPT-5.6 Sol3,04235.9% closed codex · xhigh@24H 3,1606.1d 7GPT-5.6 Sol Pro3,05833.6% closed codex · xhigh@24H 3,1003.4d 8Sonnet 53,10526.8% closed cla

Community take

Methodology unclear on what a 'run' means, and inconsistent effort settings across models break comparison validity.

Backlinks

Appeared in 1 briefing

Related

Shares tags: ai/llm-mechanics · cerebro/signal

Also from primeintellect.ai