Nanogpt Speedrun
Evaluate code-generation and pretraining capabilities of LLMs via NanoGPT Speedrun benchmark.
- Domain
- rl-env
- License
- unknown
- Published
- Sep 2025
Cite
Notes
Only stored in your browser.
Top score 0.26 by GPT-5 - 1 model reporting (1 frontier)
Top models
1
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Nanogpt Speedrun?
- Evaluate code-generation and pretraining capabilities of LLMs via NanoGPT Speedrun benchmark.
- What is the current top score on Nanogpt Speedrun?
- The top reported score is 0.26 by GPT-5, across 1 model reporting (1 from frontier labs).
- How can a model improve its Nanogpt Speedrun score?
- Tools linked to Nanogpt Speedrun on Sophon include Nanogpt Speedrun RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Nanogpt Speedrun under?
- Nanogpt Speedrun is available under unknown.