NanoGPT-Bench — leaderboard
Autonomous coding and ML-research benchmark based on the NanoGPT speedrun, measuring how much historical human optimization progress an agent can recover.
Metric: % of Human Progress Recovered. Source: www.intology.ai. 2 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 9.3 |
| 2 | GPT-5.4 (xHigh) | 8.6 |
Interactive version: theaggregate.ai/benchmark?slug=nanogpt-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.