AgentDish directory
model benchmarking
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
#1178
↓ -2
Measuring Autonomous AI Research
A research post from Prime Intellect comparing 153 autonomous runs across 18 frontier models on a nanoGPT optimizer speedrun. It presents the setup, harness, results, and discussion around autonomous AI research performance. |
Research / AI Research Evaluation | 82 | ↓ -2 | 15 days ago | Details |