Algorithmic@1.0 Leaderboard
# Covering Optimization tasks, Constructive tasks, and Interactive tasks| Rank | Model Name | Pass@1 | Pass@5 | Score@1 | Score@5 | Avg@5 | Date |
|---|---|---|---|---|---|---|---|
| 1 | Gemini 2.5 Pro | 36.2% | 60.0% | 11.7% | 24.1% | 11.0% | 11/17/2025 |
| 2 | GPT 5 Thinking | 35.2% | 61.0% | 9.8% | 22.2% | 10.7% | 11/17/2025 |
| 3 | Grok 4 | 17.8% | 46.7% | 6.3% | 19.0% | 8.8% | 11/17/2025 |
| 4 | Claude Opus 4.1 | 28.0% | 44.9% | 6.1% | 12.5% | 0.5% | 11/17/2025 |
| 5 | Claude Sonnet 4.5 | 21.5% | 48.6% | 3.9% | 13.5% | 0.6% | 11/17/2025 |
Send us an email to submit your results: qmang@berkeley.edu wenhao.chai@princeton.edu