HAL USACO — leaderboard
Princeton HAL leaderboard for USACO: 307 competitive programming problems from the USA Computing Olympiad across 4 difficulty tiers. Tests algorithmic problem-solving ability.
Metric: Accuracy (%). Source: hal.cs.princeton.edu. Status: saturation imminent. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 (Medium) | 69.06 |
| 2 | O4 Mini (High) | 64.82 |
| 3 | O4 Mini (Low) | 53.09 |
| 4 | Claude Opus 4.1 (High) | 51.47 |
| 5 | Claude Opus 4.1 (20250805) | 48.21 |
| 6 | O3 (Medium) | 46.25 |
| 7 | GPT-4.1 (2025-04-14) | 44.95 |
| 8 | DeepSeek V3 (0324) | 39.09 |
| 9 | DeepSeek R1 | 38.11 |
| 10 | Claude 3.7 Sonnet (20250219) | 29.32 |
| 11 | Gemini 2.0 Flash (001) | 27.04 |
| 12 | Claude 3.7 Sonnet (High) | 26.71 |
Interactive version: theaggregate.ai/benchmark?slug=hal-usaco · How the rankings work · Data refreshed daily, snapshot 2026-07-22.