Loong — leaderboard
Metric: Overall Avg Score (%). Source: github.com. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Pro | 55.37 |
| 2 | GPT-4o | 53.47 |
| 3 | Claude 3.5 Sonnet | 48.85 |
| 4 | Claude 3 Haiku | 44.88 |
| 5 | Qwen 2 72B Instruct | 43.29 |
| 6 | GPT-4o Mini | 42.95 |
| 7 | GLM-4 9B Chat | 38.31 |
| 8 | Llama 3.1 8B Instruct | 36.31 |
Interactive version: theaggregate.ai/benchmark?slug=loong · How the rankings work · Data refreshed daily, snapshot 2026-07-22.