SEA LLM Leaderboard - SeaExam — leaderboard
Metric: Private Average Score (%). Source: huggingface.co. 91 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 91.2 |
| 2 | Claude 3.5 Sonnet (20241022) | 80.8 |
| 3 | DeepSeek V3 (0324) | 80.8 |
| 4 | Gemini 1.5 Pro | 79.4 |
| 5 | Claude 3.7 Sonnet (20250219) | 79.1 |
| 6 | Gemini 2.0 Flash | 78.4 |
| 7 | Qwen 2.5 72B | 77.6 |
| 8 | Llama 4 Maverick Instruct | 76.7 |
| 9 | Qwen 2.5 72B Instruct | 76.6 |
| 10 | Gemini 2.0 Flash Lite | 76.4 |
| 11 | Qwen 2 72B | 75.8 |
| 12 | GPT-4.1 | 74.6 |
| 13 | Qwen 2 72B Instruct | 74.5 |
| 14 | GPT-4o (2024-08-06) | 74.1 |
| 15 | gemma-3-27B-pt | 73.3 |
Interactive version: theaggregate.ai/benchmark?slug=sea-llm-leaderboard-seaexam · How the rankings work · Data refreshed daily, snapshot 2026-07-22.