LLM Stats (Humanity's Last Exam (with tools, text-only)): leaderboard
Metric: Score (%). Source: llm-stats.com. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Pro (0813) | 60 |
| 2 | GPT-6 | 57.2 |
| 3 | Qwen 3.8 Max | 56.2 |
| 4 | Hy4 preview | 55.4 |
| 5 | Hy3 | 53.2 |
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-humanity-s-last-exam-with-tools-text-only · How It Works · Data refreshed daily, snapshot 2026-09-05.