SEAL - Humanity's Last Exam (Text Only) — leaderboard

Metric: Score. Source: scale.com. 60 models tracked.

Top models

#ModelScore
1gemini-3.1-pro-preview (thinking high)47.31
2gpt-5.4-pro-2026-03-0545.32
3Muse Spark40.92
4gemini-3-pro-preview37.72
5gpt-5.4-2026-03-05 (xhigh thinking)36.47
6claude-opus-4-6-thinking-max36.24
7gpt-5-pro-2025-10-0633.32
8gpt-5.2-2025-12-1128.5
9claude-opus-4-5-20251101-thinking26.32
10gpt-5-2025-08-0726.32

Interactive version: theaggregate.ai/benchmark?slug=seal-humanity-s-last-exam-text-only · How the rankings work · Data refreshed daily, snapshot 2026-07-22.