01
62.7%
Claude Opus 4.6
Anthropic
United StatesVerified evidenceGPQA
n/a
MathArena
66.2%
Arc-AGI-2
Leaderboard
Top 10 AI models by raw Humanity's Last Exam.
Intelligence ranks the published roster by raw Humanity's Last Exam evidence. For the benchmark policy and supporting evidence rules, see the Methodology page.
April 7, 2026Review target April 14, 2026
Buyer-facing table
Ranked by raw reasoning benchmark
| Rank | Model | Raw HLEHumanity's Last Exam | GPQA | MathArena | Arc-AGI-2 |
|---|---|---|---|---|---|
| 01 | Claude Opus 4.6 Anthropic United StatesVerified evidence |
United StatesVerified evidenceEditorial investigation
Raw benchmark view, stripped back
Intelligence is the least interpreted surface on the site. The page keeps the raw HLE result front and center, then leaves methodology and evidence depth to the model page and methodology page.
Open top intelligence model"Best if your work involves genuinely hard problems ? deep research, complex code, or legal and financial analysis ? where accuracy matters more than speed."
Claude Opus 4.6
Anthropic
