# Humanity's Last Exam (text only, with tools) — AI model rankings

The text-only questions from Humanity's Last Exam, answered with access to tools such as search or code execution. The score is the percentage answered correctly.

4 tracked models have a published Humanity's Last Exam (text only, with tools) score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | Nemotron 3.5 Super VL | NVIDIA | 46.01% | Lab | Oct 15 2026 |
| 2 | Nemotron 3 Ultra | NVIDIA | 37.4% | Lab | Jun 4 2026 |
| 3 | Nemotron 3 Super | NVIDIA | 22.82% | Lab | Mar 11 2026 |
| 4 | Nemotron 3 Nano | NVIDIA | 15.48% | Lab | Dec 15 2025 |


---

Canonical page: https://aireleasetracker.com/benchmark/hle-text-only-with-tools
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.
