Which AI model scores highest on Agents’ Last Exam v1.1?

Gemini 4 Carbon by Google holds the best Agents’ Last Exam v1.1 result among tracked models, at 77.4% (released Oct 28 2026). Higher scores are better on this benchmark.

What are the top 1 models on Agents’ Last Exam v1.1?

1. Gemini 4 Carbon (Google) — 77.4%.

How many models have a published Agents’ Last Exam v1.1 score?

1 tracked model has a published Agents’ Last Exam v1.1 score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.

Agentic computer use

Agents’ Last Exam v1.1

averaged rubric score on the 122-task October 17, 2026 v1.1 set, using ALE-Claw with a five-hour limit; separate from earlier ALE scores

Rankings

Higher is better

Gemini 4 Carbon

77.4%

Agents’ Last Exam v1.1 — frequently asked questions

: averaged rubric score on the 122-task October 17, 2026 v1.1 set, using ALE-Claw with a five-hour limit; separate from earlier ALE scores
: Gemini 4 Carbon by Google holds the best Agents’ Last Exam v1.1 result among tracked models, at 77.4% (released Oct 28 2026). Higher scores are better on this benchmark.
: 1. Gemini 4 Carbon (Google) — 77.4%.
: 1 tracked model has a published Agents’ Last Exam v1.1 score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.