Agents' Last Exam v1.1 leaderboard
As of November 14, 2026, among the results listed here, Google Gemini 4 Carbon has the highest reported Agents' Last Exam v1.1 score, 77.4% (Score), published by Google on October 28, 2026, ahead of Google Gemini 4 Argon at 69.0%. 2 models have a Agents' Last Exam v1.1 result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
2 models ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | Gemini 4 Carbon | 77.4% | Score | October 28, 2026 · read from the maker's chart | |
| 2 | Gemini 4 Argon | 69.0% | Score | October 28, 2026 · read from the maker's chart |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- All ranked results use the same reported setting.
- Spread
- 77.4% to 69.0% across 2 models.
- Freshness
- Published October 28, 2026.
- Charts
- Some values were read from charts in the announcements. Two independent readings had to match exactly.
What Agents' Last Exam v1.1 measures
Agents complete 122 tasks involving long-horizon professional work; the number is their average rubric score, graded against hidden reference outputs. Source: Agents' Last Exam V1.1