Enter opens the highlighted result. Esc closes.

Terminal-Bench 4.0-AA leaderboard

As of November 14, 2026, among the results listed here, Google Gemini 4 Carbon has the highest reported Terminal-Bench 4.0-AA score, 65.2%, published by Google on October 28, 2026, ahead of Google Gemini 4 Argon at 57.1%. 3 models have a Terminal-Bench 4.0-AA result in our records.

Scores as the model makers published them, not re-run by us; each row links to its announcement.

Best reported score

65.2%

Google Gemini 4 Carbon

Reported by Google, October 28, 2026

Runner-up

57.1%

Google Gemini 4 Argon

Reported by Google, October 28, 2026

3 models ranked · 2 makers

Reported Terminal-Bench 4.0-AA scores

Terminal-Bench 4.0-AA scores reported by model makers
Rank Model Score Setting Reported by Date
1 Gemini 4 Carbon 65.2% Not published Google October 28, 2026 · read from the maker's chart
2 Gemini 4 Argon 57.1% Not published Google October 28, 2026 · read from the maker's chart
3 Muse Wonder 52.0% max Meta October 12, 2026 (model release)

How much to trust these numbers

Source
Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
Settings
Settings differ between makers. Check the Setting column before comparing two scores.
Spread
65.2% to 52.0% across 3 models.
Freshness
Newest result published October 28, 2026; oldest October 12, 2026.
Charts
Some values were read from charts in the announcements. Two independent readings had to match exactly.

What Terminal-Bench 4.0-AA measures

It tests terminal coding, with the score reporting accuracy.