Skip to content
ModelCap

Launch report

Gemini 4 Carbon launch report

ModelCap · generated from recorded data

Google's Gemini 4 Carbon was first listed on 10 November 2026. It entered the ModelCap Index at #1 of 362 ranked language models on 11 November 2026, one day after its listed release date, backed by 5 admitted benchmarks: ARC-AGI-2 Verified, ARC-AGI-3 Verified, Arena Coding, Arena Overall and LMArena Agent. As of 19 November 2026 it is #1 on the current board.

Position at entry · 11 November 2026
#1 of 362
Listing to first measurement
1 day
Position now · 19 November 2026
#1

Position at entry

Entry is the first board position backed by at least two admitted benchmarks. Read from the board's last published snapshot of each day named below; these values are fixed and do not change with later refreshes.

Listed release date
10 November 2026
Entry · 11 November 2026
#1 of 362 ranked language modelsBacked by ARC-AGI-2 Verified, ARC-AGI-3 Verified, Arena Coding, Arena Overall, LMArena Agent
Neighbours at entry
No model ranked above itDirectly below: Gemini 4 Argon

Benchmark results

Published results admitted to the Index, as of 19 November 2026. Each board links to ModelCap's page for it and each result to its source.

Current public benchmark results for Gemini 4 Carbon
BenchmarkResultBoard positionPublished
Arena Overallgeneral · High15261516–1536#1 of 42218 November 2026
Arena Codingcoding · High15671548–1586#1 of 41718 November 2026
LMArena Agentagent · High16.1%15.4%–16.8%#4 of 6818 November 2026
ARC-AGI-2 Verifiedreasoning · Medium94.2%#5 of 29918 November 2026
ARC-AGI-3 Verifiedreasoning · Low65.1%#38 of 15118 November 2026

How this report is produced

ModelCap publishes a launch report when a newly released model first holds a measured position backed by at least two public benchmarks. The report is assembled automatically from ModelCap's own records: the board as it stood at entry, the results currently admitted to the Index and, where one exists, the estimate recorded before measurement. No text is written by hand, and no claim is made that the records do not contain. ModelCap does not run the benchmarks itself; each result links to the organisation that published it.

More launch reports