General preference

Which model people prefer on prompts they brought themselves, aggregated over pairwise votes. This measures what users like, which tracks capability without being the same thing — length, formatting, and tone move it too, which is why the style-controlled rating is the one shown.

Ordered by how many of these benchmarks put a model in their top 10, then by its best placing. Each column keeps its own ranking; nothing is averaged.

Model	In top 10	Arena — Text Overall (style control)
Gemini 4 Argon google	1/1	#1 1525
Claude Opus 4.6 anthropic	1/1	#2 1505
Claude Fable 5 anthropic	1/1	#3 1504
Claude Opus 5.5 anthropic	1/1	#4 1504
Claude Opus 4.7 anthropic	1/1	#5 1501
Claude Fable 5.1 anthropic	1/1	#6 1501
Gemini 3.8 Flash google	1/1	#7 1495
Muse Spark 1.3 meta	1/1	#8 1494
Muse Spark 1.2 meta	1/1	#9 1494
Muse Spark 1.1 meta	1/1	#10 1491

A dash means the board does not list that model — not a score of zero. Entries not yet matched to a model are left out here; they still appear on their own board.