# Arena.ai finds AI judges favor their own answers over human votes

Arena.ai compared 34,580 verdicts from 12 models with human votes across 1,460 Arena battles. On average, a model chose its own answer 58% of the time, while people chose that same answer 34% of the time.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-17T15:02:00.000Z
Query date (America/Los_Angeles): 2026-11-17

HTML: https://didcodexreset.com/news/a4427983a7104595aa60d726.html

Content language: en
Localization state: sameLanguage

Source: Arena.ai · Published 9/29/2026, 09:28:22

Arena.ai compared 34,580 verdicts from 12 models with human votes across 1,460 battles on Arena. On average, a model picked its own answer 58% of the time; people picked that same answer 34% of the time. GPT-6 Astra picked itself 88% of the time.

The models also rarely called a draw. People marked a tie or “both bad” in 32% of battles, while GPT-5.6 Sol picked a winner 96% of the time. The AI judges agreed with other models 79% of the time and with people 57% of the time, and every judge sided with other AIs over people by 18 to 27 percentage points.

Full results are in [DawidGalarowicz’s Arena article](https://x.com/i/article/2104955648664584192).

Tags: Arena, AI judges, Model evaluation, GPT-6 Astra

[View original post](https://x.com/arena/status/2104969213282840770)
