Community preference
Arena Elo (Text)
Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better.
Rankings
Higher is better#11509
Claude Fable 5
21504
Claude Opus 4.6
31503
Claude Opus 4.7
41495
Claude Opus 5
51490
Muse Spark 1.1
61488
Muse Spark
71486
Gemini 3.0 Pro
71486
GPT-5.6 Sol
71486
Kimi K3
101485
Gemini 3.1 Pro
111482
Claude Opus 4.8
111482
Gemini 3.6 Flash
131481
GPT-5.5
141476
GPT-5.2
141476
GPT-5.4
141476
Gemini 3.5 Flash
171475
Grok 4.20 Beta
Arena Elo (Text) — frequently asked questions
- What is Arena Elo (Text)?
- Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better.
- Which AI model scores highest on Arena Elo (Text)?
- Claude Fable 5 by Anthropic holds the best Arena Elo (Text) result among tracked models, at 1509 (released Jun 9 2026). Higher scores are better on this benchmark.
- What are the top 5 models on Arena Elo (Text)?
- 1. Claude Fable 5 (Anthropic) — 1509; 2. Claude Opus 4.6 (Anthropic) — 1504; 3. Claude Opus 4.7 (Anthropic) — 1503; 4. Claude Opus 5 (Anthropic) — 1495; 5. Muse Spark 1.1 (Meta) — 1490.
- How many models have a published Arena Elo (Text) score?
- 17 tracked models have a published Arena Elo (Text) score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.