← All LMArena Text Arena snapshots

LMArena Text Arena snapshot: 27 Oct 2026

Permanent, dated copy. One view has a board with this date; the other is shown below as missing, never filled in from another date. Live leaderboard →

Download CSV Every row carries the source date, check dates and source link.

Text Arena Overall: default view, as ChatJudge copies it

On the LMArena Text Arena board dated 27 Oct 2026 (default view), Gemini 4 Carbon (High) (Google) ranked #1 with an Arena score of 1528 (±9), marked Preliminary on the page.

What changed: Since the board dated 22 Oct 2026, Gemini 4 Carbon (High) took #1 at 1528, replacing Gemini 4 Argon (High) (1517 on the previous board); Gemini 4 Carbon (High) entered the top 10 and Muse Spark 1.3 (Max) dropped out.

Arena and category
Text Arena, Overall
Style control
Not stated by source. This is the page’s default view (what ChatJudge copies), not the “style control off” view
Source date
27 Oct 2026, as printed on the LMArena leaderboard page
Checked by ChatJudge
29 Oct 2026 to 5 Nov 2026
Rows
29 of 419 models listed. Top 25 overall, plus the best-ranked entry for OpenAI, xAI, DeepSeek and Z.ai (ranks 27–40).
Source
LMArena Text leaderboard ↗
Text Arena Overall, default view, 27 Oct 2026
RankModelProviderArena scoreOutput price ($ per 1M tokens)±VotesInput price ($/1M)
1Gemini 4 Carbon (High) PreliminaryGoogle1528$10±94,403$2
2Gemini 4 Argon (High)Google1520$10±611,889$2
3Claude Opus 5.5 (High)Anthropic1509$20±711,415$4
4Muse Wonder (Max)Meta1507$20±77,749$4
5Claude Fable 5.1 (Max)Anthropic1504$50±617,178$10
6Claude Fable 5 (High)Anthropic1504$50±445,341$10
7Claude Opus 4.6 (High)Anthropic1503$25±384,512$5
8Claude Opus 4.7 (High)Anthropic1501$25±465,110$5
9Claude Opus 4.6Anthropic1496$25±389,324$5
10Gemini 3.8 Flash (High) PreliminaryGoogle1496$3.75±447,803$0.75
11Muse Spark 1.3 (Max)Meta1495$4.25±522,134$1.25
12Claude Opus 4.7Anthropic1494$25±466,140$5
13Muse Spark 1.2 (xHigh)Meta1492$4.25±611,724$1.25
14Claude Opus 5 (High)Anthropic1492$25±473,167$5
15Claude Opus 5 (Max)Anthropic1491$25±535,531$5
16Muse Spark 1.1Meta1490$4.25±446,354$1.25
17Gemini 3.7 Flash (High) PreliminaryGoogle1490$3.75±532,289$0.75
18Muse SparkMeta1489–±614,140N/A
19Kimi K3 (Max)Moonshot1488–±436,780N/A
20Gemini 3.1 Pro PreviewGoogle1487$6.00±3132,547$1
21Gemini 3 ProGoogle1485$12±442,057$2
22GPT-5.6 Sol (xHigh)OpenAI1485$20±443,796$4
23Gemini 3.6 Flash (High)Google1483$3.75±436,028$0.75
24Qwen3.8-MaxAlibaba1482$6.00±531,915$2
25Claude Opus 4.8 (High)Anthropic1482$25±463,994$5
27GPT-6.1 Sol (Max)OpenAI1481$10±79,367$2
28GLM-5.3 (Max)Z.ai1481$4.40±526,606$1.4
35DeepSeek-V4.1-Flash-20260910 (Max)DeepSeek1476$1.20±613,657$0.3
40Grok 4.20 Beta 1xAI1475–±527,889N/A

Text Arena Overall: style control off, from Arena’s published dataset

Arena’s dataset has no board published on 27 Oct 2026. The nearest archived style-control-off view board is 28 Oct 2026. It is a separate board from its own source, not merged with this date.

Text Arena is run and published by LMArena (lmarena.ai, arena.ai), including the dated leaderboard dataset on Hugging Face. ChatJudge copies the published numbers and does not run the benchmark. Scores from different views or benchmarks aren’t directly comparable.