← All LMArena Text Arena snapshots

LMArena Text Arena snapshot: 6 Nov 2026

Permanent, dated copy. Two views of the same date, each from its own source. Live leaderboard →

Download CSV Both views, with a “view” column. 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 6 Nov 2026 (default view), Gemini 4 Carbon (High) (Google) ranked #1 with an Arena score of 1526 (±9), marked Preliminary on the page.

What changed: Since the board dated 27 Oct 2026, Gemini 4 Carbon (High) stayed #1 (1528 → 1526); the same 10 models made the top 10, in a different order.

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
6 Nov 2026, as printed on the LMArena leaderboard page
Checked by ChatJudge
6 Nov 2026 to 7 Nov 2026
Rows
29 of 419 models listed. Top 25 overall, plus the best-ranked entry for OpenAI, xAI, DeepSeek and Z.ai (ranks 26–39).
Source
LMArena Text leaderboard ↗
Text Arena Overall, default view, 6 Nov 2026
RankModelProviderArena scoreOutput price ($ per 1M tokens)±VotesInput price ($/1M)
1Gemini 4 Carbon (High) PreliminaryGoogle1526$10±94,483$2
2Gemini 4 Argon (High)Google1523$10±618,399$2
3Muse Wonder (Max)Meta1513$20±711,229$4
4Claude Opus 5.5 (High)Anthropic1505$20±614,849$4
5Claude Fable 5 (High)Anthropic1504$50±446,601$10
6Claude Fable 5.1 (Max)Anthropic1504$50±619,892$10
7Claude Opus 4.6 (High)Anthropic1503$25±385,548$5
8Claude Opus 4.7 (High)Anthropic1501$25±465,007$5
9Gemini 3.8 Flash (High) PreliminaryGoogle1498$3.75±459,680$0.75
10Claude Opus 4.6Anthropic1496$25±390,487$5
11Muse Spark 1.3 (Max)Meta1495$4.25±525,672$1.25
12Claude Opus 4.7Anthropic1494$25±466,092$5
13Muse Spark 1.2 (xHigh)Meta1493$4.25±614,436$1.25
14Claude Opus 5 (High)Anthropic1490$25±475,732$5
15Muse Spark 1.1Meta1490$4.25±446,714$1.25
16Claude Opus 5 (Max)Anthropic1489$25±536,681$5
17Muse SparkMeta1489–±614,119N/A
18Gemini 3.7 Flash (High) PreliminaryGoogle1489$3.75±534,346$0.75
19Kimi K3 (Max)Moonshot1488–±440,814N/A
20Gemini 3.1 Pro PreviewGoogle1487$6.00±3134,284$1
21Gemini 3 ProGoogle1486$12±442,019$2
22GPT-5.6 Sol (xHigh)OpenAI1485$20±445,082$4
23Qwen3.8-MaxAlibaba1483$6.00±536,028$2
24GPT-6.1 Sol (Max)OpenAI1483$10±612,539$2
25Gemini 3.6 Flash (High)Google1483$3.75±436,116$0.75
26GLM-5.3 (Max)Z.ai1482$4.40±530,776$1.4
28GPT-5.5 (High)OpenAI1481$30±469,197$5
37DeepSeek-V4.1-Flash-20260910 (Max)DeepSeek1475$1.20±613,976$0.3
39Grok 4.20 Beta 1xAI1475–±527,856N/A

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

On the Text Arena board Arena published on 6 Nov 2026 (style control off), Gemini 4 Carbon (High) (Google) ranked #1 with an Arena rating of 1539.1 (lower 1529.8, upper 1548.4).

What changed: Since the Arena dataset board published 28 Oct 2026, Gemini 4 Carbon (High) stayed #1 (1540.0 → 1539.1); the same 10 models made the top 10, in a different order.

Arena and category
Text Arena, Overall
Style control
Off: Arena’s dataset config “text” (on arena.ai this is the “overall-no-style-control” view)
Source date
6 Nov 2026, the leaderboard_publish_date in Arena’s dataset
Read by ChatJudge
15 Nov 2026 (dataset file SHA-256 8f6282c5efc4…)
Rows
31 of 419 models listed. Top 25 overall, plus the best-ranked entry for each major provider outside the top 25. Ratings rounded to 0.1; lower and upper bounds as published in the dataset.
Source
LMArena leaderboard dataset (Hugging Face) ↗
Same view on arena.ai
Text Arena, no style control ↗
Text Arena Overall, style control off, 6 Nov 2026
RankModelOrganisation (as published)Arena ratingLowerUpperVotes
1Gemini 4 Carbon (High)google1539.11529.81548.44,483
2Gemini 4 Argon (High)google1530.41524.91535.918,399
3Claude Fable 5.1 (Max)anthropic1513.51507.91519.019,892
4Claude Opus 5.5 (High)anthropic1512.31506.21518.414,849
5Claude Opus 5 (Max)anthropic1506.81502.21511.536,681
6Muse Wonder (Max)meta1505.11498.61511.611,229
7Claude Opus 5 (High)anthropic1502.81499.31506.475,732
8Claude Opus 4.6 (High)anthropic1501.71498.51504.985,548
9Gemini 3.8 Flash (High)google1500.51496.31504.859,680
10Claude Opus 4.6anthropic1496.51493.41499.790,487
11Claude Fable 5 (High)anthropic1491.81487.61495.946,601
12MiMo-V2.6-Proxiaomi1491.01481.71500.24,189
13Muse Spark 1.3 (Max)meta1490.71485.61495.725,672
14Claude Opus 4.7 (High)anthropic1489.71486.01493.465,007
15Gemini 3.7 Flash (High)google1488.41483.71493.034,346
16Qwen3.8-Maxalibaba1484.11479.51488.736,028
17Muse Spark 1.2 (xHigh)meta1483.61477.71489.514,436
18Claude Opus 4.7anthropic1483.21479.41486.966,092
19Gemini 3.5 Flash (High)google1482.31478.51486.248,503
20Gemini 3.1 Pro Previewgoogle1480.01477.11482.9134,284
21Gemini 3 Progoogle1479.61475.81483.342,019
22Gemini 3.6 Flash (High)google1479.21474.81483.636,116
23Muse Spark 1.1meta1478.21474.11482.446,714
24Gemini 3.5 Flash (Medium)google1478.11474.01482.247,284
25GLM-5.3 (Max)zai1475.91471.11480.730,776
26Kimi K3 (Max)moonshot1475.41471.11479.840,814
30GPT-5.5 (High)openai1471.41467.71475.169,197
39DeepSeek-V4.1-Flash-20260910 (Max)deepseek1463.51457.41469.513,976
52Grok 4.20 Beta (Reasoning, 0309)xai1450.91447.31454.666,330
98Mistral Large 3mistral1428.31425.51431.189,964
99MiniMax-M3minimax1428.21424.61431.973,158

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.