← All LMArena Text Arena snapshots

LMArena Text Arena snapshot: 9 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 9 Nov 2026 (default view), Gemini 4 Carbon (High) (Google) ranked #1 with an Arena score of 1526 (±10), marked Preliminary on the page.

What changed: Since the board dated 8 Nov 2026, Gemini 4 Carbon (High) stayed #1 (1527 → 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
9 Nov 2026, as printed on the LMArena leaderboard page
Checked by ChatJudge
9 Nov 2026 to 12 Nov 2026
Rows
30 of 420 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, 9 Nov 2026
RankModelProviderArena scoreOutput price ($ per 1M tokens)±VotesInput price ($/1M)
1Gemini 4 Carbon (High) PreliminaryGoogle1526$10±104,282$2
2Gemini 4 Argon (High)Google1522$10±519,787$2
3Muse Wonder (Max)Meta1511$20±612,032$4
4Claude Opus 5.5 (High)Anthropic1506$20±615,249$4
5Claude Fable 5 (High)Anthropic1504$50±445,524$10
6Claude Opus 4.6 (High)Anthropic1503$25±384,424$5
7Claude Fable 5.1 (Max)Anthropic1503$50±620,087$10
8Claude Opus 4.7 (High)Anthropic1501$25±464,308$5
9Gemini 3.8 Flash (High) PreliminaryGoogle1497$3.75±461,143$0.75
10Claude Opus 4.6Anthropic1496$25±389,228$5
11Muse Spark 1.3 (Max)Meta1496$4.25±526,111$1.25
12Claude Opus 4.7Anthropic1494$25±465,369$5
13Muse Spark 1.2 (xHigh)Meta1493$4.25±615,004$1.25
14Muse Spark 1.1Meta1491$4.25±445,562$1.25
15Claude Opus 5 (High)Anthropic1490$25±473,697$5
16Gemini 3.7 Flash (High) PreliminaryGoogle1489$3.75±533,300$0.75
17Muse SparkMeta1489–±614,009N/A
18Claude Opus 5 (Max)Anthropic1489$25±535,710$5
19Kimi K3 (Max)Moonshot1487–±440,867N/A
20Gemini 3.1 Pro PreviewGoogle1487$6.00±3132,296$1
21Gemini 3 ProGoogle1486$12±441,829$2
22GPT-5.6 Sol (xHigh)OpenAI1485$20±443,994$4
23Qwen3.8-MaxAlibaba1484$6.00±536,324$2
24Kimi K3.1 Pro (Max)Moonshot1483$10±113,443$2
25Gemini 3.6 Flash (High)Google1483$3.75±435,405$0.75
26GLM-5.3 (Max)Z.ai1483$4.40±531,017$1.4
27GPT-6.1 Sol (Max)OpenAI1482$10±612,952$2
29GPT-5.5 (High)OpenAI1481$30±468,359$5
37DeepSeek-V4.1-Flash-20260910 (Max)DeepSeek1475$1.20±613,580$0.3
38Grok 4.20 Beta 1xAI1475–±527,690N/A

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

On the Text Arena board Arena published on 9 Nov 2026 (style control off), Gemini 4 Carbon (High) (Google) ranked #1 with an Arena rating of 1538.3 (lower 1528.7, upper 1547.8).

What changed: Since the Arena dataset board published 8 Nov 2026, Gemini 4 Carbon (High) stayed #1 (1538.9 → 1538.3); 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
9 Nov 2026, the leaderboard_publish_date in Arena’s dataset
Read by ChatJudge
15 Nov 2026 (dataset file SHA-256 8f6282c5efc4…)
Rows
31 of 421 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, 9 Nov 2026
RankModelOrganisation (as published)Arena ratingLowerUpperVotes
1Gemini 4 Carbon (High)google1538.31528.71547.84,282
2Gemini 4 Argon (High)google1530.21524.71535.619,787
3Claude Opus 5.5 (High)anthropic1513.01507.01519.015,249
4Claude Fable 5.1 (Max)anthropic1512.41506.81517.920,087
5Claude Opus 5 (Max)anthropic1506.31501.61511.035,710
6Muse Wonder (Max)meta1503.01496.71509.412,032
7Claude Opus 5 (High)anthropic1502.31498.71505.973,697
8Claude Opus 4.6 (High)anthropic1501.71498.41504.984,424
9Gemini 3.8 Flash (High)google1500.41496.21504.661,143
10Claude Opus 4.6anthropic1496.71493.61499.989,228
11MiMo-V2.6-Proxiaomi1491.71482.31501.14,066
12Claude Fable 5 (High)anthropic1491.61487.41495.845,524
13Muse Spark 1.3 (Max)meta1491.51486.41496.526,111
14Claude Opus 4.7 (High)anthropic1489.71486.01493.564,308
15Gemini 3.7 Flash (High)google1488.81484.11493.533,300
16Qwen3.8-Maxalibaba1485.21480.61489.836,324
17Muse Spark 1.2 (xHigh)meta1484.01478.11489.915,004
18Claude Opus 4.7anthropic1483.21479.41487.065,369
19Gemini 3.5 Flash (High)google1482.91479.01486.847,642
20Gemini 3.1 Pro Previewgoogle1480.01477.11482.9132,296
21Gemini 3 Progoogle1479.51475.81483.341,829
22Gemini 3.6 Flash (High)google1479.31474.81483.735,405
23Muse Spark 1.1meta1478.71474.61482.945,562
24Gemini 3.5 Flash (Medium)google1477.91473.71482.046,377
25GLM-5.3 (Max)zai1475.91471.21480.631,017
27Kimi K3 (Max)moonshot1474.31470.01478.640,867
29GPT-5.5 (High)openai1471.21467.51474.968,359
39DeepSeek-V4.1-Flash-20260910 (Max)deepseek1463.41457.31469.513,580
51Grok 4.20 Beta (Reasoning, 0309)xai1451.31447.61454.965,713
98Mistral Large 3mistral1428.61425.81431.488,641
100MiniMax-M3minimax1428.21424.61431.972,963

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.