← All LMArena Text Arena snapshots

LMArena Text Arena snapshot: 8 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 8 Nov 2026 (default view), Gemini 4 Carbon (High) (Google) ranked #1 with an Arena score of 1527 (±10), marked Preliminary on the page.

What changed: Since the board dated 6 Nov 2026, Gemini 4 Carbon (High) stayed #1 (1526 → 1527); the top 10 kept the same models in the same 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
8 Nov 2026, as printed on the LMArena leaderboard page
Checked by ChatJudge
8 Nov 2026
Rows
29 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, 8 Nov 2026
RankModelProviderArena scoreOutput price ($ per 1M tokens)±VotesInput price ($/1M)
1Gemini 4 Carbon (High) PreliminaryGoogle1527$10±104,281$2
2Gemini 4 Argon (High)Google1522$10±518,850$2
3Muse Wonder (Max)Meta1512$20±611,483$4
4Claude Opus 5.5 (High)Anthropic1506$20±614,815$4
5Claude Fable 5 (High)Anthropic1504$50±445,562$10
6Claude Fable 5.1 (Max)Anthropic1503$50±619,755$10
7Claude Opus 4.6 (High)Anthropic1503$25±384,428$5
8Claude Opus 4.7 (High)Anthropic1501$25±464,295$5
9Gemini 3.8 Flash (High) PreliminaryGoogle1498$3.75±459,624$0.75
10Claude Opus 4.6Anthropic1496$25±389,224$5
11Muse Spark 1.3 (Max)Meta1496$4.25±525,563$1.25
12Muse Spark 1.2 (xHigh)Meta1494$4.25±614,561$1.25
13Claude Opus 4.7Anthropic1494$25±465,387$5
14Muse Spark 1.1Meta1491$4.25±445,555$1.25
15Claude Opus 5 (High)Anthropic1490$25±473,730$5
16Gemini 3.7 Flash (High) PreliminaryGoogle1489$3.75±533,306$0.75
17Muse SparkMeta1489–±614,008N/A
18Claude Opus 5 (Max)Anthropic1489$25±535,712$5
19Kimi K3 (Max)Moonshot1487–±440,409N/A
20Gemini 3.1 Pro PreviewGoogle1487$6.00±3132,347$1
21Gemini 3 ProGoogle1486$12±441,839$2
22GPT-5.6 Sol (xHigh)OpenAI1485$20±444,005$4
23Qwen3.8-MaxAlibaba1484$6.00±535,805$2
24Gemini 3.6 Flash (High)Google1483$3.75±435,428$0.75
25GLM-5.3 (Max)Z.ai1483$4.40±530,524$1.4
27GPT-6.1 Sol (Max)OpenAI1482$10±612,564$2
28GPT-5.5 (High)OpenAI1481$30±468,361$5
36DeepSeek-V4.1-Flash-20260910 (Max)DeepSeek1475$1.20±613,579$0.3
37Grok 4.20 Beta 1xAI1475–±527,679N/A

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

On the Text Arena board Arena published on 8 Nov 2026 (style control off), Gemini 4 Carbon (High) (Google) ranked #1 with an Arena rating of 1538.9 (lower 1529.4, upper 1548.5).

What changed: Since the Arena dataset board published 6 Nov 2026, Gemini 4 Carbon (High) stayed #1 (1539.1 → 1538.9); the top 10 kept the same models in the same 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
8 Nov 2026, the leaderboard_publish_date in Arena’s dataset
Read by ChatJudge
15 Nov 2026 (dataset file SHA-256 8f6282c5efc4…)
Rows
31 of 420 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, 8 Nov 2026
RankModelOrganisation (as published)Arena ratingLowerUpperVotes
1Gemini 4 Carbon (High)google1538.91529.41548.54,281
2Gemini 4 Argon (High)google1529.81524.31535.318,850
3Claude Fable 5.1 (Max)anthropic1512.71507.21518.319,755
4Claude Opus 5.5 (High)anthropic1512.71506.61518.814,815
5Claude Opus 5 (Max)anthropic1506.21501.61510.935,712
6Muse Wonder (Max)meta1504.31497.81510.711,483
7Claude Opus 5 (High)anthropic1502.41498.81506.073,730
8Claude Opus 4.6 (High)anthropic1501.61498.31504.884,428
9Gemini 3.8 Flash (High)google1500.41496.21504.659,624
10Claude Opus 4.6anthropic1496.81493.61499.989,224
11MiMo-V2.6-Proxiaomi1491.71482.31501.14,069
12Claude Fable 5 (High)anthropic1491.51487.31495.645,562
13Muse Spark 1.3 (Max)meta1491.21486.11496.225,563
14Claude Opus 4.7 (High)anthropic1489.61485.91493.464,295
15Gemini 3.7 Flash (High)google1488.81484.11493.433,306
16Qwen3.8-Maxalibaba1485.51480.91490.135,805
17Muse Spark 1.2 (xHigh)meta1484.41478.51490.314,561
18Claude Opus 4.7anthropic1483.11479.31486.965,387
19Gemini 3.5 Flash (High)google1482.81478.91486.747,646
20Gemini 3.1 Pro Previewgoogle1480.11477.21483.0132,347
21Gemini 3 Progoogle1479.51475.71483.341,839
22Gemini 3.6 Flash (High)google1479.41475.01483.835,428
23Muse Spark 1.1meta1478.61474.51482.845,555
24Gemini 3.5 Flash (Medium)google1477.81473.71482.046,403
25GLM-5.3 (Max)zai1476.01471.21480.730,524
27Kimi K3 (Max)moonshot1474.51470.21478.840,409
30GPT-5.5 (High)openai1471.11467.41474.868,361
39DeepSeek-V4.1-Flash-20260910 (Max)deepseek1463.41457.31469.513,579
50Grok 4.20 Beta (Reasoning, 0309)xai1451.21447.51454.965,716
97Mistral Large 3mistral1428.71425.91431.588,677
99MiniMax-M3minimax1428.31424.61432.072,449

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.