LMArena Text Arena snapshot: 22 Oct 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 22 Oct 2026 (default view), Gemini 4 Argon (High) (Google) ranked #1 with an Arena score of 1517 (±7).
What changed: Since the board dated 20 Oct 2026, Gemini 4 Argon (High) stayed #1 (1524 → 1517); 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
- 22 Oct 2026, as printed on the LMArena leaderboard page
- Checked by ChatJudge
- 25 Oct 2026 to 28 Oct 2026
- Rows
- 29 of 418 models listed. Top 25 overall, plus the best-ranked entry for OpenAI, xAI, DeepSeek and Z.ai (ranks 26–39).
Note: ChatJudge’s first copy of this board (25 Oct 2026) tagged Gemini 4 Argon (High) as Preliminary; later copies do not. The rows here are the later copy.
| Rank | Model | Provider | Arena score | Output price ($ per 1M tokens) | ± | Votes | Input price ($/1M) |
|---|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argon (High) | 1517 | $10 | ±7 | 10,083 | $2 | |
| 2 | Claude Opus 5.5 (High) | Anthropic | 1509 | $20 | ±7 | 10,322 | $4 |
| 3 | Muse Wonder (Max) | Meta | 1509 | $20 | ±8 | 6,001 | $4 |
| 4 | Claude Fable 5 (High) | Anthropic | 1503 | $50 | ±4 | 44,253 | $10 |
| 5 | Claude Fable 5.1 (Max) | Anthropic | 1503 | $50 | ±6 | 16,343 | $10 |
| 6 | Claude Opus 4.6 (High) | Anthropic | 1503 | $25 | ±3 | 83,454 | $5 |
| 7 | Claude Opus 4.7 (High) | Anthropic | 1501 | $25 | ±4 | 65,140 | $5 |
| 8 | Claude Opus 4.6 | Anthropic | 1497 | $25 | ±3 | 88,206 | $5 |
| 9 | Gemini 3.8 Flash (High) Preliminary | 1496 | $3.75 | ±4 | 43,997 | $0.75 | |
| 10 | Muse Spark 1.3 (Max) | Meta | 1496 | $4.25 | ±5 | 20,506 | $1.25 |
| 11 | Claude Opus 4.7 | Anthropic | 1494 | $25 | ±4 | 66,183 | $5 |
| 12 | Muse Spark 1.2 (xHigh) | Meta | 1491 | $4.25 | ±7 | 10,470 | $1.25 |
| 13 | Claude Opus 5 (Max) | Anthropic | 1491 | $25 | ±5 | 34,526 | $5 |
| 14 | Claude Opus 5 (High) | Anthropic | 1491 | $25 | ±4 | 71,020 | $5 |
| 15 | Muse Spark 1.1 | Meta | 1490 | $4.25 | ±4 | 46,121 | $1.25 |
| 16 | Gemini 3.7 Flash (High) Preliminary | 1490 | $3.75 | ±5 | 30,501 | $0.75 | |
| 17 | Muse Spark | Meta | 1489 | – | ±6 | 14,147 | N/A |
| 18 | Kimi K3 (Max) | Moonshot | 1487 | – | ±4 | 35,379 | N/A |
| 19 | Gemini 3.1 Pro Preview | 1487 | $6.00 | ±3 | 130,819 | $1 | |
| 20 | Gemini 3 Pro | 1486 | $12 | ±4 | 42,054 | $2 | |
| 21 | GPT-5.6 Sol (xHigh) | OpenAI | 1485 | $20 | ±4 | 42,713 | $4 |
| 22 | Gemini 3.6 Flash (High) | 1483 | $3.75 | ±4 | 36,102 | $0.75 | |
| 23 | Qwen3.8-Max | Alibaba | 1483 | $6.00 | ±5 | 30,500 | $2 |
| 24 | GPT-5.5 (High) | OpenAI | 1482 | $30 | ±4 | 69,375 | $5 |
| 25 | Claude Opus 4.8 (High) | Anthropic | 1481 | $25 | ±4 | 64,096 | $5 |
| 26 | GLM-5.3 (Max) | Z.ai | 1481 | $4.40 | ±5 | 25,144 | $1.4 |
| 27 | GPT-6.1 Sol (Max) | OpenAI | 1480 | $10 | ±7 | 8,305 | $2 |
| 34 | DeepSeek-V4.1-Flash-20260910 (Max) | DeepSeek | 1476 | $1.20 | ±6 | 13,750 | $0.3 |
| 39 | Grok 4.20 Beta 1 | xAI | 1475 | – | ±5 | 27,914 | N/A |
Text Arena Overall: style control off, from Arena’s published dataset
On the Text Arena board Arena published on 22 Oct 2026 (style control off), Gemini 4 Argon (High) (Google) ranked #1 with an Arena rating of 1525.7 (lower 1519.2, upper 1532.3).
What changed: Since the Arena dataset board published 20 Oct 2026, Gemini 4 Argon (High) stayed #1 (1532.3 → 1525.7); Muse Spark 1.3 (Max) entered the top 10 and Claude Fable 5 (High) dropped out.
- 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
- 22 Oct 2026, the leaderboard_publish_date in Arena’s dataset
- Read by ChatJudge
- 15 Nov 2026 (dataset file SHA-256 8f6282c5efc4…)
- Rows
- 31 of 418 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.
- Same view on arena.ai
- Text Arena, no style control ↗
| Rank | Model | Organisation (as published) | Arena rating | Lower | Upper | Votes |
|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argon (High) | 1525.7 | 1519.2 | 1532.3 | 10,083 | |
| 2 | Claude Opus 5.5 (High) | anthropic | 1516.2 | 1509.4 | 1523.0 | 10,322 |
| 3 | Claude Fable 5.1 (Max) | anthropic | 1512.5 | 1506.7 | 1518.4 | 16,343 |
| 4 | Claude Opus 5 (Max) | anthropic | 1508.3 | 1503.7 | 1513.0 | 34,526 |
| 5 | Claude Opus 5 (High) | anthropic | 1503.3 | 1499.7 | 1506.9 | 71,020 |
| 6 | Claude Opus 4.6 (High) | anthropic | 1501.5 | 1498.2 | 1504.7 | 83,454 |
| 7 | Muse Wonder (Max) | meta | 1500.5 | 1492.5 | 1508.6 | 6,001 |
| 8 | Gemini 3.8 Flash (High) | 1498.3 | 1493.8 | 1502.8 | 43,997 | |
| 9 | Claude Opus 4.6 | anthropic | 1496.8 | 1493.7 | 1500.0 | 88,206 |
| 10 | Muse Spark 1.3 (Max) | meta | 1491.1 | 1485.8 | 1496.4 | 20,506 |
| 11 | MiMo-V2.6-Pro | xiaomi | 1491.1 | 1481.8 | 1500.4 | 4,067 |
| 12 | Claude Fable 5 (High) | anthropic | 1490.9 | 1486.7 | 1495.2 | 44,253 |
| 13 | Claude Opus 4.7 (High) | anthropic | 1489.7 | 1486.0 | 1493.5 | 65,140 |
| 14 | Gemini 3.7 Flash (High) | 1489.5 | 1484.8 | 1494.2 | 30,501 | |
| 15 | Qwen3.8-Max | alibaba | 1483.6 | 1478.8 | 1488.4 | 30,500 |
| 16 | Claude Opus 4.7 | anthropic | 1483.0 | 1479.2 | 1486.7 | 66,183 |
| 17 | Muse Spark 1.2 (xHigh) | meta | 1481.9 | 1475.3 | 1488.5 | 10,470 |
| 18 | Gemini 3.5 Flash (High) | 1481.9 | 1478.0 | 1485.7 | 48,504 | |
| 19 | Gemini 3.1 Pro Preview | 1480.2 | 1477.3 | 1483.2 | 130,819 | |
| 20 | Gemini 3.6 Flash (High) | 1479.6 | 1475.2 | 1484.0 | 36,102 | |
| 21 | Gemini 3 Pro | 1479.5 | 1475.7 | 1483.2 | 42,054 | |
| 22 | Muse Spark 1.1 | meta | 1477.9 | 1473.8 | 1482.0 | 46,121 |
| 23 | Gemini 3.5 Flash (Medium) | 1477.8 | 1473.7 | 1481.9 | 47,271 | |
| 24 | Qwen3.7-Max-Preview | alibaba | 1475.1 | 1465.4 | 1484.8 | 3,941 |
| 25 | Kimi K3 (Max) | moonshot | 1475.0 | 1470.6 | 1479.5 | 35,379 |
| 27 | GLM-5.3 (Max) | zai | 1473.9 | 1468.9 | 1478.9 | 25,144 |
| 30 | GPT-5.5 (High) | openai | 1471.5 | 1467.8 | 1475.2 | 69,375 |
| 37 | DeepSeek-V4.1-Flash-20260910 (Max) | deepseek | 1464.3 | 1458.2 | 1470.3 | 13,750 |
| 51 | Grok 4.20 Beta (Reasoning, 0309) | xai | 1450.9 | 1447.3 | 1454.6 | 66,418 |
| 92 | Mistral Large 4 | mistral | 1431.9 | 1425.4 | 1438.3 | 10,331 |
| 93 | MiniMax-M3 | minimax | 1431.7 | 1428.0 | 1435.5 | 67,030 |
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.
