LMArena Creative writing arena · published July 20, 2026
Anthropic leads the LMArena creative writing arena.
As of July 20, 2026, Anthropic leads the LMArena creative writing arena with claude-fable-5 at 1512.8 across 1,798 battles, according to LMArena.
Current through July 20, 2026. 160 published snapshots. 377 of 381 models resolved (4 held for exact-match review).
| Rank | LMArena rating | Organization | Model | Reported interval | Gap to leader | Battles |
|---|---|---|---|---|---|---|
| 01 | 1512.8 | Anthropic | Claude Fable 5 | 1497.9 to 1527.7 | Leader | 1,798 |
| 02 | 1499.1 | Anthropic | claude-opus-4-6-thinking | 1492.0 to 1506.3 | -13.7 | 10,627 |
| 03 | 1487.8 | Anthropic | claude-opus-4-7-thinking | 1479.9 to 1495.8 | -25.0 | 8,434 |
| 04 | 1484.3 | Gemini 3 Pro | 1476.0 to 1492.6 | -28.5 | 6,284 | |
| 05 | 1482.6 | Anthropic | Claude Opus 4.7 | 1474.7 to 1490.4 | -30.2 | 8,647 |
| 06 | 1481.2 | OpenAI | gpt-5.6-sol-xhigh | 1460.9 to 1501.5 | -31.6 | 945 |
| 07 | 1479.3 | Anthropic | claude-opus-4-6 | 1472.3 to 1486.3 | -33.5 | 10,768 |
| 08 | 1477.9 | gemini-3.1-pro-preview | 1471.3 to 1484.4 | -34.9 | 13,886 | |
| 09 | 1468.0 | Anthropic | claude-opus-4-5-20251101-thinking-32k | 1459.6 to 1476.4 | -44.8 | 5,530 |
| 10 | 1466.8 | gemini-3.5-flash-medium | 1453.4 to 1480.3 | -46.0 | 2,233 | |
| 11 | 1464.5 | gemini-3.5-flash-high | 1448.3 to 1480.8 | -48.3 | 1,502 | |
| 12 | 1463.6 | Anthropic | claude-opus-4-8-thinking | 1454.4 to 1472.9 | -49.2 | 5,301 |
| 13 | 1462.9 | Meta | Muse Spark | 1448.7 to 1477.0 | -49.9 | 1,941 |
| 14 | 1461.1 | Anthropic | claude-opus-4-5-20251101 | 1454.5 to 1467.6 | -51.7 | 10,954 |
| 15 | 1460.0 | xAI | grok-4.20-beta1 | 1450.1 to 1470.0 | -52.8 | 3,970 |
| 16 | 1459.4 | Anthropic | claude-opus-4-8 | 1450.2 to 1468.5 | -53.4 | 5,348 |
| 17 | 1458.9 | Meta | muse-spark-1.1 | 1441.7 to 1476.1 | -53.9 | 1,278 |
| 18 | 1458.2 | gemini-3-flash | 1448.8 to 1467.7 | -54.6 | 4,680 | |
| 19 | 1455.6 | OpenAI | gpt-5.5-instant | 1445.6 to 1465.5 | -57.2 | 4,135 |
| 20 | 1453.6 | Anthropic | claude-sonnet-4-5-20250929 | 1447.4 to 1459.8 | -59.2 | 11,987 |
| 21 | 1453.4 | Z.ai | glm-5.1 | 1444.2 to 1462.6 | -59.4 | 5,126 |
| 22 | 1451.6 | Anthropic | claude-sonnet-4-6 | 1444.2 to 1458.9 | -61.2 | 9,245 |
| 23 | 1448.5 | Alibaba | qwen3.5-max-preview | 1437.3 to 1459.6 | -64.3 | 3,141 |
| 24 | 1448.3 | xAI | grok-4.20-multi-agent-beta-0309 | 1441.0 to 1455.5 | -64.5 | 9,740 |
| 25 | 1447.3 | Anthropic | claude-sonnet-4-5-20250929-thinking-32k | 1441.2 to 1453.3 | -65.5 | 12,279 |
Frontier race
Category Kings: Creative writing arena frontier by organization
Anthropic holds the creative writing arena frontier at 1513 as of July 20, 2026.
Method: Frontier is the maximum resolved LMArena rating per organization on each publish date. Organizations limited to the union of the seven tracked homepage providers and organizations in the latest board top 25 by officialRank. Quarantined dates are excluded, and this category series keeps its own method epoch and is never joined to the legacy archive.
| Organization | Latest model | Latest LMArena rating | First tracked date |
|---|---|---|---|
| Anthropic | anthropic/claude-fable-5 | 1512.8 | October 23, 2024 |
| google/gemini-3-pro | 1484.3 | October 23, 2024 | |
| OpenAI | openai/gpt-5.6-sol-xhigh | 1481.2 | October 23, 2024 |
| Meta | meta/muse-spark | 1462.9 | October 23, 2024 |
| xAI | xai/grok-4.20-beta1 | 1460.0 | October 23, 2024 |
| Z.ai | zai/glm-5.1 | 1453.4 | October 23, 2024 |
| Alibaba | alibaba/qwen3.5-max-preview | 1448.5 | October 23, 2024 |
| DeepSeek | deepseek/deepseek-v4-pro | 1443.6 | October 23, 2024 |
| Mistral AI | mistral/mistral-medium-3.5 | 1394.4 | October 23, 2024 |
Definitions
What these terms mean.
- Creative writing arena
- The LMArena style-controlled text battles filtered to prompts categorized as creative writing. It reflects human preference on those prompts, not editorial quality judged by professionals.
- Frontier by organization
- The highest resolved score for each organization on each publish date. It tracks how far each lab has pushed this category, not an average of all its models.
- Confidence interval
- The reported 95% range LMArena publishes with each rating. Overlapping intervals mean this snapshot does not separate those ranks decisively.
Follow the evidence
Compare this board against the overall LMArena rankings, shortlist candidates with the Writing and marketing guide,read the Anthropic lab file, and see how rankings are selected. Model profiles on this board: Claude Fable 5, Gemini 3 Pro, Claude Opus 4.7.
Creative writing arena questions
Which model leads the Creative writing arena right now?
According to the LMArena creative writing board published July 20, 2026, Anthropic leads with claude-fable-5 at 1512.8, across 1,798 battles. That is 13.7 points ahead of the next board entry inside this one snapshot.
Is this a Model Gauntlet creative writing ranking?
No. This board mirrors one named source, the LMArena creative writing arena, published July 20, 2026. Model Gauntlet publishes no composite or consensus score and runs no evaluation of its own.
How many models and organizations are in the creative writing board?
The reviewed artifact covers 381 models across 61 organizations, with 377 models resolved to exact identities and 4 held for review. The history spans 160 snapshots from October 23, 2024 to July 20, 2026.
Why do some scores have overlapping confidence intervals?
LMArena publishes a 95% confidence interval with each rating. Where two intervals overlap, this single snapshot does not separate those ranks decisively, so treat small creative writing gaps with caution.