Rankings
Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works
Score and price
| # | Model | Provider | Text Arena | Price $/M |
|---|---|---|---|---|
| 1 | Gemini 4 Carbon | 1527 | $2 / $10 | |
| 2 | Gemini 4 Argon | 1520 | $2 / $10 | |
| 3 | Gemini 4 Neon | 1513 | $1.50 / $7.50 | |
| 4 | Muse Wonder | Meta | 1511 | $4 / $20 |
| 5 | Claude Opus 5.5 | Anthropic | 1506 | $4 / $20 |
| 6 | Claude Fable 5 | Anthropic | 1504 | $10 / $50 |
| 7 | Claude Fable 5.2 | Anthropic | 1503 | $8 / $40 |
| 8 | Claude Fable 5.1 | Anthropic | 1503 | $10 / $50 |
| 9 | Muse Spark 1.3 | Meta | 1498 | $1.25 / $4.25 |
| 10 | Gemini 3.8 Flash | 1497 | $0.75 / $3.75 | |
| 11 | Gemini 4 Hydrogen | 1490 | $1.50 / $7.50 | |
| 12 | Claude Opus 5 | Anthropic | 1490 | $5 / $25 |
| 13 | Gemini 3.7 Flash | 1490 | $0.75 / $3.75 | |
| 14 | Kimi K3 | Moonshot AI | 1488 | $3 / $15 |
| 15 | GPT-5.6 Sol | OpenAI | 1485 | $4 / $20 |
| 16 | Qwen3.8-Max | Alibaba | 1484 | $2 / $6 |
| 17 | GPT-6.1 Sol | OpenAI | 1483 | $2 / $10 |
| 18 | Kimi K3.1 Pro | Moonshot AI | 1482 | $2 / $10 |
| 19 | GLM-5.3 | Z.ai | 1482 | $1.40 / $4.40 |
| 20 | Claude Opus 4.8 | Anthropic | 1482 | $5 / $25 |
| 21 | MiMo-V2.6-Pro | Xiaomi | 1481 | $0.43 / $0.87 |
| 22 | GPT-6 Astra | OpenAI | 1475 | $10 / $50 |
| 23 | DeepSeek V4.1 Flash | DeepSeek | 1475 | $0.15 / $0.60 |
| 24 | GLM-5.3-Flash | Z.ai | 1475 | $0.02 / $0.07 |
| 25 | GPT-6.1 Terra | OpenAI | 1474 | $1 / $5 |
| 26 | Claude Sonnet 5.5 | Anthropic | 1473 | $2 / $10 |
| 27 | GPT-6.2 Astra | OpenAI | 1468 | $8 / $40 |
| 28 | GPT-6.2 Sol | OpenAI | 1465 | $2 / $10 |
| 29 | Claude Sonnet 5 | Anthropic | 1461 | $2 / $10 |
| 30 | GPT-6 Sol | OpenAI | 1458 | $2 / $10 |
| 31 | Grok 4.6 | xAI | 1457 | $1.60 / $4.80 |
| 32 | Step 5 Preview | StepFun | 1449 | $1 / $2.70 |
| 33 | MiMo-V2.6-Flash | Xiaomi | 1448 | $0.14 / $0.28 |
| 34 | Grok 4.7 | xAI | 1443 | $2 / $6 |
| 35 | GPT-6 Luna | OpenAI | 1443 | $0.10 / $0.50 |
| 36 | Qwen3.8-27B | Alibaba | 1435 | $0.40 / $3 |
| 37 | Beam 1.0 | Reflection AI | 1434 | $0.30 / $1 |
| 38 | Mistral Large 4 | Mistral | 1423 | $0.70 / $2.10 |
| 39 | Claude Haiku 5.5 | Anthropic | 1421 | $0.10 / $0.50 |
| 40 | Inkling 2 Small | Thinking Machines | 1412 | $0.30 / $1 |
Other benchmarks
Frequently asked questions
What does Text Arena measure?
Blind head-to-head votes on everyday prompts, from writing and analysis to Q&A, turned into an Elo-style rating.
Which model has the highest Text Arena score?
Gemini 4 Carbon from Google leads Text Arena at 1527, ahead of Gemini 4 Argon (1520).
Why does Text Arena matter to engineering leaders?
A good proxy for how the model feels to the rest of the company: drafting documents, summarising, answering questions.
What are the limitations of Text Arena?
Style and formatting sway votes. A 10-point Elo gap is roughly a 51/49 preference split, so the top cluster is effectively tied.