Home / Best AI for… / Best AI for Writing
Task ranking
Best AI for Writing
Ranked by crowd preference (LMArena Elo) where available — writers are the toughest crowd — then League Score.
Our top pick: Claude Opus 5 — LMArena Elo 1522 · League Score 92 · $5.00/$25.00 per 1M. Full record, pricing and benchmarks on its model page; or run the model picker for a recommendation matched to your budget and context needs.
| # | Model | Maker | Why it ranks here |
|---|---|---|---|
| 1 | Claude Opus 5 | Anthropic | LMArena Elo 1522 · League Score 92 · $5.00/$25.00 per 1M |
| 2 | GPT-5.6 Sol | OpenAI | LMArena Elo 1514 · League Score 82 · $4.00/$20.00 per 1M |
| 3 | Gemini 3.1 Pro Preview | Google DeepMind | LMArena Elo 1500 · League Score 52 · $2.00/$12.00 per 1M |
| 4 | Kimi K3 | Moonshot AI | LMArena Elo 1500 · League Score 63 · $3.00/$15.00 per 1M |
| 5 | Claude Sonnet 5 | Anthropic | LMArena Elo 1479 · League Score 74 · $2.00/$10.00 per 1M |
| 6 | DeepSeek V4 Pro (0813) | DeepSeek | LMArena Elo 1462 · League Score 63 · $1.32/$3.96 per 1M |
| 7 | Gemini 3.5 Flash-Lite | Google DeepMind | LMArena Elo 1418 · League Score 70 · $0.30/$2.50 per 1M |
| 8 | Llama 4 Maverick | Meta | LMArena Elo 1352 · League Score 48 |
| 9 | Inkling | Thinking Machines Lab | LMArena Elo 1337 · League Score 43 |
| 10 | Jamba Large 1.7 | AI21 Labs | LMArena Elo 1197 · League Score 0 |
Rankings regenerate from the model database on every data update. Metrics and sources: methodology.