Choose a model for your task
Domain: Creative Writing. The evidence below is scoped to this domain.
64 models5 prompts24 votes
🗳️316 cells awaiting votesHow ranking works: Wilson 95% lower bound, 5 votes to rank, 30 to calibrate, arena Elo. How scores are calculated
Prompt × Model | 🥇 #1 Claude 3.5 Sonnet (Anthropic) 200K ⚡2.91 pts/$($15/1M) Elo Unavailable CI unavailable — insufficient evidence — fewer_than_two_eligible_cells | 🥈 #2 Gemini 1.5 Pro (Google) 2M ⚡8.73 pts/$($5/1M) Elo Unavailable CI unavailable — insufficient evidence — fewer_than_two_eligible_cells | 🥉 #3 DeepSeek V3 Open164K ⚡3.38 pts/$($0.89/1M) Elo Unavailable CI unavailable — insufficient evidence — fewer_than_two_eligible_cells | #4 Qwen 2.5 72B (Alibaba) Open131K ⚡7.51 pts/$($0.4/1M) Elo Unavailable CI unavailable — insufficient evidence — fewer_than_two_eligible_cells | #5 Claude Haiku 4 5 200K Elo Unavailable | #6 Claude Opus 4 8 Low Elo Unavailable | #7 Claude Sonnet 4 200K Elo Unavailable | #8 Claude Sonnet 4 5 200K Elo Unavailable | #9 Deepseek V3 2 Open131K Elo Unavailable | #10 Deepseek V4 1 Flash Open1.0M Elo Unavailable | #11 Deepseek V4 1 Flash High Elo Unavailable | #12 Deepseek V4 1 Flash Low Elo Unavailable | #13 Deepseek V4 1 Flash Max Elo Unavailable | #14 Deepseek V4 Flash Open1M Elo Unavailable | #15 Deepseek V4 Flash High Elo Unavailable | #16 Deepseek V4 Flash Max Elo Unavailable | #17 Devin Swe 1 7 Max Elo Unavailable | #18 GPT-4o (OpenAI) 128K Elo Unavailable | #19 Gemini 3 1 Flash Lite 1.0M Elo Unavailable | #20 Gemini 3 1 Flash Lite Low Elo Unavailable | #21 Gemini 3 1 Flash Lite Medium Elo Unavailable | #22 Gemini 3 5 Flash Lite 1.0M Elo Unavailable | #23 Gemini 3 8 Flash 1.0M Elo Unavailable | #24 Gemini 3 8 Flash High Elo Unavailable | #25 Gemini 3 8 Flash Low Elo Unavailable | #26 Gemini 3 8 Flash Medium Elo Unavailable | #27 Gemini Flash 3 1 Lite High Elo Unavailable | #28 Gemini Flash 3 1 Lite Low Elo Unavailable | #29 Gemini Flash 3 1 Lite Medium Elo Unavailable | #30 Glm 5 Open203K Elo 1184 | #31 Glm 5 3 Flash Open1.0M Elo Unavailable | #32 Grok 4 6 Low Elo 1216 | #33 Hy3 Open262K Elo Unavailable | #34 Hy4 Preview Open1.0M Elo Unavailable | #35 Inkling Small Open524K Elo Unavailable | #36 Laguna S 2 1 Open1.0M Elo Unavailable | #37 Ling 3 0 Flash Sante 256K Elo Unavailable | #38 Longcat 2 0 1M Elo Unavailable | #39 Mimo V2 5 Open1M Elo Unavailable | #40 Mimo V2 5 Pro Open1.0M Elo Unavailable | #41 Minimax M2 1 Open205K Elo Unavailable | #42 Minimax M2 5 Open205K Elo Unavailable | #43 Minimax M3 Open524K Elo Unavailable | #44 Minimax M3 High Elo Unavailable | #45 Minimax M3 Low Elo Unavailable | #46 Minimax M3 Medium Elo Unavailable | #47 Muse Spark Elo 1218.3 | #48 Nemotron 3 Ultra Open131K Elo Unavailable | #49 Nemotron 3 Ultra 550b A55b Open262K Elo Unavailable | #50 Omen Alpha 500K Elo 1181.7 | #51 Penguin Max Elo Unavailable | #52 Qwen 3 7 Flash 1M Elo Unavailable | #53 Qwen 3 8 27b Open1M Elo Unavailable | #54 Qwen 3 8 Flash 1M Elo Unavailable | #55 Qwen 3 8 Flash Low Elo Unavailable | #56 Qwen 3 8 Flash Medium Elo Unavailable | #57 Qwen 3 8 Flash Next Open262K Elo Unavailable | #58 Qwen 3 8 Flash Xhigh Elo Unavailable | #59 Qwen 3 8 Max 1M Elo Unavailable | #60 Qwen3 Coder Next Open262K Elo Unavailable | #61 Step 3 5 Flash Open262K Elo Unavailable | #62 Step 3 7 Flash Open262K Elo Unavailable | #63 Swe 2 Low Elo Unavailable | #64 Swe 2 Medium Elo Unavailable |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
قصيدة عمودية في الذكاء الاصطناعي Creative Writing | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
افتتاحية رواية تاريخية في بغداد Creative Writing | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
حوار بلاغي رمزي بين الماء والصحراء Creative Writing | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
مقطوعة شعرية نبطية في الكرم Creative Writing | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
قصة أطفال رمزية حول الأمان الرقمي Creative Writing |