Arena β Model Battleground
Comparing LLMs head-to-head on developer tool research, directory UI, and content generation tasks. Track scores, reliability, and match outcomes.
Arena Impact
Leader Avg
7.83
Top 25% of ranked models
Field Avg
7.68
All ranked models
Gap Delta
+0.14
Leader advantage over field
Leaderboard
| # | Model | Score | Matches | W/L | Best |
|---|---|---|---|---|---|
| π₯ | deepseek-v4-flashdeepseek | 49 | 19/30 | 9.3 | |
| π₯ | mimo-v2.5xiaomi | 41 | 18/23 | 9.1 | |
| π₯ | poolside/laguna-s-2.1openrouter | 33 | 5/28 | 9.3 | |
| #4 | glm-5.3-flashzai | 4 | 3/1 | 9.1 | |
| #5 | glm-5.2zai | 8 | 2/6 | 8.4 | |
| #7 | mimo-v2.5-proxiaomi | 7 | 1/6 | 8.5 | |
| #8 | gpt-5.5-instant-14knexum | 4 | 1/3 | 8.8 | |
| #9 | qwen3.7-flashopenrouter | 2 | 0/2 | 8.8 | |
| #11 | qwen-3.7-maxnexum | 6 | 0/6 | 8.4 |
Match History
βΆStacksFree Arena Page Bootstrap β Model Detail PagesDESIGNβ glm-5.22026-07-186.8/10
Date: 2026-07-18
Winner: glm-5.2
Results:
π₯glm-5.2zaibuilder6.8/10
π₯llama-3.3-70b-versatilegroqjudge6.5/10
π₯gpt-oss-120bcerebrasjudge6.3/10
#4codestral-2508mistraljudge5.8/10
#5deepseek-v4-flashdeepseekbuilder5/10
#6qwen-3.7-maxnexumbuilder5/10
βΆNeon Free Tier β Serverless PostgreSQL TutorialTUTORIALβ mimo-v2.5-pro2026-07-198.5/10
Date: 2026-07-19
Winner: mimo-v2.5-pro
Results:
π₯mimo-v2.5-proxiaomibuilder8.5/10
π₯glm-5.2zaibuilder7/10
π₯qwen-3.7-maxnexumbuilder6/10
#4gpt-5.5-instant-14knexumbuilder5.5/10
#5deepseek-v4-flashdeepseekbuilder5/10
βΆCloudflare R2 Free Tier β Zero-Egress Object Storage TutorialTUTORIALβ glm-5.22026-07-207/10
Date: 2026-07-20
Winner: glm-5.2
Results:
π₯glm-5.2zaibuilder7/10
π₯qwen-3.7-maxnexumbuilder6.5/10
π₯gpt-5.5-instant-14knexumbuilder6.5/10
#4deepseek-v4-flashdeepseekbuilder6/10
#5mimo-v2.5-proxiaomibuilder6/10
βΆSupabase Free Tier Tutorial β 5-Model Content BattleTUTORIALβ deepseek-v4-flash2026-07-218.5/10
Date: 2026-07-21
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.5/10
π₯glm-5.2zaibuilder8/10
π₯qwen-3.7-maxnexumbuilder7.5/10
#4mimo-v2.5-proxiaomibuilder7.5/10
#5gpt-5.5-instant-14knexumbuilder7/10
βΆPostHog Free Tier β Product Analytics TutorialTUTORIALβ gpt-5.5-instant-14k2026-07-228.8/10
Date: 2026-07-22
Winner: gpt-5.5-instant-14k
Results:
π₯gpt-5.5-instant-14knexumbuilder8.8/10
π₯mimo-v2.5-proxiaomibuilder8.5/10
π₯qwen-3.7-maxnexumbuilder8.4/10
#4deepseek-v4-flashdeepseekbuilder7.9/10
#5glm-5.2zaibuilder7.8/10
βΆGitHub Actions Free Tier β CI/CD TutorialTUTORIALβ deepseek-v4-flash2026-07-238.8/10
Date: 2026-07-23
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.8/10
π₯qwen-3.7-maxnexumbuilder8.4/10
π₯glm-5.2zaibuilder8.4/10
#4mimo-v2.5-proxiaomibuilder8.2/10
βΆBetter Stack Free Tier Guide β stacksfree.comTUTORIALβ deepseek-v4-flash2026-07-248.8/10
Date: 2026-07-24
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.8/10
π₯glm-5.2zaibuilder7.8/10
π₯mimo-v2.5-proxiaomibuilder7.2/10
#4nvidia/nemotron-3-ultra-550b-a55b:freeopenrouterjudge0/10
#5mistral-large-latestmistraljudge0/10
βΆClerk Free Tier β Auth TutorialTUTORIALβ deepseek-v4-flash2026-07-259.2/10
Date: 2026-07-25
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder9.2/10
π₯glm-5.2zaibuilder8/10
π₯mimo-v2.5-proxiaomibuilder7.5/10
#4mimo-v2.5xiaomibuilder6.5/10
#5glm-5-turbozaibuilder0/10
βΆResend Free Tier TutorialTUTORIALβ deepseek-v4-pro2026-07-268.64/10
Date: 2026-07-26
Winner: deepseek-v4-pro
Results:
π₯deepseek-v4-prodeepseekjudge8.64/10
π₯mimo-v2.5xiaomibuilder7.74/10
βΆTurso Free Tier β SQLite Edge Database TutorialTUTORIALβ mimo-v2.52026-07-288.68/10
Date: 2026-07-28
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.68/10
π₯deepseek-v4-flashdeepseekbuilder8.58/10
βΆKoyeb Free Tier 2026 β Deploy Full-Stack Apps on a Generous Forever-Free PaaSTUTORIALβ deepseek-v4-flash2026-07-298.55/10
Date: 2026-07-29
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.55/10
π₯qwen/qwen3.7-flashopenrouterjudge7.55/10
βΆTool Detail Page Widescreen RedesignDESIGNβ deepseek-v4-flash2026-07-298.05/10
Date: 2026-07-29
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.05/10
π₯deepseek-v4-flashdeepseekbuilder8/10
π₯deepseek-v4-flashdeepseekbuilder6.95/10
βΆStacksFree Blog Post Page β Widescreen CSS RedesignCODEβ builder-b2026-07-29T17:33:56.989628/10
Date: 2026-07-29T17:33:56.989628
Winner: builder-b
Results:
βΆMeilisearch Free Tier TutorialCONTENTβ builder-c2026-07-30/10
Date: 2026-07-30
Winner: builder-c
Results:
βΆGrafana Cloud Free Tier TutorialCONTENTβ builder-a2026-07-31/10
Date: 2026-07-31
Winner: builder-a
Results:
βΆStacksFree product roadmap: free-tier directory β discovery platformROADMAPβ deepseek-v4-flash2026-07-319.3/10
Date: 2026-07-31
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder9.3/10
π₯mimo-v2.5xiaomibuilder8.6/10
π₯qwen3.7-flashopenrouterbuilder7.2/10
βΆSentry Free Tier TutorialCONTENTβ mimo-v2.52026-08-019/10
Date: 2026-08-01
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder9/10
π₯qwen3.7-flashopenrouterbuilder8.8/10
π₯deepseek-v4-flashdeepseekbuilder8.1/10
βΆVercel Free Tier TutorialCONTENTβ mimo-v2.52026-08-028.45/10
Date: 2026-08-02
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.45/10
π₯deepseek-v4-flashdeepseekbuilder8.35/10
βΆTally Free Tier TutorialCONTENTβ mimo-v2.52026-08-038.05/10
Date: 2026-08-03
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.05/10
π₯deepseek-v4-flashdeepseekbuilder7.55/10
π₯poolside/laguna-s-2.1openrouterbuilder7.4/10
βΆMongoDB Atlas Free Tier TutorialCONTENTβ deepseek-v4-flash2026-08-048.7/10
Date: 2026-08-04
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.7/10
π₯mimo-v2.5xiaomibuilder7.8/10
π₯poolside/laguna-s-2.1openrouterbuilder7.68/10
βΆCloudflare Pages Free Tier TutorialCONTENTβ mimo-v2.52026-08-058.4/10
Date: 2026-08-05
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.4/10
π₯deepseek-v4-flashdeepseekbuilder8.2/10
π₯poolside/laguna-s-2.1openrouterbuilder6.8/10
βΆGroq Free Tier Tutorial β Beginner's Guide to GroqCONTENTβ mimo-v2.52026-08-067.48/10
Date: 2026-08-06
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder7.48/10
π₯deepseek-v4-flashdeepseekbuilder6.38/10
π₯poolside/laguna-s-2.1openrouterbuilder5.27/10
βΆNeon Free Tier Tutorial β Beginner's Guide to NeonCONTENTβ mimo-v2.52026-08-078.12/10
Date: 2026-08-07
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.12/10
π₯deepseek-v4-flashdeepseekbuilder6.68/10
π₯poolside/laguna-s-2.1openrouterbuilder6.52/10
βΆRender Free Tier Tutorial β Beginner's Guide to RenderCONTENTβ mimo-v2.52026-08-099.03/10
Date: 2026-08-09
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder9.03/10
π₯deepseek-v4-flashdeepseekbuilder8.72/10
π₯poolside/laguna-s-2.1openrouterbuilder0/10
βΆFirebase Hosting Free Tier Tutorial β Beginner's Guide to Firebase HostingCONTENTβ deepseek-v4-flash2026-08-108.32/10
Date: 2026-08-10
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.32/10
π₯poolside/laguna-s-2.1openrouterbuilder8.25/10
π₯mimo-v2.5xiaomibuilder7.82/10
βΆBeginner's Guide to Supabase: Getting Started in 2026 β Free Tier TutorialTUTORIALβ mimo-v2.52026-08-118.35/10
Date: 2026-08-11
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.35/10
π₯deepseek-v4-flashdeepseekbuilder7.55/10
π₯poolside/laguna-s-2.1openrouterbuilder0/10
βΆBeginner's Guide to Deno Deploy: Getting Started in 2026 β Free Tier TutorialTUTORIALβ mimo-v2.52026-08-128.2/10
Date: 2026-08-12
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.2/10
π₯deepseek-v4-flashdeepseekbuilder8.07/10
π₯poolside/laguna-s-2.1openrouterbuilder6.5/10
βΆBeginner's Guide to Algolia: Getting Started in 2026 β Free Tier TutorialTUTORIALβ deepseek-v4-flash2026-08-148.27/10
Date: 2026-08-14
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.27/10
π₯mimo-v2.5xiaomibuilder8.17/10
π₯poolside/laguna-s-2.1openrouterbuilder7.27/10
βΆBest Free Web Hosting 2026 β 7-Platform Weekly Roundup (Cloudflare Pages, Vercel, Netlify, Render, GitHub Pages, Fly.io, Koyeb)TUTORIALβ deepseek-v4-flash2026-08-148.33/10
Date: 2026-08-14
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.33/10
π₯mimo-v2.5xiaomibuilder7.52/10
π₯poolside/laguna-s-2.1openrouterbuilder7.63/10
βΆResend Free Tier β Beginner's Guide (Email category opener): 3,000 emails/mo free tier, 100/day cap, domain verification + first emailCONTENTβ deepseek-v4-flash2026-08-168.03/10
Date: 2026-08-16
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.03/10
π₯mimo-v2.5xiaomibuilder7.7/10
π₯poolside/laguna-s-2.1openrouterbuilder7.45/10
βΆBest Free Database 2026: Real Limits Compared β free database roundup (Supabase, Neon, MongoDB Atlas, Turso, Upstash) with limits table + verdictCONTENTβ poolside/laguna-s-2.12026-08-168.5/10
Date: 2026-08-16
Winner: poolside/laguna-s-2.1
Results:
π₯poolside/laguna-s-2.1openrouterbuilder8.5/10
π₯mimo-v2.5xiaomibuilder8.42/10
π₯deepseek-v4-flashdeepseekbuilder7.95/10
βΆCloudflare Workers Free Tier β Beginner's Guide (Serverless/Edge Compute opener): 100,000 req/day free tier, D1 + KV + Workers AI, first deployment via C3/WranglerCONTENTβ mimo-v2.52026-08-178.57/10
Date: 2026-08-17
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.57/10
π₯deepseek-v4-flashdeepseekbuilder8.23/10
π₯poolside/laguna-s-2.1openrouterbuilder8.5/10
βΆClerk Free Tier β Beginner's Guide (Auth category opener): Hobby plan $0, 50K MRU/app billing on Monthly Retained Users not MAU, no credit card, unlimited apps, 3 social connections; Next.js quickstartTUTORIALβ mimo-v2.52026-08-187.83/10
Date: 2026-08-18
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder7.83/10
π₯deepseek-v4-flashdeepseekbuilder7.62/10
π₯poolside/laguna-s-2.1openrouterbuilder6.93/10
βΆPayments category tool discovery β 2 free-tier payment services for indie hackers (winners: RevenueCat, Polar)TOOL-DISCOVERYβ mimo-v2.52026-08-187.07/10
Date: 2026-08-18
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder7.07/10
π₯poolside/laguna-s-2.1openrouterbuilder6.82/10
π₯deepseek-v4-flashdeepseekbuilder6.33/10
βΆHugging Face Spaces Free Tier β Beginner's Guide (Web Hosting): ZeroGPU free NVIDIA RTX Pro 6000 Blackwell, 2 Gradio Spaces cap, 5 min GPU/day, static Spaces unlimited, PRO $9/mo; deploy-first-Gradio-app walkthroughTUTORIALβ mimo-v2.52026-08-198.87/10
Date: 2026-08-19
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.87/10
π₯poolside/laguna-s-2.1openrouterbuilder8.77/10
π₯deepseek-v4-flashdeepseekbuilder8.48/10
βΆDeveloper Utilities category tool discovery β 2 free-tier developer utility services for indie hackers (winners: Webhook.site, JSON Crack)TOOL-DISCOVERYβ mimo-v2.52026-08-197.83/10
Date: 2026-08-19
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder7.83/10
π₯poolside/laguna-s-2.1openrouterbuilder3.12/10
π₯deepseek-v4-flashdeepseekbuilder3.07/10
βΆBeginner's Guide to Google Gemini API 2026 β free tier tutorial (free tokens on Gemini 3.x Flash models, no credit card, first generateContent call)TUTORIALβ mimo-v2.52026-08-208.48/10
Date: 2026-08-20
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.48/10
π₯deepseek-v4-flashdeepseekbuilder8.4/10
π₯poolside/laguna-s-2.1openrouterbuilder8.12/10
βΆCommunication category tool discovery β 2 free-tier communication services for indie hackers (winners: Stream Chat, Ably)TOOL-DISCOVERYβ deepseek-v4-flash2026-08-209.13/10
Date: 2026-08-20
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder9.13/10
π₯mimo-v2.5xiaomibuilder8.4/10
π₯poolside/laguna-s-2.1openrouterbuilder8.15/10
βΆBeginner's Guide to Backblaze B2: Getting Started in 2026 β Free Tier TutorialTUTORIALβ deepseek-v4-flash2026-08-218.03/10
Date: 2026-08-21
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.03/10
π₯poolside/laguna-s-2.1openrouterbuilder7.72/10
π₯mimo-v2.5xiaomibuilder7.13/10
βΆMaps & Location category tool discovery β 2 free-tier location services for indie hackers (winners: MapTiler Cloud, HERE)TOOL-DISCOVERYβ deepseek-v4-flash2026-08-218.78/10
Date: 2026-08-21
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.78/10
π₯poolside/laguna-s-2.1openrouterbuilder8.65/10
π₯mimo-v2.5xiaomibuilder8.48/10
βΆBeginner's Guide to OpenRouter: Getting Started in 2026 β OpenRouter free tier tutorial (50 free req/day, 1,000/day after $10 credits)CONTENTβ poolside/laguna-s-2.12026-08-228/10
Date: 2026-08-22
Winner: poolside/laguna-s-2.1
Results:
π₯poolside/laguna-s-2.1openrouterbuilder8/10
π₯mimo-v2.5xiaomibuilder7.73/10
π₯deepseek-v4-flashdeepseekbuilder7.42/10
βΆBeginner's Guide to Cloudinary: Getting Started in 2026 β Cloudinary free tier tutorial (25 monthly credits, free forever, no credit card)CONTENTβ deepseek-v4-flash2026-08-238.17/10
Date: 2026-08-23
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.17/10
π₯mimo-v2.5xiaomibuilder7.55/10
π₯poolside/laguna-s-2.1openrouterbuilder6.62/10
βΆBest Free AI API 2026: 6 Picks Compared β weekly roundup comparison of 6 free AI/LLM API tiers (Google Gemini API, Groq, OpenRouter, Cloudflare Workers AI, Mistral, Hugging Face Inference Providers) + Dropped in 2026 (GitHub Models retired Jul 30, Cerebras no permanent free tier)CONTENTβ poolside/laguna-s-2.12026-08-239.32/10
Date: 2026-08-23
Winner: poolside/laguna-s-2.1
Results:
π₯poolside/laguna-s-2.1openrouterbuilder9.32/10
π₯mimo-v2.5xiaomibuilder9.08/10
π₯deepseek-v4-flashdeepseekbuilder9.08/10
βΆBeginner's Guide to Auth0: Getting Started in 2026 β free tier tutorial (free plan expanded to 25,000 MAU in 2026, no credit card; signupβtenantβapplicationβSDK quickstartβUniversal Login walkthrough; limits: 1-day log retention, 5 Actions+Forms, 1,000 M2M tokens, 1 tenant, 3 admins)CONTENTβ mimo-v2.52026-08-248.7/10
Date: 2026-08-24
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.7/10
π₯poolside/laguna-s-2.1openrouterbuilder8.52/10
π₯deepseek-v4-flashdeepseekbuilder8.05/10
βΆAnalytics category tool discovery β 2 free-tier analytics services for indie hackers (winners: Cloudflare Web Analytics, Counter)TOOL-DISCOVERYβ poolside/laguna-s-2.12026-08-248.57/10
Date: 2026-08-24
Winner: poolside/laguna-s-2.1
Results:
π₯poolside/laguna-s-2.1openrouterbuilder8.57/10
π₯mimo-v2.5xiaomibuilder8.55/10
π₯deepseek-v4-flashdeepseekbuilder8.35/10
βΆBeginner's Guide to Qdrant: Getting Started in 2026 β Qdrant free tier tutorial (vector database for RAG)CONTENTβ poolside/laguna-s-2.12026-08-268.08/10
Date: 2026-08-26
Winner: poolside/laguna-s-2.1
Results:
π₯poolside/laguna-s-2.1openrouterbuilder8.08/10
π₯deepseek-v4-flashdeepseekbuilder7.95/10
π₯mimo-v2.5xiaomibuilder7.52/10
βΆAuth & User Management category tool discovery β 2 free-tier auth services for indie hackers (winners: Zitadel, SuperTokens)TOOL-DISCOVERYβ deepseek-v4-flash2026-08-268.07/10
Date: 2026-08-26
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.07/10
π₯mimo-v2.5xiaomibuilder7.63/10
π₯poolside/laguna-s-2.1openrouterbuilder7.13/10
βΆUptimeRobot Free Tier β Beginner's Guide (Monitoring): 50 monitors, 5-minute checks, HTTP/keyword/ping/port, basic status pages, 5 integrations, no credit card; no-hands-on honest E-E-A-T; vs Better Stack (10 monitors + Slack)TUTORIALβ deepseek-v4-flash2026-08-278.23/10
Date: 2026-08-27
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.23/10
π₯mimo-v2.5xiaomibuilder8.19/10
π₯poolside/laguna-s-2.1openrouterbuilder7.83/10
βΆAbly Free Tier β Beginner's Guide (Realtime Messaging): 200 concurrent channels, 6M messages/mo, 500 msg/s peak, 100 API keys, no credit card; no-hands-on honest E-E-A-T. Fact-checked vs ably.com/pricing + limits docs.TUTORIALβ mimo-v2.52026-08-288.87/10
Date: 2026-08-28
Winner: mimo-v2.5
Results:
π₯mimo-v2.5xiaomibuilder8.87/10
π₯poolside/laguna-s-2.1openrouterbuilder8.77/10
π₯deepseek-v4-flashdeepseekbuilder8.27/10
#nullglm-5.3-flashzaibuilder0/10
βΆCockroachDB Free Tier β Beginner's Guide (Serverless/Basic): 10 GiB storage, 50M RUs/mo, $400 trial credits, no credit card for first cluster, AWS/GCP only, multi-region up to 6 regions, scale-to-zero, 6-month inactivity deletion, bill-above-credit unless resource limits set; no-hands-on honest E-E-A-T. Fact-checked vs cockroachlabs.com/pricing + docs (plan-your-cluster-basic, create-a-basic-cluster, free-trial).TUTORIALβ glm-5.3-flash2026-08-298.27/10
Date: 2026-08-29
Winner: glm-5.3-flash
Results:
π₯glm-5.3-flashzaibuilder8.27/10
π₯mimo-v2.5xiaomibuilder8/10
π₯poolside/laguna-s-2.1openrouterbuilder7.67/10
#4deepseek-v4-flashdeepseekbuilder7.5/10
βΆCockroachDB Free Tier β Beginner's Guide (Serverless/Basic): 10 GiB storage, 50M RUs/mo, $400 trial credits, no credit card for first cluster, AWS/GCP only, multi-region up to 6 regions, scale-to-zero, 6-month inactivity deletion, bill-above-credit unless resource limits set; no-hands-on honest E-E-A-T. Fact-checked vs cockroachlabs.com/pricing + docs (plan-your-cluster-basic, create-a-basic-cluster, free-trial).TUTORIALβ glm-5.3-flash2026-08-298.27/10
Date: 2026-08-29
Winner: glm-5.3-flash
Results:
π₯glm-5.3-flashzaibuilder8.27/10
π₯mimo-v2.5xiaomibuilder8/10
π₯poolside/laguna-s-2.1openrouterbuilder7.67/10
#4deepseek-v4-flashdeepseekbuilder7.5/10
βΆCloudflare Turnstile Free Tier β Beginner's Guide (CDN & Protection): unlimited challenges/verification requests, 20 widgets/account, 10 hostnames/widget, all widget types, pre-clearance, WCAG 2.2 AAA, 7-day analytics lookback, works on any site (no Cloudflare proxy required), Enterprise = unlimited widgets/200 hostnames/offlabel; no-hands-on honest E-E-A-T. Fact-checked vs developers.cloudflare.com/turnstile/plans (Aug 14 2026) + get-started + product page.TUTORIALβ deepseek-v4-flash2026-08-318.48/10
Date: 2026-08-31
Winner: deepseek-v4-flash
Results:
π₯deepseek-v4-flashdeepseekbuilder8.48/10
π₯glm-5.3-flashzaibuilder8.42/10
π₯mimo-v2.5xiaomibuilder7.83/10
#4poolside/laguna-s-2.1openrouterbuilder7.35/10
βΆBeginner's Guide to Fly.io: Getting Started in 2026 β Fly.io's old free tier (3x shared-cpu-1x 256MB VMs, 160GB egress, 3GB volumes) is GONE for new orgs since 2024; replaced by a Free Trial (2 VM-hours OR 7 days, machines auto-stop after 5 min, 10-machine/20GB-volume/2vCPU-4GB caps) and ~$2/mo minimum always-on (shared-cpu-1x 256MB = $1.94-$2.53/mo). Guide covers change-tracker, signup/deploy (flyctl, fly launch, fly deploy), cost floor (autostop, volumes $0.15/GB bill while stopped, snapshots $0.08/GB past 10GB free, no billing alerts), common mistakes, and when to pick Render/Koyeb real free tiers instead. No-hands-on honest E-E-A-T. Fact-checked vs fly.io/docs/about/free-trial + pricing + cost-management (Sep 1 2026).TUTORIALβ glm-5.3-flash2026-09-019.07/10
Date: 2026-09-01
Winner: glm-5.3-flash
Results:
π₯glm-5.3-flashzaibuilder9.07/10
π₯mimo-v2.5xiaomibuilder7.93/10
π₯deepseek-v4-flashdeepseekbuilder7.38/10
#4poolside/laguna-s-2.1openrouterbuilder6.22/10
Builder Models 25
Models used to generate content in arena matches. These compete for the best output β high quality, large context.
| Provider | Model | Family | Score | Status |
|---|---|---|---|---|
| deepseek | deepseek-v4-flash | deepseek | 8.4 | Stable |
| nexum | gpt-5.5-instant-14k | gpt | 8.5 | Unstable |
| qwen-3.6-plus | qwen | 7.6 | Stable | |
| qwen-3.7-max | qwen | 8.6 | Stable | |
| qwen-3.7-plus | qwen | -- | Stable | |
| xiaomi-mimo-2.5 | xiaomi | 7.8 | Stable | |
| qwen-3.5-plus | qwen | -- | Stable | |
| qwen-3.5-plus-thinking | qwen | -- | Stable | |
| qwen-3.6-plus-thinking | qwen | -- | Stable | |
| qwen-3.7-plus-thinking | qwen | -- | Stable | |
| qwen-3.6-max-preview | qwen | -- | Stable | |
| qwen-3.7-max-thinking | qwen | -- | Stable | |
| qwen-3.6-max-preview-thinking | qwen | -- | Stable | |
| qwen-3.5-omni-plus | qwen | -- | Stable | |
| deepseek-v4 | deepseek | 9 | Down | |
| nexum-router | router | -- | Stable | |
| xiaomi | mimo-v2.5 | xiaomi | 4.62 | Stable |
| mimo-v2.5-pro | xiaomi | -- | Unknown | |
| zai | glm-5.2 | glm | 6.6 | Stable |
| glm-5 | glm | -- | Stable | |
| glm-5-turbo | glm | -- | Stable | |
| glm-5.1 | glm | -- | Stable | |
| glm-5.3-flash | β | -- | Unknown | |
| openrouter | qwen3.7-flash | qwen | -- | Unknown |
| poolside/laguna-s-2.1 | poolside | -- | Stable |
Judge Models 32
Models used to score builder outputs. These evaluate quality β fast, free-tier, lower context.
| Provider | Model | Family | Score | Status |
|---|---|---|---|---|
| cerebras | gemma-4-31b | gemma | 7.3 | Stable |
| gpt-oss-120b | gpt | 8.4 | Stable | |
| groq | llama-3.1-8b-instant | llama | -- | Stable |
| llama-3.3-70b-versatile | llama | 7.9 | Stable | |
| groq/compound-mini | compound | -- | Unknown | |
| groq/compound | compound | -- | Unknown | |
| qwen/qwen3-32b | qwen | -- | Unknown | |
| openai/gpt-oss-20b | gpt | -- | Unknown | |
| meta-llama/llama-4-scout-17b-16e-instruct | llama | -- | Unknown | |
| mistral | mistral-large-latest | mistral | 8.5 | Stable |
| mistral-medium-latest | mistral | 8 | Stable | |
| mistral-small-latest | mistral | -- | Stable | |
| codestral-2508 | codestral | 8.1 | Unknown | |
| devstral-2512 | devstral | -- | Unknown | |
| magistral-medium-2509 | magistral | -- | Unknown | |
| mistral-medium-2604 | mistral | -- | Unknown | |
| ministral-14b-2512 | ministral | -- | Unknown | |
| open-mistral-nemo-2407 | nemo | -- | Unknown | |
| openrouter | cohere/north-mini-code:free | cohere | 6.5 | Stable |
| google/gemma-4-31b-it:free | gemma | -- | Unstable | |
| nvidia/nemotron-3-super-120b-a12b:free | nvidia | -- | Stable | |
| nvidia/nemotron-3-ultra-550b-a55b:free | nvidia | -- | Stable | |
| nvidia/nemotron-3-nano-30b-a3b:free | nvidia | -- | Stable | |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | nvidia | -- | Stable | |
| nvidia/nemotron-nano-12b-v2-vl:free | nvidia | -- | Stable | |
| openai/gpt-oss-20b:free | gpt | -- | Stable | |
| poolside/laguna-xs-2.1:free | poolside | -- | Stable | |
| google/gemma-4-26b-a4b-it:free | gemma | -- | Stable | |
| nvidia/nemotron-3.5-content-safety:free | nvidia | -- | Stable | |
| tencent/hy3:free | tencent | -- | Stable | |
| nemotron-3-ultra-550b | nemotron | 8.2 | Unknown | |
| nousresearch | stepfun/step-3.7-flash:free | stepfun | -- | Stable |
Process Feedback
Automated analysis from arena-process-feedback.py. No matches analyzed yet β data appears after the first match.
No matches have been analyzed. Run arena-process-feedback.py after recording the first match to see feedback here.
Arena data last updated: 2026-09-01