Models.dev: Tracks open-source model specifications and pricing in a detailed database, but lacks interactive side-by-side benchmarking leaderboards. Design Arena records 949,534 monthly visits with -13.2% month-over-month growth and Free pricing. Models.dev records 200,451 monthly visits with -3.9% growth and Free pricing.
Crowdsourced arena where AI models compete and humans crown the best design output
Open-source database of AI models, prices and capabilities
| Dimension / Metric | | |
|---|---|---|
| Official Domain | designarena.ai | models.dev |
| Pricing Model | Free | Free |
| Monthly Visits | 949.53K (949,534) | 200.45K (200,451) |
| MoM Traffic Delta | -143.97K (-13.2%) | -8.17K (-3.9%) |
| Primary Market & Share | 🇮🇳 India (24.2%) | 🇨🇳 China (23%) |
| Direct Visits / mo | 564.6K | 136.32K |
| User Rating | 4.4 | 4.4 |
| Supported Platforms | Website | Website |
Crowdsourced arena where AI models compete and humans crown the best design output
Enter a prompt and see how multiple leading models respond, then cast a vote for the best output — the core mechanism that keeps the benchmark crowdsourced and independent.
Public rankings cover website and frontend builds, images and image editing, video and image-to-video, 3D, SVG, slides, spreadsheets, PDFs, code art, and text-to-speech.
Results are aggregated with Elo/Bradley-Terry-style rating systems, so rankings reflect collective human taste rather than lab-reported scores.
Dedicated leaderboards for agentic coding, Godot game dev, React Native, Android (Kotlin), and full-stack builders help developers pick the right model for real work.
Open-source database of AI models, prices and capabilities
Every model uses a consistent provider/model format so the same model across providers can be compared directly.
Side-by-side context window, output limit, reasoning, tool calling, structured output, and temperature support.
Input and output prices per million tokens listed alongside release and update dates.
Covers closed flagship APIs and open-weight models from many labs in one sortable catalogue.
SpecialistProvides side-by-side benchmarking and community leaderboards, but specifically evaluates programming and code generation models.
SpecialistProvides side-by-side benchmarking and community leaderboards, but specifically evaluates programming and code generation models.
SpecialistIncludes model pricing trackers and developer news alongside tools directories, but less focused on raw API specs.
SpecialistIncludes model pricing trackers and developer news alongside tools directories, but less focused on raw API specs.
SpecialistA library of Midjourney styles, SREF codes, prompts and guides
SpecialistA library of Midjourney styles, SREF codes, prompts and guides
SpecialistOffers public model benchmarking and performance leaderboards, but concentrates on computer-use and mobile agents rather than design.
SpecialistOffers public model benchmarking and performance leaderboards, but concentrates on computer-use and mobile agents rather than design.
SpecialistCatalogues and compares AI infrastructure tools and services across categories, but lacks deep per-token pricing tables.
SpecialistCatalogues and compares AI infrastructure tools and services across categories, but lacks deep per-token pricing tables.
SpecialistArchives how various AI models answer identical prompts over time, offering qualitative comparison rather than pricing.
SpecialistArchives how various AI models answer identical prompts over time, offering qualitative comparison rather than pricing.
Tracks per-token API prices across major AI providers in a simple comparison table, but omits broader model specs.
Tracks per-token API prices across major AI providers in a simple comparison table, but omits broader model specs.
SpecialistTest how AI models cooperate, negotiate, and deceive in strategy games
SpecialistTest how AI models cooperate, negotiate, and deceive in strategy games
SpecialistHelps compare foundation model performance and AI stacks, but functions more as a decision workspace than raw database.
SpecialistHelps compare foundation model performance and AI stacks, but functions more as a decision workspace than raw database.
Builds community leaderboards through direct model polling, but covers general foundation models rather than design outputs.
Builds community leaderboards through direct model polling, but covers general foundation models rather than design outputs.
Free / Open-sourceA free, open-source comparison directory for evaluating AI model pricing and capabilities very similar to Models.dev.
Free / Open-sourceA free, open-source comparison directory for evaluating AI model pricing and capabilities very similar to Models.dev.
Aggregates LLM benchmarks, pricing, and capabilities into an intelligence platform, but lacks open-source database access.
Aggregates LLM benchmarks, pricing, and capabilities into an intelligence platform, but lacks open-source database access.
