Overview Benchmaxxing Benchmarks Compare Charts

More ▾

Cost vs Capability Providers per Model Provider explorer Gateways EU & Sovereign Jev-class models Image JevBench AudioJevBench Submit a model About

Benchmaxxing Benchmarks

Overview Benchmaxxing Compare Charts Cost vs Capability Providers per Model Provider explorer Gateways EU & Sovereign Jev-class models Image JevBench AudioJevBench Submit a model About

Ranking

ScoreMin score

Price basis

Fixed I/O blendTask workload

Models, providers and labs

Regional

Hosted in

Provider company based in

Model lab based in

Hosting = where inference runs; company = where the provider or lab is registered.

EU hosting means the route's inference runs inside the EU: an EU region, AWS Bedrock's EU cross-region (geo) profiles, Azure's Europe Data Zone, or a provider whose entire public fleet is documented as EU-hosted, each checked per model against the provider's documentation. Global deployments do not count, and neither does an EU billing region, an EU company or an EU control plane on its own. One disclosed company-policy exception stays in, marked “EU equivalent”.

Data confidentialitywhat the provider may do with your prompts

More settings

Evidence requirements (benchmark evidence, priced provider, measured task tokens) sit above the table they apply to.

“Hide deprecated” removes retired models (every Artificial Analysis configuration retired, on no current DesignArena board) and older retired configurations of current models. Applies to model tables, charts, price views & model offers; benchmark evidence stays unfiltered.

Charts

Leaderboard, cheapest models, open vs closed, and score against cost — all under your current filters.

Loading charts…

Benchmark Heaven

Sources & methodology Decision model benchmarks JevBench methodology Need custom eval on your data?Public API GitHub MIT licence Privacy Terms Impressum

Benchmark results with their source and date, and a modeled cost per task that accounts for provider prices, caching and token efficiency. Data from OpenRouter, Artificial Analysis, Epoch AI, DesignArena, benchmark maintainers and provider catalogs. Data: Artificial Analysis · Data: Epoch AI (CC BY)

Open source (MIT) and a hobby project — the code is on GitHub, built to give the world better tools to decide which LLM to choose for the job. The licence covers the code, not the third-party data (its own terms apply).

Benchmark publishers can ask for their numbers to be removed or shown differently — data sources & removal on request.

Support Benchmark Heaven · Payments go to productivity-boost.com Betriebs UG (haftungsbeschränkt) & Co. KG, the one-person company behind this project.