The best AI models, by task
One general-purpose leaderboard hides the decisions that matter. These pages rank models per task, from measured benchmark evidence and live pricing, using the same quality projection that routes Inferbase production traffic. Where evidence does not exist, the pages say so.
Ranked by measured coding benchmarks, not editorial opinion, with current pricing and context windows alongside every entry.
View the rankingRanked by knowledge and graduate-level reasoning benchmarks (MMLU-Pro, GPQA, HLE), with pricing and context windows for every entry.
View the rankingThe general-purpose ranking: ordered by composite intelligence evidence, with the price and context data needed to judge the tradeoff.
View the rankingOnly models with affirmatively verified tool support, ranked by measured quality, because a silently mangled tool call is worse than a refusal.
View the rankingModels with verified structured-output support, ranked by measured quality, for pipelines where a malformed response is a production incident.
View the rankingModels that accept image input, ranked by general quality evidence, since no independent vision benchmark suite is ingested yet, and this page says so.
View the rankingRanked by advertised context window, an objective spec, with the quality and price data needed to judge whether the headline number is worth it.
View the rankingEmbedding models compared on price and specs. No quality benchmark suite for embeddings is ingested yet, and this page makes no quality claim.
View the rankingHow these rankings are made
Generated from the Inferbase catalog, with the same quality projection the router consults for live requests.
Independent benchmark suites are ingested, rank-normalized, and projected into per-task quality scores. Rankings combine that quality signal with objective specifications and current pricing, and they regenerate automatically as the data changes.
Two commitments hold across all of these pages. First, no ranking is published for a task without measured evidence, which is why some popular tasks do not have a page yet. Second, missing data is shown as missing: a model without benchmark results for a task is omitted from that ranking rather than scored by guesswork.
Frequently asked questions
Where the data comes from and how to use it.
From the same data plane that powers Inferbase routing: independent benchmark suites are ingested, rank-normalized, and projected into per-task quality scores, combined with catalog specifications and live pricing. Each page states its exact methodology and how many models qualified for its ranking.
The ordering is computed from measured evidence by the engine that routes production traffic, refreshed automatically as benchmarks and prices change. Where evidence does not exist, the pages say so explicitly instead of substituting opinion.
Because no independent benchmark evidence for them is ingested yet. Pages exist only for tasks where the ranking can be defended with data; new task pages are added as evidence coverage grows.
Pages regenerate at least hourly from live catalog data. Benchmark results, prices, and model availability update on the catalog sync cycle, and a new model appears in rankings as soon as covered evidence for it lands.
Models marked as served on Inferbase are available immediately through one OpenAI-compatible API, individually pinned or behind smart routing that picks per request from the same quality data these pages display.
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.