| Model | Provider | Age (days) | Params (Total / Active) | Context | Capabilities | ⭐ Rating | AA Index | 💻 Code Idx | 🤖 Agent Idx | Speed (t/s) | Input $/1M | Pulls | Tier |
|---|
📚 Data Sources & References
Ollama Model Registry
Model descriptions, capabilities, parameter counts, context windows, pull counts, and benchmark tables sourced directly from each model's page.
ollama.com/search?c=cloud →Artificial Analysis
AA Intelligence Index is a composite score (0-100+) that combines multiple benchmark results into a single metric of model capability. Coding Index and Agentic Index are sub-indices focused on coding and agentic benchmarks. Also sourced: input/output pricing and tokens-per-second speed for 1st-party APIs.
artificialanalysis.ai →Provider 1st-Party APIs
Per-token pricing and speed (t/s) come from each provider's public API documentation. These are not Ollama Cloud prices.
Ollama Cloud Pricing
Ollama Cloud uses subscription tiers with GPU-time metering (not per-token). Free: light usage. Pro: $20/mo, 50x usage, 3 concurrent models. Max: $100/mo, 250x usage, 10 concurrent.
ollama.com/pricing →Star Ratings
Subjective 1-5 star ratings curated by the site authors based on benchmark performance, community sentiment, value proposition, and real-world agent performance.
Benchmark Sources
Benchmark values come from model READMEs on Ollama and provider-published results. Benchmarks include: MMLU-Pro, GPQA Diamond, LiveCodeBench, SWE-Bench, HLE, AIME, Terminal-Bench, Codeforces ELO, BrowseComp.
📝 Citation note: Data is refreshed weekly via automated scraping. Last full scrape: 2026-05-08. Site built by vlat + Moxie ⚡ using Hermes Agent.