--- title: Which model should I actually use? — The Agentic AI Hub | daily.dev description: The labs, the benchmarks and their catches, and what models cost. Ends with how to choose. canonical: https://daily.dev/agentic-ai-hub/paths/which-model/ og:type: website og:url: https://daily.dev/agentic-ai-hub/paths/which-model/ og:title: Which model should I actually use? — The Agentic AI Hub | daily.dev og:description: The labs, the benchmarks and their catches, and what models cost. Ends with how to choose. og:image: https://daily.dev/assets/og/agentic-ai-hub.png?v=40e6ff69 og:site_name: daily.dev og:locale: en_US twitter:card: summary_large_image twitter:site: @dailydotdev twitter:creator: @dailydotdev twitter:title: Which model should I actually use? — The Agentic AI Hub | daily.dev twitter:description: The labs, the benchmarks and their catches, and what models cost. Ends with how to choose. twitter:image: https://daily.dev/assets/og/agentic-ai-hub.png?v=40e6ff69 --- [Skip to main content ](#main-content) # Which model should I actually use? The labs, the benchmarks and their catches, and what models cost. Ends with how to choose. [Start reading → ](/agentic-ai-hub/the-labs-whos-who/?path=which-model&i=0) [Check yourself first ↓ ](#quiz) 1. [ 1 The Labs: Who's Who Snapshot as of July 19, 2026\. Valuations and funding are dated and sourced. › ](/agentic-ai-hub/the-labs-whos-who/?path=which-model&i=0) 2. [ 2 Frontier Model Comparison A dated snapshot of the current top-tier, closed ("frontier") models, meaning the API-only models from the major labs that set the capability bar. › ](/agentic-ai-hub/frontier-model-comparison/?path=which-model&i=1) 3. [ 3 Open-Weight Models The models you can download, self-host, and fine-tune. As of July 2026\. Two things to know: (1) "open weight" ≠ open source. › ](/agentic-ai-hub/open-weight-models/?path=which-model&i=2) 4. [ 4 Benchmarks & Leaderboards The single most useful mental model here is that benchmarks tell you what a model can do on someone else's task. › ](/agentic-ai-hub/benchmarks-leaderboards/?path=which-model&i=3) 5. [ 5 Pricing & Cost Reference Pricing is a Frontier Model Comparison snapshot. This section is the durable part: how to reason about cost so you're not surprised by a bill. › ](/agentic-ai-hub/pricing-cost-reference/?path=which-model&i=4) 6. [ 6 How to Choose a Model The honest answer is to shortlist from benchmarks and reputation, then run a small eval on your actual task. › ](/agentic-ai-hub/how-to-choose-a-model/?path=which-model&i=5) ## Check yourself. One question per step. Take it cold to find where to start, or after reading to see what stuck. Nobody's grading you. Best so far: Question 1 of 6 1. Step 1 As of mid-2026, who leads the open-weight frontier? A Meta, doubling down on open Llama releases B Chinese labs like DeepSeek, Qwen, Kimi, and Zhipu C OpenAI and Anthropic, via open flagship releases D European labs, led by Mistral The open-weight leaders are now DeepSeek, Alibaba's Qwen, Moonshot's Kimi, and Zhipu's GLM, while Meta has pivoted toward closed frontier models. [Covered in step 1 · The Labs: Who's Who → ](/agentic-ai-hub/the-labs-whos-who/?path=which-model&i=0) Next question → 2. Step 2 How should you actually use a frontier model comparison table? A As a live price sheet, since frontier API prices are stable B As proof one lab wins across every task C For the at-a-glance shape of the field, then verify on live trackers D As a guide to open-weight models too Prices and versions move weekly, so any table is a dated snapshot. It shows the shape of the field; current specs, speed, and prices come from live sources like Artificial Analysis and OpenRouter. [Covered in step 2 · Frontier Model Comparison → ](/agentic-ai-hub/frontier-model-comparison/?path=which-model&i=1) Next question → 3. Step 3 You've picked an open-weight model to build a product on. What should you check first? A Whether it tops the Open LLM Leaderboard B Its total parameter count C Whether it runs in Ollama D Its license, because open weight doesn't mean open source Some open-weight models ship under permissive Apache-2.0 or MIT licenses, but others carry custom use restrictions, so the license column matters before you build on one. [Covered in step 3 · Open-Weight Models → ](/agentic-ai-hub/open-weight-models/?path=which-model&i=2) Next question → 4. Step 4 A model tops SWE-bench and LMArena. What do those scores tell you? A It will be the best model for your workload too B What it can do on someone else's task, not necessarily yours C Its scores are guaranteed free of contamination D Its agentic scores transfer across any harness Benchmarks tell you what a model can do on someone else's task; only an eval on your own workload tells you what it does on yours. Use leaderboards to shortlist, then test. [Covered in step 4 · Benchmarks & Leaderboards → ](/agentic-ai-hub/benchmarks-leaderboards/?path=which-model&i=3) Next question → 5. Step 5 Two models list similar per-token prices. Why can real costs still differ sharply? A Providers silently change prices per request B Input tokens always cost more than output C Batch APIs add hidden surcharges D Token counts per task vary, because tokenizers and hidden reasoning tokens differ Different tokenizers can emit \~30% more tokens for the same text, and hybrid models bill hidden thinking tokens as output, so compare cost per task, not the headline per-token price. [Covered in step 5 · Pricing & Cost Reference → ](/agentic-ai-hub/pricing-cost-reference/?path=which-model&i=4) Next question → 6. Step 6 Starting a new AI feature, which model choice does the handbook recommend by default? A A flagship, stepping down only when cost or latency forces it B The cheapest tier, upgrading if quality disappoints C A fine-tuned small open model from day one D One model committed to for the year Defaulting to a flagship is cheaper than debugging quality problems from an under-powered model, and behind a gateway you can step down a tier with a config change later. [Covered in step 6 · How to Choose a Model → ](/agentic-ai-hub/how-to-choose-a-model/?path=which-model&i=5) See results → of 6 * [ 1 The Labs: Who's Who → ](/agentic-ai-hub/the-labs-whos-who/?path=which-model&i=0) * [ 2 Frontier Model Comparison → ](/agentic-ai-hub/frontier-model-comparison/?path=which-model&i=1) * [ 3 Open-Weight Models → ](/agentic-ai-hub/open-weight-models/?path=which-model&i=2) * [ 4 Benchmarks & Leaderboards → ](/agentic-ai-hub/benchmarks-leaderboards/?path=which-model&i=3) * [ 5 Pricing & Cost Reference → ](/agentic-ai-hub/pricing-cost-reference/?path=which-model&i=4) * [ 6 How to Choose a Model → ](/agentic-ai-hub/how-to-choose-a-model/?path=which-model&i=5) Try again [Where to next → ](#path-next-title) ## Where to next. More guided paths through the handbook. Pick the next question worth answering. [ I'm new to all this. Where do I start? → ](/agentic-ai-hub/paths/where-do-i-start/)[ How do I build my own agent? → ](/agentic-ai-hub/paths/build-your-own-agent/)[ Can I trust what agents produce? → ](/agentic-ai-hub/paths/trust-agent-output/) [All reading paths → ](/agentic-ai-hub/#paths-start-here) [Browse every chapter ](/agentic-ai-hub/#pages) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/og-image.png?v=a830cdf1","width":1200,"height":630},"sameAs":["https://twitter.com/dailydotdev","https://www.linkedin.com/company/dailydotdev","https://github.com/dailydotdev","https://www.instagram.com/dailydotdev"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","description":"Free, personalized developer news aggregator. Stay on top of software development news, AI coding tools, and web dev - curated daily from trusted sources.","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}},{"@type":"WebPage","@id":"https://daily.dev/agentic-ai-hub/paths/which-model/","url":"https://daily.dev/agentic-ai-hub/paths/which-model/","name":"Which model should I actually use? | The Agentic AI Hub","description":"The labs, the benchmarks and their catches, and what models cost. Ends with how to choose.","inLanguage":"en-US","isPartOf":{"@id":"https://daily.dev/#website"}},{"@type":"ItemList","numberOfItems":6,"itemListElement":[{"@type":"ListItem","position":1,"url":"https://daily.dev/agentic-ai-hub/the-labs-whos-who/","name":"The Labs: Who's Who"},{"@type":"ListItem","position":2,"url":"https://daily.dev/agentic-ai-hub/frontier-model-comparison/","name":"Frontier Model Comparison"},{"@type":"ListItem","position":3,"url":"https://daily.dev/agentic-ai-hub/open-weight-models/","name":"Open-Weight Models"},{"@type":"ListItem","position":4,"url":"https://daily.dev/agentic-ai-hub/benchmarks-leaderboards/","name":"Benchmarks & Leaderboards"},{"@type":"ListItem","position":5,"url":"https://daily.dev/agentic-ai-hub/pricing-cost-reference/","name":"Pricing & Cost Reference"},{"@type":"ListItem","position":6,"url":"https://daily.dev/agentic-ai-hub/how-to-choose-a-model/","name":"How to Choose a Model"}],"@id":"https://daily.dev/agentic-ai-hub/paths/which-model/#steps"},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev/"},{"@type":"ListItem","position":2,"name":"The Agentic AI Hub","item":"https://daily.dev/agentic-ai-hub/"},{"@type":"ListItem","position":3,"name":"New to AI?","item":"https://daily.dev/agentic-ai-hub/#paths-start-here"},{"@type":"ListItem","position":4,"name":"Which model should I actually use?","item":"https://daily.dev/agentic-ai-hub/paths/which-model/"}]}]} ```