{"ok":true,"data":{"publisher":"LLM Tier","source":"https://www.llm-tier.com","licence":"CC-BY-4.0","licence_url":"https://creativecommons.org/licenses/by/4.0/","attribution":"Data by LLM Tier, https://www.llm-tier.com, licensed CC-BY-4.0","generated_at":"2026-09-12T10:42:58.953Z","measured_at":"2026-08-15T09:11:37.500Z","full_stack_app_builders_index_definition":"Composite index from 0 to 100, two decimals, computed as the weighted sum of ten subscores each from 0 to 100. You give this class a written specification and it returns a hosted, running application. Figures reflect the measurement cycle at measured_at, not the serialisation time at generated_at.","coding_agents_index_definition":"Composite index from 0 to 100, two decimals, computed as the weighted sum of nine subscores each from 0 to 100. Code ownership is not scored: a coding agent edits a repository you already own, so that property was never the vendor's to grant. The remaining nine weights are rescaled by 100/97 so they still sum to 100. You point this class at an existing repository, terminal or IDE and it changes the code; the output is a diff, not a deployment. An index score here is not comparable to a full_stack_app_builders index score.","models_index_definition":"There is no models index. This lab runs no language-model harness and holds no model-level run records, so it does not publish a composite for models. Every field under models_roster and models_legacy is either a vendor-published fact, an attributed third party benchmark result (Arena WebDev, Artificial Analysis, Terminal-Bench v2.1), or explicitly null where no source states one. Full disclosure is on /leaderboard/llms and the LLM section of /methodology.","turn_latency_definition":"Median wall clock seconds for one prompt, not for a whole build. The test specification is nine prompts, run five times per product, so a single row here is the middle value of 45 recorded prompt executions.","turn_latency_derived_minutes_caveat":"Derived, not separately measured. It is nine times the median prompt latency, converted to minutes. It is not a measured end-to-end wall clock for one continuous session, and it excludes any operator time between prompts. This derivation understates the real end-to-end wall clock.","fx":{"rate_usd_per_eur":1.1699,"rate_date":"2026-08-21","source":"European Central Bank euro foreign exchange reference rates","note":"Used only to compute pricing.price_eur_normalised on each row, for the Value axis. Every pricing.price_display figure above is the vendor's own currency, unrelated to this rate."},"boards_not_comparable_note":"full_stack_app_builders and coding_agents are two separate measurements with separate weight tables. An index_score, subscore or rank from one is never comparable to the other, even where the axis key is the same name. Neither is comparable to anything under models_roster or models_legacy, which carry no index_score or rank at all.","full_stack_app_builders_weights":[{"key":"agent_perf","label":"Agent performance","weight_percent":18},{"key":"reliability","label":"Reliability","weight_percent":18},{"key":"scalability","label":"Scalability","weight_percent":13},{"key":"seo_geo","label":"SEO and GEO","weight_percent":12},{"key":"api_mcp","label":"API and MCP","weight_percent":9},{"key":"integrations","label":"Integrations","weight_percent":8},{"key":"design","label":"Design output","weight_percent":7},{"key":"speed","label":"Turn latency","weight_percent":7},{"key":"value","label":"Value","weight_percent":5},{"key":"code_ownership","label":"Code ownership","weight_percent":3}],"coding_agents_weights":[{"key":"agent_perf","label":"Agent performance","weight_percent":18.55},{"key":"reliability","label":"Reliability","weight_percent":18.56},{"key":"scalability","label":"Scalability","weight_percent":13.4},{"key":"seo_geo","label":"SEO and GEO","weight_percent":12.37},{"key":"api_mcp","label":"API and MCP","weight_percent":9.28},{"key":"integrations","label":"Integrations","weight_percent":8.25},{"key":"design","label":"Design output","weight_percent":7.22},{"key":"speed","label":"Turn latency","weight_percent":7.22},{"key":"value","label":"Value","weight_percent":5.15}],"counts":{"full_stack_app_builders":20,"coding_agents":17,"models_roster":26,"models_legacy":12,"published_products":37},"full_stack_app_builders":[{"rank":1,"rank_delta":4,"slug":"totalum","name":"Totalum","board":"fullstack-builder","official_url":"https://www.totalum.app","page_url":"https://www.llm-tier.com/builders/totalum","index_score":89.48,"index_score_recomputed":89.49,"subscores":{"agent_perf":94,"reliability":93.3,"scalability":92,"seo_geo":95,"api_mcp":97,"integrations":88,"design":86,"speed":61.3,"value":69,"code_ownership":96},"turn_latency_seconds":{"p10":59.2,"median":106.3,"p90":167.6,"full_spec_minutes_derived":15.9},"runs":{"completed":44,"failed":1,"reliability_pct":93.3},"shipped_output":{"html_bytes_no_js":41984,"lcp_ms":1480,"cls":0.02},"pricing":{"summary":"Free tier for testing, then from EUR 29 per month on the Starter plan. Pricing is per account, not per project: the vendor FAQ states projects are unlimited, and plans scale with monthly credits and database size. Database, storage and hosting are included.","price_display":"EUR 29 / month","price_amount":29,"price_currency":"EUR","price_unit":"account","price_source_url":"https://www.totalum.app/en","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":29},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":2,"rank_delta":-1,"slug":"firebase-studio","name":"Firebase Studio","board":"fullstack-builder","official_url":"https://firebase.studio","page_url":"https://www.llm-tier.com/builders/firebase-studio","index_score":80.92,"index_score_recomputed":80.92,"subscores":{"agent_perf":79,"reliability":86.7,"scalability":87,"seo_geo":73,"api_mcp":79,"integrations":90,"design":72,"speed":65,"value":92,"code_ownership":84},"turn_latency_seconds":{"p10":65.8,"median":100.3,"p90":161.3,"full_spec_minutes_derived":15},"runs":{"completed":44,"failed":1,"reliability_pct":86.7},"shipped_output":{"html_bytes_no_js":22528,"lcp_ms":1980,"cls":0.05},"pricing":{"summary":"No seat price during preview. The generated project bills through the underlying cloud plan, so the running cost depends on usage rather than a licence.","price_display":"No cost","price_amount":0,"price_currency":"USD","price_unit":"account","price_source_url":"https://firebase.google.com/docs/studio/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":0},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":3,"rank_delta":-1,"slug":"lovable","name":"Lovable","board":"fullstack-builder","official_url":"https://lovable.dev","page_url":"https://www.llm-tier.com/builders/lovable","index_score":80.54,"index_score_recomputed":80.54,"subscores":{"agent_perf":89,"reliability":82.2,"scalability":78,"seo_geo":75,"api_mcp":66,"integrations":86,"design":92,"speed":76.5,"value":72,"code_ownership":79},"turn_latency_seconds":{"p10":52.6,"median":85.2,"p90":133.1,"full_spec_minutes_derived":12.8},"runs":{"completed":43,"failed":2,"reliability_pct":82.2},"shipped_output":{"html_bytes_no_js":18432,"lcp_ms":2140,"cls":0.06},"pricing":{"summary":"Free tier with a small daily credit allowance. Paid plans from USD 25 per month, metered per agent message.","price_display":"USD 25 / month, billed monthly","price_amount":25,"price_currency":"USD","price_unit":"account","price_source_url":"https://lovable.dev/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":21.37},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":4,"rank_delta":1,"slug":"v0","name":"v0","board":"fullstack-builder","official_url":"https://v0.app","page_url":"https://www.llm-tier.com/builders/v0","index_score":78.31,"index_score_recomputed":78.31,"subscores":{"agent_perf":80,"reliability":84.4,"scalability":72,"seo_geo":76,"api_mcp":60,"integrations":66,"design":94,"speed":100,"value":68,"code_ownership":86},"turn_latency_seconds":{"p10":44.9,"median":65.2,"p90":104.1,"full_spec_minutes_derived":9.8},"runs":{"completed":44,"failed":1,"reliability_pct":84.4},"shipped_output":{"html_bytes_no_js":27648,"lcp_ms":1620,"cls":0.04},"pricing":{"summary":"Free tier with monthly credits. Plus from USD 30 per user per month with usage based credits above the allowance.","price_display":"USD 30 / user / month","price_amount":30,"price_currency":"USD","price_unit":"user","price_source_url":"https://v0.app/pricing","price_fetched_at":"2026-09-06","price_note":null,"price_eur_normalised":25.64},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":5,"rank_delta":1,"slug":"replit","name":"Replit","board":"fullstack-builder","official_url":"https://replit.com","page_url":"https://www.llm-tier.com/builders/replit","index_score":75.47,"index_score_recomputed":75.47,"subscores":{"agent_perf":83,"reliability":86.7,"scalability":80,"seo_geo":62,"api_mcp":71,"integrations":77,"design":73,"speed":48,"value":72,"code_ownership":82},"turn_latency_seconds":{"p10":92.8,"median":135.7,"p90":188.8,"full_spec_minutes_derived":20.4},"runs":{"completed":43,"failed":2,"reliability_pct":86.7},"shipped_output":{"html_bytes_no_js":9216,"lcp_ms":2880,"cls":0.12},"pricing":{"summary":"Free tier for prototypes. Core from USD 20 per month including agent time, deployments and always on services.","price_display":"USD 20 / month, billed monthly","price_amount":20,"price_currency":"USD","price_unit":"account","price_source_url":"https://replit.com/pricing","price_fetched_at":"2026-09-08","price_note":null,"price_eur_normalised":17.1},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":6,"rank_delta":1,"slug":"bolt-new","name":"Bolt.new","board":"fullstack-builder","official_url":"https://bolt.new","page_url":"https://www.llm-tier.com/builders/bolt-new","index_score":74.68,"index_score_recomputed":74.68,"subscores":{"agent_perf":81,"reliability":80,"scalability":70,"seo_geo":66,"api_mcp":58,"integrations":72,"design":85,"speed":79.4,"value":71,"code_ownership":88},"turn_latency_seconds":{"p10":51.8,"median":82.1,"p90":136,"full_spec_minutes_derived":12.3},"runs":{"completed":44,"failed":1,"reliability_pct":80},"shipped_output":{"html_bytes_no_js":12288,"lcp_ms":2460,"cls":0.09},"pricing":{"summary":"Free daily token allowance. Pro from USD 25 per month with token top ups sold separately.","price_display":"USD 25 / month, billed monthly","price_amount":25,"price_currency":"USD","price_unit":"account","price_source_url":"https://bolt.new/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":21.37},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":7,"rank_delta":1,"slug":"base44","name":"Base44","board":"fullstack-builder","official_url":"https://base44.com","page_url":"https://www.llm-tier.com/builders/base44","index_score":73.05,"index_score_recomputed":73.05,"subscores":{"agent_perf":75,"reliability":84.4,"scalability":68,"seo_geo":64,"api_mcp":66,"integrations":75,"design":80,"speed":69.3,"value":76,"code_ownership":55},"turn_latency_seconds":{"p10":58.8,"median":94.1,"p90":161.4,"full_spec_minutes_derived":14.1},"runs":{"completed":45,"failed":0,"reliability_pct":84.4},"shipped_output":{"html_bytes_no_js":14336,"lcp_ms":2320,"cls":0.08},"pricing":{"summary":"Free tier with a monthly message allowance. Paid plans from USD 16 per month, billed annually.","price_display":"USD 16 / month, billed annually","price_amount":16,"price_currency":"USD","price_unit":"account","price_source_url":"https://base44.com/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":13.68},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":8,"rank_delta":2,"slug":"anything","name":"Anything","board":"fullstack-builder","official_url":"https://create.xyz","page_url":"https://www.llm-tier.com/builders/anything","index_score":69.97,"index_score_recomputed":69.98,"subscores":{"agent_perf":71,"reliability":77.8,"scalability":62,"seo_geo":68,"api_mcp":57,"integrations":66,"design":83,"speed":69.3,"value":76,"code_ownership":70},"turn_latency_seconds":{"p10":55.2,"median":94.1,"p90":146.8,"full_spec_minutes_derived":14.1},"runs":{"completed":43,"failed":2,"reliability_pct":77.8},"shipped_output":{"html_bytes_no_js":18432,"lcp_ms":1960,"cls":0.05},"pricing":{"summary":"Free tier with monthly credits. Paid plans from USD 19 per month with usage based credits above the allowance.","price_display":"USD 19 / month","price_amount":19,"price_currency":"USD","price_unit":"account","price_source_url":"https://create.xyz/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":16.24},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":9,"rank_delta":2,"slug":"softgen","name":"Softgen","board":"fullstack-builder","official_url":"https://softgen.ai","page_url":"https://www.llm-tier.com/builders/softgen","index_score":69.48,"index_score_recomputed":69.48,"subscores":{"agent_perf":74,"reliability":73.3,"scalability":68,"seo_geo":66,"api_mcp":58,"integrations":70,"design":78,"speed":60.1,"value":70,"code_ownership":74},"turn_latency_seconds":{"p10":65.1,"median":108.4,"p90":176.3,"full_spec_minutes_derived":16.3},"runs":{"completed":40,"failed":5,"reliability_pct":73.3},"shipped_output":{"html_bytes_no_js":17408,"lcp_ms":2180,"cls":0.06},"pricing":{"summary":"Free trial credits, then from USD 25 per month with a monthly message allowance.","price_display":"USD 25 / month","price_amount":25,"price_currency":"USD","price_unit":"account","price_source_url":"https://softgen.ai/","price_fetched_at":"2026-08-21","price_note":"Softgen publishes its plan prices with a bare dollar sign and no currency word anywhere on the page. USD is inferred by this lab rather than stated by the vendor, and the converted euro figure rests on that inference.","price_eur_normalised":21.37},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":10,"rank_delta":2,"slug":"emergent","name":"Emergent","board":"fullstack-builder","official_url":"https://emergent.sh","page_url":"https://www.llm-tier.com/builders/emergent","index_score":68.68,"index_score_recomputed":68.68,"subscores":{"agent_perf":79,"reliability":80,"scalability":66,"seo_geo":58,"api_mcp":61,"integrations":63,"design":71,"speed":45.1,"value":74,"code_ownership":72},"turn_latency_seconds":{"p10":81.7,"median":144.6,"p90":309.3,"full_spec_minutes_derived":21.7},"runs":{"completed":39,"failed":6,"reliability_pct":80},"shipped_output":{"html_bytes_no_js":8192,"lcp_ms":3120,"cls":0.14},"pricing":{"summary":"Credit based. Entry bundle from USD 20 per month. No free tier completed the full specification.","price_display":"USD 20 / month, billed monthly","price_amount":20,"price_currency":"USD","price_unit":"account","price_source_url":"https://emergent.sh/","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":17.1},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":11,"rank_delta":2,"slug":"floot","name":"Floot","board":"fullstack-builder","official_url":"https://floot.com","page_url":"https://www.llm-tier.com/builders/floot","index_score":68.66,"index_score_recomputed":68.66,"subscores":{"agent_perf":72,"reliability":68.9,"scalability":66,"seo_geo":70,"api_mcp":55,"integrations":64,"design":84,"speed":71.6,"value":70,"code_ownership":62},"turn_latency_seconds":{"p10":46.1,"median":91.1,"p90":174.2,"full_spec_minutes_derived":13.7},"runs":{"completed":39,"failed":6,"reliability_pct":68.9},"shipped_output":{"html_bytes_no_js":19456,"lcp_ms":2020,"cls":0.05},"pricing":{"summary":"Free tier with a daily allowance. Paid plans from USD 25 per month.","price_display":"USD 25 / month","price_amount":25,"price_currency":"USD","price_unit":"account","price_source_url":"https://floot.com/en/pricing","price_fetched_at":"2026-08-21","price_note":"Floot's plan table prints bare dollar signs and never names a currency. USD is this lab's inference from the symbol, not something the vendor publishes, and the normalised euro price inherits that inference.","price_eur_normalised":21.37},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":12,"rank_delta":2,"slug":"dyad","name":"Dyad","board":"fullstack-builder","official_url":"https://dyad.sh","page_url":"https://www.llm-tier.com/builders/dyad","index_score":67.49,"index_score_recomputed":67.49,"subscores":{"agent_perf":68,"reliability":55.6,"scalability":64,"seo_geo":72,"api_mcp":60,"integrations":62,"design":72,"speed":77.8,"value":90,"code_ownership":98},"turn_latency_seconds":{"p10":54.4,"median":83.8,"p90":149.9,"full_spec_minutes_derived":12.6},"runs":{"completed":35,"failed":10,"reliability_pct":55.6},"shipped_output":{"html_bytes_no_js":20480,"lcp_ms":1880,"cls":0.04},"pricing":{"summary":"Free and open source with your own model key, so the only cost is the tokens you spend. A hosted Pro tier is also available from USD 20 per month for a managed model key and extra features.","price_display":"No licence fee, bring your own model key","price_amount":0,"price_currency":"USD","price_unit":"account","price_source_url":"https://dyad.sh/","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":0},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":13,"rank_delta":2,"slug":"bind-ai","name":"Bind AI","board":"fullstack-builder","official_url":"https://getbind.co","page_url":"https://www.llm-tier.com/builders/bind-ai","index_score":65.59,"index_score_recomputed":65.6,"subscores":{"agent_perf":69,"reliability":64.4,"scalability":60,"seo_geo":58,"api_mcp":62,"integrations":68,"design":70,"speed":67.9,"value":75,"code_ownership":80},"turn_latency_seconds":{"p10":53.5,"median":96,"p90":186.6,"full_spec_minutes_derived":14.4},"runs":{"completed":36,"failed":9,"reliability_pct":64.4},"shipped_output":{"html_bytes_no_js":13312,"lcp_ms":2240,"cls":0.07},"pricing":{"summary":"Free tier with limited model access. Paid plans from USD 18 per month with a choice of underlying models.","price_display":"USD 18 / month","price_amount":18,"price_currency":"USD","price_unit":"account","price_source_url":"https://getbind.co/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":15.39},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":14,"rank_delta":2,"slug":"rocket-new","name":"Rocket.new","board":"fullstack-builder","official_url":"https://rocket.new","page_url":"https://www.llm-tier.com/builders/rocket-new","index_score":62.12,"index_score_recomputed":62.12,"subscores":{"agent_perf":70,"reliability":60,"scalability":61,"seo_geo":57,"api_mcp":52,"integrations":59,"design":75,"speed":60.8,"value":66,"code_ownership":58},"turn_latency_seconds":{"p10":53.3,"median":107.2,"p90":217,"full_spec_minutes_derived":16.1},"runs":{"completed":34,"failed":11,"reliability_pct":60},"shipped_output":{"html_bytes_no_js":7168,"lcp_ms":3260,"cls":0.16},"pricing":{"summary":"Credit based with a small free allowance. Paid plans from USD 25 per month.","price_display":"USD 25 / month","price_amount":25,"price_currency":"USD","price_unit":"account","price_source_url":"https://rocket.new/pricing","price_fetched_at":"2026-08-21","price_note":"Rocket describes each tier as a monthly platform fee quoted with a bare dollar sign, and states no currency anywhere on its pricing page. USD is this lab's reading, not a vendor statement, and the euro figure follows from it.","price_eur_normalised":21.37},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":15,"rank_delta":2,"slug":"caffeine","name":"Caffeine","board":"fullstack-builder","official_url":"https://caffeine.ai","page_url":"https://www.llm-tier.com/builders/caffeine","index_score":62.08,"index_score_recomputed":62.08,"subscores":{"agent_perf":70,"reliability":66.7,"scalability":74,"seo_geo":48,"api_mcp":52,"integrations":46,"design":68,"speed":43.3,"value":84,"code_ownership":58},"turn_latency_seconds":{"p10":76,"median":150.6,"p90":295.5,"full_spec_minutes_derived":22.6},"runs":{"completed":42,"failed":3,"reliability_pct":66.7},"shipped_output":{"html_bytes_no_js":6144,"lcp_ms":2840,"cls":0.11},"pricing":{"summary":"Four monthly plans: Free at USD 0, Host at USD 5, Studio at USD 25 with a USD 10 first month, and Business at USD 250. Each carries a fixed monthly credit allowance rather than open ended usage billing, at 15 welcome credits on the free plan, then 20, 100 and 1000 a month. The free plan remixes existing app market apps only, so USD 5 is the entry price for building from scratch. Annual billing is offered at a stated 20 percent discount. The plan buys capacity on a decentralised runtime, so there is no separate server to size or maintain alongside it.","price_display":"USD 5 / month","price_amount":5,"price_currency":"USD","price_unit":"account","price_source_url":"https://caffeine.ai/pricing","price_fetched_at":"2026-09-02","price_note":"Every figure on caffeine.ai/pricing is a bare dollar sign, and the page names no currency at all. The USD label here is this lab's reading of that symbol rather than a vendor statement, and the euro figure is converted on the same basis.","price_eur_normalised":4.27},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":16,"rank_delta":2,"slug":"zite","name":"Zite","board":"fullstack-builder","official_url":"https://zite.com","page_url":"https://www.llm-tier.com/builders/zite","index_score":61.06,"index_score_recomputed":61.07,"subscores":{"agent_perf":68,"reliability":60,"scalability":58,"seo_geo":60,"api_mcp":47,"integrations":55,"design":77,"speed":57.5,"value":76,"code_ownership":48},"turn_latency_seconds":{"p10":60.2,"median":113.4,"p90":193.1,"full_spec_minutes_derived":17},"runs":{"completed":35,"failed":10,"reliability_pct":60},"shipped_output":{"html_bytes_no_js":10240,"lcp_ms":2740,"cls":0.11},"pricing":{"summary":"Free tier with limited credits and one workspace. Paid plans from USD 25 per month.","price_display":"USD 25 / month, billed monthly","price_amount":25,"price_currency":"USD","price_unit":"account","price_source_url":"https://zite.com/pricing","price_fetched_at":"2026-09-08","price_note":null,"price_eur_normalised":21.37},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":17,"rank_delta":2,"slug":"bolt-diy","name":"bolt.diy","board":"fullstack-builder","official_url":"https://github.com/stackblitz-labs/bolt.diy","page_url":"https://www.llm-tier.com/builders/bolt-diy","index_score":59.85,"index_score_recomputed":59.85,"subscores":{"agent_perf":60,"reliability":55.6,"scalability":52,"seo_geo":62,"api_mcp":48,"integrations":54,"design":74,"speed":57.3,"value":82,"code_ownership":97},"turn_latency_seconds":{"p10":59.6,"median":113.8,"p90":231.5,"full_spec_minutes_derived":17.1},"runs":{"completed":35,"failed":10,"reliability_pct":55.6},"shipped_output":{"html_bytes_no_js":15360,"lcp_ms":2320,"cls":0.08},"pricing":{"summary":"Free and open source, community maintained. You supply the model key.","price_display":"No licence fee, bring your own model key","price_amount":0,"price_currency":"USD","price_unit":"account","price_source_url":"https://github.com/stackblitz-labs/bolt.diy","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":0},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":18,"rank_delta":3,"slug":"youware","name":"YouWare","board":"fullstack-builder","official_url":"https://youware.com","page_url":"https://www.llm-tier.com/builders/youware","index_score":58.53,"index_score_recomputed":58.53,"subscores":{"agent_perf":63,"reliability":48.9,"scalability":54,"seo_geo":61,"api_mcp":44,"integrations":52,"design":82,"speed":81.5,"value":null,"code_ownership":52},"turn_latency_seconds":{"p10":46.3,"median":80,"p90":143,"full_spec_minutes_derived":12},"runs":{"completed":31,"failed":14,"reliability_pct":48.9},"shipped_output":{"html_bytes_no_js":14336,"lcp_ms":2120,"cls":0.07},"pricing":{"summary":"youware.com/pricing returns HTTP 200 with a rendered 404 body. No entry price and no free tier statement is published by the vendor. Read August 21, 2026.","price_display":"Not published by the vendor","price_amount":null,"price_currency":null,"price_unit":null,"price_source_url":"https://youware.com/pricing","price_fetched_at":"2026-08-21","price_note":"youware.com/pricing returns HTTP 200 with a rendered 404 body. No entry price and no free tier statement is published by the vendor. Read August 21, 2026.","price_eur_normalised":null},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":19,"rank_delta":4,"slug":"trickle","name":"Trickle","board":"fullstack-builder","official_url":"https://trickle.so","page_url":"https://www.llm-tier.com/builders/trickle","index_score":58.11,"index_score_recomputed":58.11,"subscores":{"agent_perf":62,"reliability":51.1,"scalability":52,"seo_geo":63,"api_mcp":41,"integrations":49,"design":79,"speed":74.9,"value":74,"code_ownership":45},"turn_latency_seconds":{"p10":49.4,"median":87,"p90":137.1,"full_spec_minutes_derived":13.1},"runs":{"completed":34,"failed":11,"reliability_pct":51.1},"shipped_output":{"html_bytes_no_js":15360,"lcp_ms":2260,"cls":0.07},"pricing":{"summary":"Free tier for public pages. Paid plans from USD 17 per month.","price_display":"USD 17 / month","price_amount":17,"price_currency":"USD","price_unit":"account","price_source_url":"https://trickle.so/pricing","price_fetched_at":"2026-08-21","price_note":"Trickle's pricing page uses a bare dollar sign throughout and names no currency. The USD label is this lab's reading of the symbol, not a vendor statement, and the euro conversion depends on it.","price_eur_normalised":14.53},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":20,"rank_delta":4,"slug":"catdoes","name":"CatDoes","board":"fullstack-builder","official_url":"https://catdoes.com","page_url":"https://www.llm-tier.com/builders/catdoes","index_score":56.99,"index_score_recomputed":56.99,"subscores":{"agent_perf":66,"reliability":48.9,"scalability":58,"seo_geo":42,"api_mcp":48,"integrations":60,"design":80,"speed":47.6,"value":74,"code_ownership":66},"turn_latency_seconds":{"p10":72.2,"median":137.1,"p90":249,"full_spec_minutes_derived":20.6},"runs":{"completed":32,"failed":13,"reliability_pct":48.9},"shipped_output":{"html_bytes_no_js":8192,"lcp_ms":2460,"cls":0.09},"pricing":{"summary":"Free build credits, then from USD 17 per month. Store submission is a separate cost.","price_display":"USD 17 / month","price_amount":17,"price_currency":"USD","price_unit":"account","price_source_url":"https://catdoes.com/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":14.53},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null}],"coding_agents":[{"rank":1,"rank_delta":-1,"slug":"claude-code","name":"Claude Code","board":"coding-agent","official_url":"https://claude.com","page_url":"https://www.llm-tier.com/builders/claude-code","index_score":79.72,"index_score_recomputed":79.72,"subscores":{"agent_perf":95,"reliability":91.1,"scalability":86,"seo_geo":62,"api_mcp":78,"integrations":76,"design":68,"speed":47.9,"value":80},"turn_latency_seconds":{"p10":39.9,"median":65.5,"p90":100.7,"full_spec_minutes_derived":9.8},"runs":{"completed":44,"failed":1,"reliability_pct":91.1},"shipped_output":{"html_bytes_no_js":26624,"lcp_ms":1680,"cls":0.03},"pricing":{"summary":"Included with a consumer subscription from USD 17 per month, billed annually, or metered per token through the API.","price_display":"USD 17 / month, billed annually","price_amount":17,"price_currency":"USD","price_unit":"account","price_source_url":"https://claude.com/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":14.53},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":2,"rank_delta":-1,"slug":"cursor","name":"Cursor","board":"coding-agent","official_url":"https://cursor.com","page_url":"https://www.llm-tier.com/builders/cursor","index_score":77.92,"index_score_recomputed":77.92,"subscores":{"agent_perf":92,"reliability":86.7,"scalability":82,"seo_geo":58,"api_mcp":74,"integrations":80,"design":66,"speed":58.8,"value":80},"turn_latency_seconds":{"p10":28.7,"median":53.4,"p90":82.7,"full_spec_minutes_derived":8},"runs":{"completed":42,"failed":3,"reliability_pct":86.7},"shipped_output":{"html_bytes_no_js":24576,"lcp_ms":1720,"cls":0.03},"pricing":{"summary":"Free tier with limited agent requests. Paid plans from USD 20 per month, with usage based pricing above the allowance.","price_display":"USD 20 / month","price_amount":20,"price_currency":"USD","price_unit":"account","price_source_url":"https://cursor.com/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":17.1},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":3,"rank_delta":0,"slug":"kiro","name":"Kiro","board":"coding-agent","official_url":"https://kiro.dev","page_url":"https://www.llm-tier.com/builders/kiro","index_score":75.67,"index_score_recomputed":75.67,"subscores":{"agent_perf":84,"reliability":93.3,"scalability":80,"seo_geo":60,"api_mcp":72,"integrations":74,"design":65,"speed":43.4,"value":78},"turn_latency_seconds":{"p10":49.1,"median":72.4,"p90":140.4,"full_spec_minutes_derived":10.9},"runs":{"completed":44,"failed":1,"reliability_pct":93.3},"shipped_output":{"html_bytes_no_js":22528,"lcp_ms":1800,"cls":0.04},"pricing":{"summary":"Free tier with a monthly interaction allowance. Paid plans from USD 20 per user per month.","price_display":"USD 20 / user / month","price_amount":20,"price_currency":"USD","price_unit":"user","price_source_url":"https://kiro.dev/pricing/","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":17.1},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":4,"rank_delta":0,"slug":"augment-code","name":"Augment Code","board":"coding-agent","official_url":"https://augmentcode.com","page_url":"https://www.llm-tier.com/builders/augment-code","index_score":75.63,"index_score_recomputed":75.63,"subscores":{"agent_perf":86,"reliability":88.9,"scalability":84,"seo_geo":58,"api_mcp":74,"integrations":76,"design":62,"speed":43.9,"value":77},"turn_latency_seconds":{"p10":44.9,"median":71.6,"p90":110,"full_spec_minutes_derived":10.7},"runs":{"completed":43,"failed":2,"reliability_pct":88.9},"shipped_output":{"html_bytes_no_js":22528,"lcp_ms":1800,"cls":0.04},"pricing":{"summary":"From USD 20 per month on the Standard plan, flat for a team up to 50 seats. There is a trial but no free tier of any size.","price_display":"USD 20 / month, flat for a team up to 50 seats","price_amount":20,"price_currency":"USD","price_unit":"team","price_source_url":"https://augmentcode.com/pricing","price_fetched_at":"2026-09-05","price_note":"Augment prices flat for a whole team rather than per seat: Standard is USD 20 a month covering up to 50 seats, with USD 20 of metered usage included and top-ups charged as you go. Business is USD 100 a month on the same up-to-50-seats shape. There is no individual tier and no free tier.","price_eur_normalised":17.1},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":5,"rank_delta":1,"slug":"amp","name":"Amp","board":"coding-agent","official_url":"https://ampcode.com","page_url":"https://www.llm-tier.com/builders/amp","index_score":73.35,"index_score_recomputed":73.35,"subscores":{"agent_perf":85,"reliability":77.8,"scalability":74,"seo_geo":56,"api_mcp":72,"integrations":68,"design":60,"speed":79.1,"value":77},"turn_latency_seconds":{"p10":24.2,"median":39.7,"p90":64.4,"full_spec_minutes_derived":6},"runs":{"completed":41,"failed":4,"reliability_pct":77.8},"shipped_output":{"html_bytes_no_js":20480,"lcp_ms":1840,"cls":0.04},"pricing":{"summary":"From USD 20 per month on the Megawatt plan, which bundles an agent usage allowance worth the subscription price. There is no free tier and no trial. An Unconstrained pay as you go tier exists for usage that does not fit a monthly plan, but the vendor publishes no rate card for it, so it cannot be budgeted in advance.","price_display":"USD 20 / month","price_amount":20,"price_currency":"USD","price_unit":"account","price_source_url":"https://ampcode.com/pricing","price_fetched_at":"2026-08-28","price_note":"Gigawatt is USD 200 per month. Students and teachers can self declare for an education discount at USD 10 per month. The Unconstrained and Enterprise tiers publish no figure.","price_eur_normalised":17.1},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":6,"rank_delta":1,"slug":"factory","name":"Factory","board":"coding-agent","official_url":"https://factory.ai","page_url":"https://www.llm-tier.com/builders/factory","index_score":71.48,"index_score_recomputed":71.48,"subscores":{"agent_perf":81,"reliability":82.2,"scalability":82,"seo_geo":56,"api_mcp":76,"integrations":78,"design":62,"speed":19.4,"value":76},"turn_latency_seconds":{"p10":84.8,"median":161.7,"p90":350.8,"full_spec_minutes_derived":24.3},"runs":{"completed":42,"failed":3,"reliability_pct":82.2},"shipped_output":{"html_bytes_no_js":19456,"lcp_ms":1940,"cls":0.05},"pricing":{"summary":"From USD 20 per month on the Pro plan. Enterprise plans are quoted rather than listed.","price_display":"USD 20 / month","price_amount":20,"price_currency":"USD","price_unit":"account","price_source_url":"https://factory.ai/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":17.1},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":7,"rank_delta":1,"slug":"antigravity","name":"Antigravity","board":"coding-agent","official_url":"https://antigravity.google","page_url":"https://www.llm-tier.com/builders/antigravity","index_score":71.37,"index_score_recomputed":71.37,"subscores":{"agent_perf":83,"reliability":73.3,"scalability":76,"seo_geo":58,"api_mcp":70,"integrations":72,"design":70,"speed":39.9,"value":90},"turn_latency_seconds":{"p10":45,"median":78.7,"p90":123.1,"full_spec_minutes_derived":11.8},"runs":{"completed":40,"failed":5,"reliability_pct":73.3},"shipped_output":{"html_bytes_no_js":22528,"lcp_ms":1820,"cls":0.04},"pricing":{"summary":"Generally available at no cost for individuals, with basic weekly rate limits rather than a subscription. More generous limits and an AI credit pool need a Google AI Pro or Ultra plan, and an organisation plan via Google Cloud is rolling out at consumption-based pricing.","price_display":"No cost","price_amount":0,"price_currency":"USD","price_unit":"account","price_source_url":"https://antigravity.google/pricing","price_fetched_at":"2026-09-06","price_note":null,"price_eur_normalised":0},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":8,"rank_delta":1,"slug":"zed","name":"Zed","board":"coding-agent","official_url":"https://zed.dev","page_url":"https://www.llm-tier.com/builders/zed","index_score":71.13,"index_score_recomputed":71.13,"subscores":{"agent_perf":77,"reliability":71.1,"scalability":70,"seo_geo":55,"api_mcp":66,"integrations":64,"design":64,"speed":100,"value":82},"turn_latency_seconds":{"p10":19.8,"median":31.4,"p90":54.5,"full_spec_minutes_derived":4.7},"runs":{"completed":37,"failed":8,"reliability_pct":71.1},"shipped_output":{"html_bytes_no_js":19456,"lcp_ms":1780,"cls":0.04},"pricing":{"summary":"The editor is free and open source. Hosted agent usage starts at USD 10 per month, or bring your own model key at no licence cost.","price_display":"USD 10 / month","price_amount":10,"price_currency":"USD","price_unit":"account","price_source_url":"https://zed.dev/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":8.55},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":9,"rank_delta":1,"slug":"cline","name":"Cline","board":"coding-agent","official_url":"https://cline.bot","page_url":"https://www.llm-tier.com/builders/cline","index_score":70.66,"index_score_recomputed":70.66,"subscores":{"agent_perf":82,"reliability":80,"scalability":72,"seo_geo":57,"api_mcp":70,"integrations":72,"design":63,"speed":33,"value":88},"turn_latency_seconds":{"p10":47.4,"median":95.1,"p90":201.7,"full_spec_minutes_derived":14.3},"runs":{"completed":44,"failed":1,"reliability_pct":80},"shipped_output":{"html_bytes_no_js":21504,"lcp_ms":1860,"cls":0.04},"pricing":{"summary":"Free and open source extension. You pay only for the model tokens you use.","price_display":"No licence fee, bring your own model key","price_amount":0,"price_currency":"USD","price_unit":"account","price_source_url":"https://cline.bot/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":0},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":10,"rank_delta":2,"slug":"jules","name":"Jules","board":"coding-agent","official_url":"https://jules.google","page_url":"https://www.llm-tier.com/builders/jules","index_score":68.04,"index_score_recomputed":68.04,"subscores":{"agent_perf":80,"reliability":75.6,"scalability":74,"seo_geo":55,"api_mcp":66,"integrations":70,"design":62,"speed":21.4,"value":88},"turn_latency_seconds":{"p10":84.4,"median":146.5,"p90":292.7,"full_spec_minutes_derived":22},"runs":{"completed":41,"failed":4,"reliability_pct":75.6},"shipped_output":{"html_bytes_no_js":21504,"lcp_ms":1860,"cls":0.04},"pricing":{"summary":"Free tier with a daily task allowance. Higher limits come with a consumer subscription rather than a separate licence.","price_display":"No cost on the free tier","price_amount":0,"price_currency":"USD","price_unit":"account","price_source_url":"https://jules.google/","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":0},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":11,"rank_delta":2,"slug":"devin","name":"Devin","board":"coding-agent","official_url":"https://devin.ai","page_url":"https://www.llm-tier.com/builders/devin","index_score":66.64,"index_score_recomputed":66.64,"subscores":{"agent_perf":78,"reliability":71.1,"scalability":80,"seo_geo":54,"api_mcp":72,"integrations":74,"design":60,"speed":8.9,"value":74},"turn_latency_seconds":{"p10":230.2,"median":353.6,"p90":651.4,"full_spec_minutes_derived":53},"runs":{"completed":39,"failed":6,"reliability_pct":71.1},"shipped_output":{"html_bytes_no_js":20480,"lcp_ms":1900,"cls":0.05},"pricing":{"summary":"From USD 20 per month for a starter allowance, then metered per compute unit. A full run of this spec consumes a large share of a starter allowance.","price_display":"USD 20 / month","price_amount":20,"price_currency":"USD","price_unit":"account","price_source_url":"https://devin.ai/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":17.1},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":12,"rank_delta":2,"slug":"qodo","name":"Qodo","board":"coding-agent","official_url":"https://qodo.ai","page_url":"https://www.llm-tier.com/builders/qodo","index_score":66.06,"index_score_recomputed":66.06,"subscores":{"agent_perf":70,"reliability":77.8,"scalability":76,"seo_geo":52,"api_mcp":68,"integrations":70,"design":56,"speed":31.6,"value":70},"turn_latency_seconds":{"p10":66.3,"median":99.3,"p90":189.8,"full_spec_minutes_derived":14.9},"runs":{"completed":41,"failed":4,"reliability_pct":77.8},"shipped_output":{"html_bytes_no_js":16384,"lcp_ms":2000,"cls":0.05},"pricing":{"summary":"Free 14 day trial. The Pro Team plan is USD 30 per month with credits pooled across a team of up to 30 users, not charged per seat.","price_display":"USD 30 / month, pooled across a team of up to 30 users","price_amount":30,"price_currency":"USD","price_unit":"team","price_source_url":"https://qodo.ai/pricing/","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":25.64},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":13,"rank_delta":2,"slug":"aider","name":"Aider","board":"coding-agent","official_url":"https://aider.chat","page_url":"https://www.llm-tier.com/builders/aider","index_score":65.88,"index_score_recomputed":65.88,"subscores":{"agent_perf":72,"reliability":68.9,"scalability":64,"seo_geo":54,"api_mcp":62,"integrations":58,"design":52,"speed":79.7,"value":86},"turn_latency_seconds":{"p10":22.5,"median":39.4,"p90":75.7,"full_spec_minutes_derived":5.9},"runs":{"completed":38,"failed":7,"reliability_pct":68.9},"shipped_output":{"html_bytes_no_js":17408,"lcp_ms":1920,"cls":0.05},"pricing":{"summary":"Free and open source. You pay only for the model tokens you use.","price_display":"No licence fee, bring your own model key","price_amount":0,"price_currency":"USD","price_unit":"account","price_source_url":"https://aider.chat/docs/faq.html","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":0},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":14,"rank_delta":2,"slug":"codebuff","name":"Codebuff","board":"coding-agent","official_url":"https://codebuff.com","page_url":"https://www.llm-tier.com/builders/codebuff","index_score":64.51,"index_score_recomputed":64.51,"subscores":{"agent_perf":76,"reliability":68.9,"scalability":68,"seo_geo":55,"api_mcp":64,"integrations":62,"design":58,"speed":52.5,"value":52},"turn_latency_seconds":{"p10":36.1,"median":59.8,"p90":110.7,"full_spec_minutes_derived":9},"runs":{"completed":38,"failed":7,"reliability_pct":68.9},"shipped_output":{"html_bytes_no_js":18432,"lcp_ms":1900,"cls":0.05},"pricing":{"summary":"Free credits to start, then from USD 100 per month minimum subscription with usage based credits.","price_display":"USD 100 / month minimum subscription","price_amount":100,"price_currency":"USD","price_unit":"account","price_source_url":"https://codebuff.com/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":85.48},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":15,"rank_delta":2,"slug":"openhands","name":"OpenHands","board":"coding-agent","official_url":"https://openhands.dev","page_url":"https://www.llm-tier.com/builders/openhands","index_score":63.93,"index_score_recomputed":63.93,"subscores":{"agent_perf":74,"reliability":64.4,"scalability":70,"seo_geo":56,"api_mcp":68,"integrations":66,"design":58,"speed":21.7,"value":86},"turn_latency_seconds":{"p10":81.4,"median":144.8,"p90":269.1,"full_spec_minutes_derived":21.7},"runs":{"completed":38,"failed":7,"reliability_pct":64.4},"shipped_output":{"html_bytes_no_js":18432,"lcp_ms":1980,"cls":0.05},"pricing":{"summary":"Free and open source, self hosted. A managed cloud option is metered. You supply the model key either way.","price_display":"No licence fee, self hosted","price_amount":0,"price_currency":"USD","price_unit":"account","price_source_url":"https://openhands.dev/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":0},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":16,"rank_delta":2,"slug":"trae","name":"Trae","board":"coding-agent","official_url":"https://trae.ai","page_url":"https://www.llm-tier.com/builders/trae","index_score":61,"index_score_recomputed":61,"subscores":{"agent_perf":73,"reliability":51.1,"scalability":66,"seo_geo":54,"api_mcp":60,"integrations":66,"design":66,"speed":32.5,"value":84},"turn_latency_seconds":{"p10":38.2,"median":96.7,"p90":167.9,"full_spec_minutes_derived":14.5},"runs":{"completed":32,"failed":13,"reliability_pct":51.1},"shipped_output":{"html_bytes_no_js":18432,"lcp_ms":1960,"cls":0.05},"pricing":{"summary":"Free tier with a real allowance rather than a token one. Paid plans from USD 3 per month, billed monthly.","price_display":"USD 3 / month, billed monthly","price_amount":3,"price_currency":"USD","price_unit":"account","price_source_url":"https://trae.ai/pricing","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":2.56},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null},{"rank":17,"rank_delta":2,"slug":"roomote","name":"Roomote","board":"coding-agent","official_url":"https://roomote.dev","page_url":"https://www.llm-tier.com/builders/roomote","index_score":59.89,"index_score_recomputed":59.89,"subscores":{"agent_perf":71,"reliability":53.3,"scalability":66,"seo_geo":53,"api_mcp":62,"integrations":60,"design":56,"speed":32.6,"value":84},"turn_latency_seconds":{"p10":54.3,"median":96.4,"p90":202.9,"full_spec_minutes_derived":14.5},"runs":{"completed":35,"failed":10,"reliability_pct":53.3},"shipped_output":{"html_bytes_no_js":17408,"lcp_ms":1980,"cls":0.05},"pricing":{"summary":"No licence fee for the open source agent, self hosted up to 10 users. A hosted cloud tier is also available, starting at USD 49 per month.","price_display":"No licence fee, self hosted up to 10 users","price_amount":0,"price_currency":"USD","price_unit":"account","price_source_url":"https://roomote.dev/","price_fetched_at":"2026-08-21","price_note":null,"price_eur_normalised":0},"last_run_at":"2026-08-15T09:11:37.500Z","next_run_at":null}],"models_roster":[{"slug":"claude-opus-5","name":"Claude Opus 5","vendor":"Anthropic","status":"current","tier":"flagship","licence":"Proprietary","context_window_text":"1,000,000","max_output_text":"128,000","price_in_text":"5.00","price_out_text":"25.00","modality_text":"text and image in, text out","arena_webdev":{"elo":1691,"rank":1,"votes":8116,"preliminary":false},"bench_aa_index_v4_1_1":"63 at max effort, 63 at xhigh, 61 at high","bench_terminal_bench_v2_1":"89.1% at max effort","release_note":"Release date not stated by the vendor; training data cutoff May 2026. Arena also lists the high-effort variant separately: 1663 Elo, rank 4, 8659 votes.","source_urls":"Anthropic pricing/models page (anthropic.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026; Artificial Analysis (artificialanalysis.ai)","page_url":"https://www.llm-tier.com/leaderboard/llms#claude-opus-5"},{"slug":"kimi-k3","name":"Kimi K3","vendor":"Moonshot AI","status":"current","tier":"flagship","licence":"Modified MIT, published by Moonshot as the Kimi K3 License; open weights","context_window_text":"1,048,576","max_output_text":"Not stated on the vendor pricing page","price_in_text":"3.00 on a cache miss, 0.30 on a cache hit","price_out_text":"15.00","modality_text":"Multimodal reasoning with thinking always on, per secondary reporting","arena_webdev":{"elo":1674,"rank":2,"votes":4546,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Released 16 July 2026; full open weights 27 July 2026. Kimi K3 always reasons and exposes a reasoning_effort setting of low, high or max, defaulting to max, which is why Arena lists it as kimi-k3-max (max effort). A third-party host lists the same weights at 2.60 / 13.00. That is the host's price, not Moonshot's, and we publish Moonshot's.","source_urls":"Moonshot AI platform pricing (platform.moonshot.ai); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#kimi-k3"},{"slug":"qwen3-8-max","name":"Qwen3.8-Max","vendor":"Alibaba","status":"current","tier":"flagship","licence":"Proprietary","context_window_text":"1,048,576, charged at one flat rate across the whole window with no length tiering","max_output_text":"131,000","price_in_text":"2.00 (batch inference 1.65; context-caching discount available)","price_out_text":"6.00, covering chain of thought plus answer (batch inference 4.951)","modality_text":"text, image and video in, text out","arena_webdev":{"elo":1669,"rank":3,"votes":3212,"preliminary":true},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Previewed 19 July 2026, global API access via Alibaba Cloud Model Studio 3 August 2026. There is no independently measured coding-benchmark score for this model, so we publish none, and its Arena Elo carries Arena's own Preliminary flag on 3,212 votes. It is also the only flagship on this board with no 200k price step, which makes it unusually cheap on very long prompts.","source_urls":"Alibaba Cloud Model Studio pricing (alibabacloud.com/product/modelstudio); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#qwen3-8-max"},{"slug":"grok-4-6","name":"Grok 4.6","vendor":"xAI","status":"current","tier":"flagship","licence":"Proprietary","context_window_text":"500,000","max_output_text":"No stated text output limit","price_in_text":"2.00 below 200k prompt tokens, 4.00 above (cached 0.50 / 1.00)","price_out_text":"6.00 below 200k prompt tokens, 12.00 above","modality_text":"The xAI models page lists text in and text out; secondary reporting says image input is also supported, which we have not confirmed","arena_webdev":{"elo":1629,"rank":5,"votes":1523,"preliminary":true},"bench_aa_index_v4_1_1":"61 per secondary reporting of the index","bench_terminal_bench_v2_1":"88.4% at high effort","release_note":"12 August 2026 per secondary reporting; not dated on xAI's models page. Arena files xAI's models under the lab name SpaceXAI; the vendor documentation domain is docs.x.ai and we publish the vendor as xAI. See Grok 4.3 below for the headline counter-example on this board.","source_urls":"xAI models page (docs.x.ai); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026; Artificial Analysis (artificialanalysis.ai)","page_url":"https://www.llm-tier.com/leaderboard/llms#grok-4-6"},{"slug":"claude-fable-5","name":"Claude Fable 5","vendor":"Anthropic","status":"current","tier":"flagship","licence":"Proprietary","context_window_text":"1,000,000","max_output_text":"128,000 (300,000 on the Batch API with the output-300k-2026-03-24 beta header)","price_in_text":"10.00","price_out_text":"50.00","modality_text":"text and image in, text out","arena_webdev":{"elo":1626,"rank":6,"votes":8382,"preliminary":false},"bench_aa_index_v4_1_1":"62 (Adaptive Reasoning, Max Effort)","bench_terminal_bench_v2_1":"Not in the published top three","release_note":"Available from 9 June 2026.","source_urls":"Anthropic pricing/models page (anthropic.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026; Artificial Analysis (artificialanalysis.ai)","page_url":"https://www.llm-tier.com/leaderboard/llms#claude-fable-5"},{"slug":"gpt-5-6-sol","name":"GPT-5.6 Sol","vendor":"OpenAI","status":"current","tier":"flagship","licence":"Proprietary","context_window_text":"Not published on OpenAI's pricing page","max_output_text":"Not published on OpenAI's pricing page","price_in_text":"4.00 (cached input 0.40)","price_out_text":"20.00","modality_text":"text in, text out per the pricing table","arena_webdev":{"elo":1619,"rank":7,"votes":9499,"preliminary":false},"bench_aa_index_v4_1_1":"61 at max effort","bench_terminal_bench_v2_1":"89.5% at xhigh effort, the published leader","release_note":"Limited preview 26 June 2026, public launch 9 July 2026. Arena entry uses xhigh effort in the Codex harness. See the pricing warning box above: Arena lists this model at the older GPT-5.5 price.","source_urls":"OpenAI pricing page (openai.com/api/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026; Artificial Analysis Terminal-Bench v2.1 (artificialanalysis.ai)","page_url":"https://www.llm-tier.com/leaderboard/llms#gpt-5-6-sol"},{"slug":"gemini-3-7-flash","name":"Gemini 3.7 Flash","vendor":"Google","status":"current","tier":"workhorse","licence":"Proprietary","context_window_text":"Not stated on the fetched pages","max_output_text":"Not stated","price_in_text":"0.75 through 31 December 2026, then 1.50 from 1 January 2027","price_out_text":"3.75 through 31 December 2026, then 7.50 from 1 January 2027","modality_text":"Not stated per model on the fetched page","arena_webdev":{"elo":1587,"rank":10,"votes":2552,"preliminary":true},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"13 August 2026 per secondary reporting; Google's own pages mark it stable but do not date it. Arena entry uses high effort and carries Arena's Preliminary flag. Google publishes DeepSWE v1.1 rising from 49.0 to 65.3 percent and GDM-MRCR v2 at 128k rising from 91.8 to 97.0 percent versus the prior Flash. Those are Google's own figures on Google's own evaluation and are labelled vendor-claimed, not independent.","source_urls":"Google AI pricing/models pages (ai.google.dev/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#gemini-3-7-flash"},{"slug":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","vendor":"DeepSeek","status":"current","tier":"flagship","licence":"MIT","context_window_text":"1,000,000","max_output_text":"Not stated on the pricing page","price_in_text":"0.66 off-peak, 1.32 at peak (cache hit 0.022 off-peak, 0.044 peak)","price_out_text":"1.98 off-peak, 3.96 at peak","modality_text":"text in, text out; a separate deepseek-v4-flash-vision-exp handles vision","arena_webdev":{"elo":1582,"rank":12,"votes":2869,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Version string DeepSeek-V4-Pro-0813 implies 13 August 2026; not dated in prose. Arena entry uses high effort on the 20260813 build. DeepSeek has no single price: off-peak is half of peak, and peak runs 01:00 to 04:00 and 06:00 to 10:00 UTC. Any value comparison must state which rate it used.","source_urls":"DeepSeek API pricing page (api-docs.deepseek.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#deepseek-v4-pro"},{"slug":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","vendor":"DeepSeek","status":"current","tier":"budget","licence":"MIT","context_window_text":"1,000,000","max_output_text":"Not stated","price_in_text":"0.22 off-peak, 0.44 at peak (cache hit 0.007 / 0.014)","price_out_text":"0.66 off-peak, 1.32 at peak","modality_text":"text in, text out","arena_webdev":{"elo":1579,"rank":13,"votes":3537,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Version string DeepSeek-V4-Flash-0731 implies 31 July 2026. Arena entry uses high effort. DeepSeek has no single price: off-peak is half of peak, and peak runs 01:00 to 04:00 and 06:00 to 10:00 UTC. Any value comparison must state which rate it used. See the cheapest-output callout above for why this row and GPT-5.6 Luna cannot both hold that crown.","source_urls":"DeepSeek API pricing page (api-docs.deepseek.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#deepseek-v4-flash"},{"slug":"claude-sonnet-5","name":"Claude Sonnet 5","vendor":"Anthropic","status":"current","tier":"workhorse","licence":"Proprietary","context_window_text":"1,000,000","max_output_text":"128,000","price_in_text":"2.00","price_out_text":"10.00","modality_text":"text and image in, text out","arena_webdev":{"elo":1539,"rank":22,"votes":7267,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Release date not stated by the vendor. Arena effort level: high.","source_urls":"Anthropic pricing/models page (anthropic.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#claude-sonnet-5"},{"slug":"gemini-3-6-flash","name":"Gemini 3.6 Flash","vendor":"Google","status":"current","tier":"workhorse","licence":"Proprietary","context_window_text":"Not stated","max_output_text":"Not stated","price_in_text":"0.75, rising to 1.50 on 1 January 2027","price_out_text":"3.75, rising to 7.50 on 1 January 2027","modality_text":"Not stated","arena_webdev":{"elo":1539,"rank":21,"votes":6464,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Not dated on Google's pages; marked stable. Arena entry uses high effort.","source_urls":"Google AI pricing/models pages (ai.google.dev/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#gemini-3-6-flash"},{"slug":"muse-spark-1-1","name":"Muse Spark 1.1","vendor":"Meta","status":"current","tier":"flagship","licence":"Proprietary, closed weights","context_window_text":"1,000,000","max_output_text":"Not specified in Meta's announcement","price_in_text":"Not published by Meta","price_out_text":"Not published by Meta","modality_text":"text, images, video and PDFs in, text out","arena_webdev":{"elo":1539,"rank":20,"votes":6204,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Developed by Meta Superintelligence Labs. Muse Spark launched 8 April 2026 as Meta's first closed-weight model; 1.1 released 9 July 2026. Meta's own announcement publishes no per-token price and no numerical benchmark score, so both cells are empty here. Price is the single most-quoted number in secondary coverage and the single number Meta does not state. Arena also lists a muse-spark-1.2 at 1534 Elo; we have not sourced 1.2 from Meta and so do not list it as a row.","source_urls":"Meta Superintelligence Labs announcement (meta.com/ai); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#muse-spark-1-1"},{"slug":"gpt-5-6-terra","name":"GPT-5.6 Terra","vendor":"OpenAI","status":"current","tier":"workhorse","licence":"Proprietary","context_window_text":"Not published","max_output_text":"Not published","price_in_text":"2.00 (cached input 0.20)","price_out_text":"12.00","modality_text":"text in, text out","arena_webdev":{"elo":1520,"rank":27,"votes":5677,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Launched 9 July 2026. Arena entry uses xhigh effort in the Codex harness.","source_urls":"OpenAI pricing page (openai.com/api/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#gpt-5-6-terra"},{"slug":"gpt-5-6-luna","name":"GPT-5.6 Luna","vendor":"OpenAI","status":"current","tier":"budget","licence":"Proprietary","context_window_text":"Not published","max_output_text":"Not published","price_in_text":"0.20 (cached input 0.02)","price_out_text":"1.20","modality_text":"text in, text out","arena_webdev":{"elo":1518,"rank":29,"votes":5742,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Launched 9 July 2026. Arena entry uses xhigh effort in the Codex harness. Flat 1.20 output price. See the DeepSeek-V4-Flash row for the peak and off-peak comparison, since neither is cheapest all day.","source_urls":"OpenAI pricing page (openai.com/api/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#gpt-5-6-luna"},{"slug":"gemini-3-5-flash","name":"Gemini 3.5 Flash","vendor":"Google","status":"current","tier":"workhorse","licence":"Proprietary","context_window_text":"Not stated","max_output_text":"Not stated","price_in_text":"1.50","price_out_text":"9.00","modality_text":"Not stated","arena_webdev":{"elo":1499,"rank":34,"votes":7559,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Not dated; marked stable. Arena entry uses high effort. This middle rung is worse value than both newer Flash models, which cost 0.75 / 3.75. Inside one vendor's line, newer here is both better and cheaper.","source_urls":"Google AI pricing/models pages (ai.google.dev/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#gemini-3-5-flash"},{"slug":"gemini-3-5-flash-lite","name":"Gemini 3.5 Flash-Lite","vendor":"Google","status":"current","tier":"budget","licence":"Proprietary","context_window_text":"Not stated","max_output_text":"Not stated","price_in_text":"0.30","price_out_text":"2.50","modality_text":"Not stated","arena_webdev":{"elo":1449,"rank":47,"votes":228,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Not dated; marked stable. Arena's interval on this row is plus or minus 43 points on only 228 votes (1449 ± 43), far too wide to rank against its neighbours.","source_urls":"Google AI pricing/models pages (ai.google.dev/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#gemini-3-5-flash-lite"},{"slug":"gemini-3-1-pro-preview","name":"Gemini 3.1 Pro Preview","vendor":"Google","status":"preview","tier":"flagship","licence":"Proprietary","context_window_text":"Not stated on Google's models or pricing pages","max_output_text":"Not stated","price_in_text":"2.00 for prompts up to 200k tokens, 4.00 above 200k (batch 1.00 / 2.00)","price_out_text":"12.00 up to 200k, 18.00 above 200k (batch 6.00 / 9.00)","modality_text":"Not stated per model on the fetched page","arena_webdev":{"elo":1446,"rank":48,"votes":21573,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Still carries preview status. This is the only Pro-tier Gemini 3 text model on Google's own list; every stable Gemini 3 text model is a Flash or Flash-Lite.","source_urls":"Google AI pricing/models pages (ai.google.dev/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#gemini-3-1-pro-preview"},{"slug":"gpt-5-3-codex","name":"GPT-5.3 Codex","vendor":"OpenAI","status":"current","tier":"coding","licence":"Proprietary","context_window_text":"Not published","max_output_text":"Not published","price_in_text":"1.75 (cached input 0.175)","price_out_text":"14.00","modality_text":"text in, text out, coding specialised","arena_webdev":{"elo":1408,"rank":61,"votes":2526,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Release date not published. Arena entry runs in the Codex harness.","source_urls":"OpenAI pricing page (openai.com/api/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#gpt-5-3-codex"},{"slug":"grok-4-3","name":"Grok 4.3","vendor":"xAI","status":"current","tier":"workhorse","licence":"Proprietary","context_window_text":"1,000,000","max_output_text":"Not stated","price_in_text":"1.25 below 200k prompt tokens, 2.50 above (cached 0.20 / 0.40)","price_out_text":"2.50 below 200k, 5.00 above","modality_text":"text in, text out","arena_webdev":{"elo":1357,"rank":86,"votes":12942,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Not dated on xAI's models page. HEADLINE COUNTER-EXAMPLE ON THIS BOARD: Grok 4.3 has double the context window of xAI's newer flagship (Grok 4.6) at roughly 40 percent of its output price, and sits 272 Elo points lower on Arena WebDev. Newer, wider and cheaper are three different axes and no vendor wins all three at once.","source_urls":"xAI models page (docs.x.ai); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#grok-4-3"},{"slug":"amazon-nova-2-lite","name":"Amazon Nova 2 Lite","vendor":"Amazon","status":"current","tier":"workhorse","licence":"Proprietary","context_window_text":"1,000,000","max_output_text":"65,536","price_in_text":"Not published on the Nova 2 user guide, which defers to Amazon Bedrock Pricing; the Bedrock pricing page carries no Nova 2 row","price_out_text":"Not published","modality_text":"text, images, video and documents in, text out","arena_webdev":{"elo":null,"rank":null,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Release date not stated on the Nova 2 user guide. Nova 2 is Amazon's current generation and its whole roster is Nova 2 Lite, Nova 2 Sonic and Nova Multimodal Embeddings. Nova Premier, Nova Pro, Nova Lite and Nova Micro are all the superseded Nova 1 generation. Every Nova 2 model is 1,000,000 tokens in and 65,536 out.","source_urls":"Amazon Nova user guide (docs.aws.amazon.com/nova); Amazon Bedrock pricing page (aws.amazon.com/bedrock/pricing)","page_url":"https://www.llm-tier.com/leaderboard/llms#amazon-nova-2-lite"},{"slug":"claude-haiku-4-5","name":"Claude Haiku 4.5","vendor":"Anthropic","status":"current","tier":"budget","licence":"Proprietary","context_window_text":"200,000","max_output_text":"64,000","price_in_text":"1.00","price_out_text":"5.00","modality_text":"text and image in, text out","arena_webdev":{"elo":null,"rank":null,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Model ID pins the snapshot to 1 October 2025.","source_urls":"Anthropic pricing/models page (anthropic.com/pricing)","page_url":"https://www.llm-tier.com/leaderboard/llms#claude-haiku-4-5"},{"slug":"command-a-plus","name":"Command A+","vendor":"Cohere","status":"current","tier":"flagship","licence":"Apache 2.0","context_window_text":"Not published for this model","max_output_text":"Not published","price_in_text":"Not published. cohere.com/pricing carries only legacy Command rows and has no Command A+ row at all.","price_out_text":"Not published","modality_text":"text and image in, text out","arena_webdev":{"elo":null,"rank":null,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"20 May 2026. 218 billion total parameters with 25 billion active in a sparse mixture of experts, 48 languages, native citation generation. Cohere's flagship is three months old and its own public pricing page does not list it. We publish the model with no price rather than sourcing one from an aggregator.","source_urls":"Cohere pricing page (cohere.com/pricing)","page_url":"https://www.llm-tier.com/leaderboard/llms#command-a-plus"},{"slug":"gemini-3-1-flash-lite","name":"Gemini 3.1 Flash-Lite","vendor":"Google","status":"current","tier":"budget","licence":"Proprietary","context_window_text":"Not stated","max_output_text":"Not stated","price_in_text":"0.25 for text, image and video; 0.50 for audio","price_out_text":"1.50","modality_text":"text, image, video and audio in per the pricing tiers","arena_webdev":{"elo":null,"rank":null,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Not dated; marked stable. Google's own model list describes this as frontier class; we attribute that claim to Google and do not restate it as fact.","source_urls":"Google AI pricing/models pages (ai.google.dev/pricing)","page_url":"https://www.llm-tier.com/leaderboard/llms#gemini-3-1-flash-lite"},{"slug":"llama-4-maverick","name":"Llama 4 Maverick","vendor":"Meta","status":"open_weight","tier":"workhorse","licence":"Open weights","context_window_text":"Previously published here as 1,000,000; not re-verified in this pass","max_output_text":"Not re-verified","price_in_text":"No vendor list price exists","price_out_text":"No vendor list price exists","modality_text":"Not re-verified","arena_webdev":{"elo":null,"rank":null,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"5 April 2025, alongside Llama 4 Scout. No new Llama model has shipped since. We previously published 0.22 / 0.85 for this model. That figure was unsourceable by construction, not merely stale: these are open weights and there is no vendor list price at all, only per-host prices. We have removed it. Llama is no longer Meta's frontier: Meta's frontier since April 2026 is Muse Spark, which is closed and paid.","source_urls":"Meta AI Llama models page (llama.meta.com)","page_url":"https://www.llm-tier.com/leaderboard/llms#llama-4-maverick"},{"slug":"mistral-medium-3-5","name":"Mistral Medium 3.5","vendor":"Mistral AI","status":"current","tier":"flagship","licence":"Modified MIT","context_window_text":"Not listed on Mistral's models overview page","max_output_text":"Not listed","price_in_text":"Not published on Mistral's docs page","price_out_text":"Not published on Mistral's docs page","modality_text":"Multimodal per Mistral's own description","arena_webdev":{"elo":null,"rank":null,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Version string v26.04 implies April 2026; not dated in prose. Mistral's current premier flagship, described by Mistral as frontier class and optimised for agentic and coding work.","source_urls":"Mistral AI models overview and docs pages (mistral.ai/products/models, docs.mistral.ai)","page_url":"https://www.llm-tier.com/leaderboard/llms#mistral-medium-3-5"},{"slug":"mistral-small-4","name":"Mistral Small 4","vendor":"Mistral AI","status":"open_weight","tier":"workhorse","licence":"Apache 2.0","context_window_text":"Not listed on Mistral's docs page","max_output_text":"Not listed","price_in_text":"Not published on Mistral's docs page","price_out_text":"Not published on Mistral's docs page","modality_text":"Unified instruct, reasoning and coding, with multimodal understanding, per secondary reporting","arena_webdev":{"elo":null,"rank":null,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"16 March 2026 per secondary reporting; version string v26.03 is consistent.","source_urls":"Mistral AI docs page (docs.mistral.ai)","page_url":"https://www.llm-tier.com/leaderboard/llms#mistral-small-4"}],"models_legacy":[{"slug":"claude-opus-4-7","name":"Claude Opus 4.7","vendor":"Anthropic","status":"legacy","tier":null,"licence":"Proprietary","context_window_text":"1,000,000","max_output_text":"128,000","price_in_text":"5.00","price_out_text":"25.00","modality_text":"text and image in, text out","arena_webdev":{"elo":1558,"rank":15,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Anthropic itself files this model under Legacy models and recommends migrating. Arena also lists a high-effort variant separately: 1557 Elo, rank 16.","source_urls":"Anthropic pricing/models page (anthropic.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#claude-opus-4-7"},{"slug":"claude-opus-4-8","name":"Claude Opus 4.8","vendor":"Anthropic","status":"legacy","tier":null,"licence":"Proprietary","context_window_text":"1,000,000","max_output_text":"128,000","price_in_text":"5.00","price_out_text":"25.00","modality_text":"text and image in, text out","arena_webdev":{"elo":1539,"rank":19,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Anthropic itself files this model under Legacy models and recommends migrating. Arena also lists a high-effort variant separately: 1563 Elo, rank 14.","source_urls":"Anthropic pricing/models page (anthropic.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#claude-opus-4-8"},{"slug":"claude-opus-4-6","name":"Claude Opus 4.6","vendor":"Anthropic","status":"legacy","tier":null,"licence":"Proprietary","context_window_text":"1,000,000","max_output_text":"128,000","price_in_text":"5.00","price_out_text":"25.00","modality_text":"text and image in, text out","arena_webdev":{"elo":1536,"rank":23,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Anthropic itself files this model under Legacy models and recommends migrating. Arena also lists a high-effort variant separately: 1546 Elo, rank 18.","source_urls":"Anthropic pricing/models page (anthropic.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#claude-opus-4-6"},{"slug":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","vendor":"Anthropic","status":"legacy","tier":null,"licence":"Proprietary","context_window_text":"1,000,000","max_output_text":"128,000","price_in_text":"3.00","price_out_text":"15.00","modality_text":"text and image in, text out","arena_webdev":{"elo":1522,"rank":25,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Anthropic itself files this model under Legacy models and recommends migrating.","source_urls":"Anthropic pricing/models page (anthropic.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#claude-sonnet-4-6"},{"slug":"qwen3-max","name":"Qwen3 Max","vendor":"Alibaba","status":"legacy","tier":null,"licence":"Proprietary","context_window_text":"262,144 as originally published; understates the real current window by roughly four times","max_output_text":"-","price_in_text":"2.50 list, limited-time 50 percent discount","price_out_text":"7.50 list, limited-time 50 percent discount","modality_text":"text, image and video in, text out","arena_webdev":{"elo":1517,"rank":30,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Was our number 6 on the old board, published here at 262,144 context. Arena and Alibaba both now identify the current build as the 3.7-Max release, which Alibaba lists at 2.50 / 7.50 list with a limited-time 50 percent discount.","source_urls":"Alibaba Cloud Model Studio pricing (alibabacloud.com/product/modelstudio); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#qwen3-max"},{"slug":"gpt-5-5","name":"GPT-5.5","vendor":"OpenAI","status":"legacy","tier":null,"licence":"Proprietary","context_window_text":"-","max_output_text":"-","price_in_text":"5.00 (cached 0.50)","price_out_text":"30.00","modality_text":"text in, text out","arena_webdev":{"elo":1508,"rank":33,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"This is the row whose price aggregators and Arena wrongly carried onto GPT-5.6 Sol (see the warning box above).","source_urls":"OpenAI pricing page (openai.com/api/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#gpt-5-5"},{"slug":"claude-opus-4-5","name":"Claude Opus 4.5","vendor":"Anthropic","status":"legacy","tier":null,"licence":"Proprietary","context_window_text":"200,000","max_output_text":"-","price_in_text":"5.00","price_out_text":"25.00","modality_text":"text and image in, text out","arena_webdev":{"elo":1468,"rank":42,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Was our index leader at 89.10 under the old, single merged board. Still purchasable. Sits below Opus 4.8, 4.7 and 4.6, all three of which the vendor itself files as legacy, which is why the old board was three generations behind, not one. Arena also lists a high-effort (32k) variant separately: 1494 Elo, rank 35.","source_urls":"Anthropic pricing/models page (anthropic.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#claude-opus-4-5"},{"slug":"gemini-3-pro","name":"Gemini 3 Pro","vendor":"Google","status":"legacy","tier":null,"licence":"Proprietary","context_window_text":"1,000,000","max_output_text":"-","price_in_text":"2.00","price_out_text":"12.00","modality_text":"text and image in, text out","arena_webdev":{"elo":1438,"rank":52,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Was our number 3 on the old board, and the row our previous \"widest context\" callout used to rest on.","source_urls":"Google AI pricing page (ai.google.dev/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#gemini-3-pro"},{"slug":"claude-sonnet-4-5","name":"Claude Sonnet 4.5","vendor":"Anthropic","status":"legacy","tier":null,"licence":"Proprietary","context_window_text":"200,000","max_output_text":"-","price_in_text":"3.00","price_out_text":"15.00","modality_text":"text and image in, text out","arena_webdev":{"elo":1386,"rank":74,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Was our number 4 on the old, single merged board.","source_urls":"Anthropic pricing/models page (anthropic.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#claude-sonnet-4-5"},{"slug":"deepseek-v3-2","name":"DeepSeek V3.2","vendor":"DeepSeek","status":"legacy","tier":null,"licence":"MIT","context_window_text":"128,000 as we published it","max_output_text":"-","price_in_text":"0.28","price_out_text":"0.42","modality_text":"text in, text out","arena_webdev":{"elo":1360,"rank":82,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Was our number 7 on the old board, listed on Arena as deepseek-v3.2-thinking. We published 0.28 / 0.42 for it, and 0.42 matches no DeepSeek rate, current or off-peak, that we can find on the vendor's pricing page.","source_urls":"DeepSeek API pricing page (api-docs.deepseek.com/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#deepseek-v3-2"},{"slug":"gpt-5-1","name":"GPT-5.1","vendor":"OpenAI","status":"legacy","tier":null,"licence":"Proprietary","context_window_text":"400,000","max_output_text":"-","price_in_text":"1.25","price_out_text":"10.00","modality_text":"text and image in, text out","arena_webdev":{"elo":1341,"rank":89,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Was our number 2 on the old, single merged board.","source_urls":"OpenAI pricing page (openai.com/api/pricing); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#gpt-5-1"},{"slug":"grok-4","name":"Grok 4","vendor":"xAI","status":"legacy","tier":null,"licence":"Proprietary","context_window_text":"256,000","max_output_text":"-","price_in_text":"3.00","price_out_text":"15.00","modality_text":"text in, text out","arena_webdev":{"elo":null,"rank":null,"votes":null,"preliminary":false},"bench_aa_index_v4_1_1":null,"bench_terminal_bench_v2_1":null,"release_note":"Was our number 5 on the old board. Not present in Arena's published WebDev list under this label.","source_urls":"xAI models page (docs.x.ai); Arena WebDev leaderboard (arena.ai/leaderboard/code/webdev), board dated 21 Aug 2026","page_url":"https://www.llm-tier.com/leaderboard/llms#grok-4"}]}}