{"source":"BenchGecko","url":"https://benchgecko.ai/model/llama-3-1-nemotron-ultra-253b-v1","as_of":"2026-04-14","license":"BenchGecko collected data (prices, provider offers, Gecko Tests) is CC BY 4.0 · https://creativecommons.org/licenses/by/4.0/. Benchmark scores belong to their original publishers (see sources) and are aggregated with attribution. Attribution required: \"Source: BenchGecko\" with a link.","attribution":"Source: BenchGecko · https://benchgecko.ai/model/llama-3-1-nemotron-ultra-253b-v1","cite":"Llama 3.1 Nemotron Ultra 253B v1 · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-14. https://benchgecko.ai/model/llama-3-1-nemotron-ultra-253b-v1","slug":"llama-3-1-nemotron-ultra-253b-v1","name":"Llama 3.1 Nemotron Ultra 253B v1","provider":{"name":"NVIDIA","slug":"nvidia"},"model_type":"text","release_date":"2025-04-08","is_open_source":true,"status":"active","context_window":131072,"description":"Llama-3.1-Nemotron-Ultra-253B-v1 is a large language model (LLM) optimized for advanced reasoning, human-interactive chat, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta’s Llama-3.1-405B-Instruct, it has been significantly customized using Neural...","benchgecko_score":null,"avg_score":0,"list_price":{"input_usd_per_m":0.6,"output_usd_per_m":1.8,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":0.6,"output":1.8},"providers":[],"cheapest_provider":null,"providers_source":null,"scores":[{"benchmark":"Chatbot Arena Elo — Overall","benchmark_slug":"arena-elo-overall","score":1346.81,"unit":"elo","category":"arena","source":"LMArena","source_url":"https://lmarena.ai/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/arena-elo-overall"},{"benchmark":"Artificial Analysis — Quality Index","benchmark_slug":"aa-quality-index","score":15.02,"unit":"index","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-quality-index"},{"benchmark":"Artificial Analysis — Coding Index","benchmark_slug":"aa-coding-index","score":13.09,"unit":"index","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-coding-index"},{"benchmark":"Artificial Analysis — Agentic Index","benchmark_slug":"aa-agentic-index","score":3.8,"unit":"index","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-agentic-index"}],"gecko_tests":null,"links":{"page":"https://benchgecko.ai/model/llama-3-1-nemotron-ultra-253b-v1","json":"https://benchgecko.ai/api/v1/models/llama-3-1-nemotron-ultra-253b-v1","price_history":"https://benchgecko.ai/api/v1/price-history/llama-3-1-nemotron-ultra-253b-v1","provider_prices":null}}