{"source":"BenchGecko","url":"https://benchgecko.ai/model/llama-3-70b-instruct","as_of":"2026-05-03","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-3-70b-instruct","cite":"Llama 3 70B Instruct · benchmarks, pricing and providers. BenchGecko, data as of 2026-05-03. https://benchgecko.ai/model/llama-3-70b-instruct","slug":"llama-3-70b-instruct","name":"Llama 3 70B Instruct","provider":{"name":"Meta","slug":"meta"},"model_type":"text","release_date":"2024-04-18","is_open_source":true,"status":"active","context_window":8192,"description":"Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...","benchgecko_score":{"value":30.6,"rank":244,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":30.6,"list_price":{"input_usd_per_m":0.51,"output_usd_per_m":0.74,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":0.51,"output":0.74},"providers":[],"cheapest_provider":null,"providers_source":null,"scores":[{"benchmark":"Chatbot Arena Elo — Overall","benchmark_slug":"arena-elo-overall","score":1275.13,"unit":"elo","category":"arena","source":"LMArena","source_url":"https://lmarena.ai/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/arena-elo-overall"},{"benchmark":"MMLU","benchmark_slug":"mmlu","score":72.4,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/mmlu"},{"benchmark":"Winogrande","benchmark_slug":"winogrande","score":67,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/winogrande"},{"benchmark":"CMMLU","benchmark_slug":"cmmlu","score":36.85,"unit":"%","category":"knowledge","source":"Published CJK benchmark suites","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/cmmlu"},{"benchmark":"OpenBookQA","benchmark_slug":"openbookqa","score":30.13,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/openbookqa"},{"benchmark":"MATH level 5","benchmark_slug":"math-level-5","score":22.55,"unit":"%","category":"math","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/math-level-5"},{"benchmark":"GPQA diamond","benchmark_slug":"gpqa-diamond","score":20.75,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/gpqa-diamond"},{"benchmark":"Cybench","benchmark_slug":"cybench","score":5,"unit":"%","category":"coding","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/cybench"},{"benchmark":"OTIS Mock AIME 2024-2025","benchmark_slug":"otis-mock-aime-2024-2025","score":4.21,"unit":"%","category":"math","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/otis-mock-aime-2024-2025"}],"gecko_tests":null,"links":{"page":"https://benchgecko.ai/model/llama-3-70b-instruct","json":"https://benchgecko.ai/api/v1/models/llama-3-70b-instruct","price_history":"https://benchgecko.ai/api/v1/price-history/llama-3-70b-instruct","provider_prices":null}}