{"source":"BenchGecko","url":"https://benchgecko.ai/model/llama-4-maverick","as_of":"2026-10-05","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-4-maverick","cite":"Llama 4 Maverick · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/llama-4-maverick","slug":"llama-4-maverick","name":"Llama 4 Maverick","provider":{"name":"Meta","slug":"meta"},"model_type":"multimodal","release_date":"2025-04-05","is_open_source":true,"status":"active","context_window":1048576,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","benchgecko_score":{"value":22.1,"rank":275,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":22.1,"list_price":{"input_usd_per_m":0.1875,"output_usd_per_m":0.6525,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":0.1875,"output":0.6525},"providers":[{"provider":"DigitalOcean","endpoint":"digitalocean","quantization":null,"context_tokens":128000,"input_usd_per_m":0.1875,"output_usd_per_m":0.6525,"cache_read_usd_per_m":null,"uptime_1d_pct":99.89,"as_of":"2026-10-05"},{"provider":"Novita","endpoint":"novita/fp8","quantization":"fp8","context_tokens":1048576,"input_usd_per_m":0.27,"output_usd_per_m":0.85,"cache_read_usd_per_m":null,"uptime_1d_pct":99.37,"as_of":"2026-10-05"},{"provider":"Google","endpoint":"google-vertex/us-east5","quantization":null,"context_tokens":524288,"input_usd_per_m":0.35,"output_usd_per_m":1.15,"cache_read_usd_per_m":null,"uptime_1d_pct":null,"as_of":"2026-10-05"},{"provider":"Parasail","endpoint":"parasail/fp8","quantization":"fp8","context_tokens":524288,"input_usd_per_m":0.35,"output_usd_per_m":1,"cache_read_usd_per_m":0.17,"uptime_1d_pct":99.9,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"DigitalOcean","endpoint":"digitalocean","quantization":null,"context_tokens":128000,"input_usd_per_m":0.1875,"output_usd_per_m":0.6525,"cache_read_usd_per_m":null,"uptime_1d_pct":99.89,"as_of":"2026-10-05"},"providers_source":"OpenRouter endpoints API, one row per provider, refreshed daily","scores":[{"benchmark":"MATH level 5","benchmark_slug":"math-level-5","score":73.02,"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":"Artificial Analysis · GPQA Diamond","benchmark_slug":"aa-gpqa-diamond","score":67.1,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-gpqa-diamond"},{"benchmark":"Artificial Analysis · MMMU Pro","benchmark_slug":"aa-mmmu-pro","score":62.1,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-mmmu-pro"},{"benchmark":"Lech Mazur Writing","benchmark_slug":"lech-mazur-writing","score":62,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/lech-mazur-writing"},{"benchmark":"GPQA diamond","benchmark_slug":"gpqa-diamond","score":55.98,"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":"GeoBench","benchmark_slug":"geobench","score":52,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/geobench"},{"benchmark":"Artificial Analysis · Long Context Reasoning","benchmark_slug":"aa-long-context-reasoning","score":50,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-long-context-reasoning"},{"benchmark":"Fiction.LiveBench","benchmark_slug":"fiction-livebench","score":46.2,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/fiction-livebench"},{"benchmark":"Artificial Analysis · IFBench","benchmark_slug":"aa-ifbench","score":43,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-ifbench"},{"benchmark":"Dtbench","benchmark_slug":"dtbench","score":36.45,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/dtbench"},{"benchmark":"Artificial Analysis · SciCode","benchmark_slug":"aa-scicode","score":31.7,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-scicode"},{"benchmark":"WeirdML","benchmark_slug":"weirdml","score":24.47,"unit":"%","category":"coding","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/weirdml"},{"benchmark":"SWE-Bench Verified (Bash Only)","benchmark_slug":"swe-bench-verified-bash-only","score":21.04,"unit":"%","category":"coding","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/swe-bench-verified-bash-only"},{"benchmark":"OTIS Mock AIME 2024-2025","benchmark_slug":"otis-mock-aime-2024-2025","score":20.48,"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"},{"benchmark":"Lmca","benchmark_slug":"lmca","score":18.67,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/lmca"},{"benchmark":"Artificial Analysis · tau2-Bench Telecom","benchmark_slug":"aa-tau2-bench","score":17.8,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-tau2-bench"},{"benchmark":"Artificial Analysis — Coding Index","benchmark_slug":"aa-coding-index","score":16.28,"unit":"index","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-coding-index"},{"benchmark":"Aider polyglot","benchmark_slug":"aider-polyglot","score":15.6,"unit":"%","category":"coding","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/aider-polyglot"},{"benchmark":"SimpleBench","benchmark_slug":"simplebench","score":13.24,"unit":"%","category":"reasoning","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/simplebench"},{"benchmark":"Artificial Analysis — Quality Index","benchmark_slug":"aa-quality-index","score":9.99,"unit":"index","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-quality-index"},{"benchmark":"Artificial Analysis · Terminal-Bench Hard","benchmark_slug":"aa-terminal-bench-hard","score":6.8,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-terminal-bench-hard"},{"benchmark":"Artificial Analysis · Humanity's Last Exam","benchmark_slug":"aa-humanitys-last-exam","score":4.9,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-humanitys-last-exam"},{"benchmark":"ARC-AGI","benchmark_slug":"arc-agi","score":4.38,"unit":"%","category":"reasoning","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/arc-agi"},{"benchmark":"Artificial Analysis — Agentic Index","benchmark_slug":"aa-agentic-index","score":1.31,"unit":"index","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-agentic-index"},{"benchmark":"FrontierMath-2025-02-28-Private","benchmark_slug":"frontiermath-2025-02-28-private","score":1.21,"unit":"%","category":"math","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/frontiermath-2025-02-28-private"},{"benchmark":"HLE","benchmark_slug":"hle","score":0.92,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/hle"},{"benchmark":"ARC-AGI-2","benchmark_slug":"arc-agi-2","score":0.1,"unit":"%","category":"reasoning","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/arc-agi-2"},{"benchmark":"Artificial Analysis · CritPt","benchmark_slug":"aa-critpt","score":0,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-critpt"},{"benchmark":"Artificial Analysis · GDPval","benchmark_slug":"aa-gdpval","score":0,"unit":"%","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-gdpval"}],"gecko_tests":{"gecko_score":20,"rank":12,"tests_taken":3,"tests":[{"test":"who-are-you","name":"Who Are You","grade":"E","value":50,"verdict":"Sometimes says it is Google or OpenAI","url":"https://benchgecko.ai/gecko-tests/who-are-you"},{"test":"world-map","name":"World Map","grade":"E","value":79.2,"verdict":"79.2% of the map right","url":"https://benchgecko.ai/gecko-tests/world-map"},{"test":"tokenizer-tax","name":"Tokenizer Tax","grade":"B","value":55.9,"verdict":"44% more tokens outside English","url":"https://benchgecko.ai/gecko-tests/tokenizer-tax"}],"scorecard_url":"https://benchgecko.ai/gecko-tests/scorecard"},"links":{"page":"https://benchgecko.ai/model/llama-4-maverick","json":"https://benchgecko.ai/api/v1/models/llama-4-maverick","price_history":"https://benchgecko.ai/api/v1/price-history/llama-4-maverick","provider_prices":"https://benchgecko.ai/pricing/arbitrage/llama-4-maverick"}}