{"source":"BenchGecko","url":"https://benchgecko.ai/model/grok-4-5","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/grok-4-5","cite":"Grok 4.5 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/grok-4-5","slug":"grok-4-5","name":"Grok 4.5","provider":{"name":"xAI","slug":"xai"},"model_type":"multimodal","release_date":"2026-07-08","is_open_source":false,"status":"active","context_window":500000,"description":"Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","benchgecko_score":{"value":62.4,"rank":73,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":62.4,"list_price":{"input_usd_per_m":2,"output_usd_per_m":6,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":2,"output":6},"providers":[{"provider":"xAI","endpoint":"xai","quantization":null,"context_tokens":500000,"input_usd_per_m":2,"output_usd_per_m":6,"cache_read_usd_per_m":0.3,"uptime_1d_pct":99.29,"as_of":"2026-10-05"},{"provider":"xAI","endpoint":"xai/zdr","quantization":null,"context_tokens":500000,"input_usd_per_m":2,"output_usd_per_m":6,"cache_read_usd_per_m":0.3,"uptime_1d_pct":99.86,"as_of":"2026-10-05"},{"provider":"xAI","endpoint":"xai/priority","quantization":null,"context_tokens":500000,"input_usd_per_m":4,"output_usd_per_m":12,"cache_read_usd_per_m":0.6,"uptime_1d_pct":null,"as_of":"2026-10-05"},{"provider":"xAI","endpoint":"xai/zdr/priority","quantization":null,"context_tokens":500000,"input_usd_per_m":4,"output_usd_per_m":12,"cache_read_usd_per_m":0.6,"uptime_1d_pct":97.18,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"xAI","endpoint":"xai","quantization":null,"context_tokens":500000,"input_usd_per_m":2,"output_usd_per_m":6,"cache_read_usd_per_m":0.3,"uptime_1d_pct":99.29,"as_of":"2026-10-05"},"providers_source":"OpenRouter endpoints API, one row per provider, refreshed daily","scores":[{"benchmark":"Chatbot Arena Elo — Coding","benchmark_slug":"arena-elo-coding","score":1551.82,"unit":"elo","category":"arena","source":"LMArena","source_url":"https://lmarena.ai/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/arena-elo-coding"},{"benchmark":"Chatbot Arena Elo — Overall","benchmark_slug":"arena-elo-overall","score":1465.79,"unit":"elo","category":"arena","source":"LMArena","source_url":"https://lmarena.ai/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/arena-elo-overall"},{"benchmark":"OTIS Mock AIME 2024-2025","benchmark_slug":"otis-mock-aime-2024-2025","score":97.78,"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":"Dtbench","benchmark_slug":"dtbench","score":94.22,"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":"GPQA diamond","benchmark_slug":"gpqa-diamond","score":91.25,"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":"ARC-AGI","benchmark_slug":"arc-agi","score":87.17,"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":"Surface Evolver Bench","benchmark_slug":"surface-evolver-bench","score":74.38,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/surface-evolver-bench"},{"benchmark":"SimpleBench","benchmark_slug":"simplebench","score":64,"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":"FrontierMath-Tiers-1-3-v2-Private","benchmark_slug":"frontiermath-tiers-1-3-v2-private","score":57.19,"unit":"%","category":"math","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/frontiermath-tiers-1-3-v2-private"},{"benchmark":"APEX-Agents","benchmark_slug":"apex-agents","score":56.2,"unit":"%","category":"agentic","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/apex-agents"},{"benchmark":"Deepswe","benchmark_slug":"deepswe","score":53.76,"unit":"%","category":"coding","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/deepswe"},{"benchmark":"Lmca","benchmark_slug":"lmca","score":53.18,"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":"ARC-AGI-2","benchmark_slug":"arc-agi-2","score":52.64,"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":"SimpleQA Verified","benchmark_slug":"simpleqa-verified","score":48.3,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/simpleqa-verified"},{"benchmark":"WeirdML","benchmark_slug":"weirdml","score":46.43,"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":"Frontiercode","benchmark_slug":"frontiercode","score":42.44,"unit":"%","category":"coding","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/frontiercode"},{"benchmark":"Chess Puzzles","benchmark_slug":"chess-puzzles","score":32.66,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/chess-puzzles"},{"benchmark":"Proofbench","benchmark_slug":"proofbench","score":31,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/proofbench"},{"benchmark":"FrontierMath-Tier-4-v2-Private","benchmark_slug":"frontiermath-tier-4-v2-private","score":24.39,"unit":"%","category":"math","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/frontiermath-tier-4-v2-private"},{"benchmark":"PostTrainBench","benchmark_slug":"posttrainbench","score":23.45,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/posttrainbench"},{"benchmark":"Furniture Assembly","benchmark_slug":"furniture-assembly","score":0,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/furniture-assembly"}],"gecko_tests":{"gecko_score":null,"rank":null,"tests_taken":2,"tests":[{"test":"who-are-you","name":"Who Are You","grade":"B","value":100,"verdict":"Knows who made it","url":"https://benchgecko.ai/gecko-tests/who-are-you"},{"test":"tokenizer-tax","name":"Tokenizer Tax","grade":"C","value":49.6,"verdict":"50% 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/grok-4-5","json":"https://benchgecko.ai/api/v1/models/grok-4-5","price_history":"https://benchgecko.ai/api/v1/price-history/grok-4-5","provider_prices":"https://benchgecko.ai/pricing/arbitrage/grok-4-5"}}