{"source":"BenchGecko","url":"https://benchgecko.ai/model/gpt-5-4-pro","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/gpt-5-4-pro","cite":"GPT-5.4 Pro · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/gpt-5-4-pro","slug":"gpt-5-4-pro","name":"GPT-5.4 Pro","provider":{"name":"OpenAI","slug":"openai"},"model_type":"multimodal","release_date":"2026-03-05","is_open_source":false,"status":"active","context_window":1050000,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","benchgecko_score":{"value":80.7,"rank":19,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":80.7,"list_price":{"input_usd_per_m":30,"output_usd_per_m":180,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":30,"output":180},"providers":[{"provider":"OpenAI","endpoint":"openai/flex","quantization":null,"context_tokens":1050000,"input_usd_per_m":15,"output_usd_per_m":90,"cache_read_usd_per_m":null,"uptime_1d_pct":null,"as_of":"2026-10-05"},{"provider":"Azure","endpoint":"azure","quantization":null,"context_tokens":1050000,"input_usd_per_m":30,"output_usd_per_m":180,"cache_read_usd_per_m":null,"uptime_1d_pct":100,"as_of":"2026-10-05"},{"provider":"OpenAI","endpoint":"openai","quantization":null,"context_tokens":1050000,"input_usd_per_m":30,"output_usd_per_m":180,"cache_read_usd_per_m":null,"uptime_1d_pct":100,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"OpenAI","endpoint":"openai/flex","quantization":null,"context_tokens":1050000,"input_usd_per_m":15,"output_usd_per_m":90,"cache_read_usd_per_m":null,"uptime_1d_pct":null,"as_of":"2026-10-05"},"providers_source":"OpenRouter endpoints API, one row per provider, refreshed daily","scores":[{"benchmark":"ARC-AGI","benchmark_slug":"arc-agi","score":94.5,"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":"GPQA diamond","benchmark_slug":"gpqa-diamond","score":92.8,"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-2","benchmark_slug":"arc-agi-2","score":83.33,"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":"FrontierMath-Tiers-1-3-v2-Private","benchmark_slug":"frontiermath-tiers-1-3-v2-private","score":82.46,"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":"SimpleBench","benchmark_slug":"simplebench","score":68.92,"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":"Chess Puzzles","benchmark_slug":"chess-puzzles","score":58.6,"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":"FrontierMath-Tier-4-v2-Private","benchmark_slug":"frontiermath-tier-4-v2-private","score":58.54,"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":"WeirdML","benchmark_slug":"weirdml","score":57.44,"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":"FrontierMath-2025-02-28-Private","benchmark_slug":"frontiermath-2025-02-28-private","score":50,"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":"SimpleQA Verified","benchmark_slug":"simpleqa-verified","score":47.8,"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":"HLE","benchmark_slug":"hle","score":41.51,"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":"FrontierMath-Tier-4-2025-07-01-Private","benchmark_slug":"frontiermath-tier-4-2025-07-01-private","score":37.5,"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-4-2025-07-01-private"}],"gecko_tests":null,"links":{"page":"https://benchgecko.ai/model/gpt-5-4-pro","json":"https://benchgecko.ai/api/v1/models/gpt-5-4-pro","price_history":"https://benchgecko.ai/api/v1/price-history/gpt-5-4-pro","provider_prices":"https://benchgecko.ai/pricing/arbitrage/gpt-5-4-pro"}}