{"source":"BenchGecko","url":"https://benchgecko.ai/model/gpt-4-1","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-4-1","cite":"GPT-4.1 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/gpt-4-1","slug":"gpt-4-1","name":"GPT-4.1","provider":{"name":"OpenAI","slug":"openai"},"model_type":"multimodal","release_date":"2025-04-14","is_open_source":false,"status":"active","context_window":1047576,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","benchgecko_score":{"value":37.9,"rank":205,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":37.9,"list_price":{"input_usd_per_m":2,"output_usd_per_m":8,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":2,"output":8},"providers":[{"provider":"Azure","endpoint":"azure","quantization":null,"context_tokens":1047576,"input_usd_per_m":2,"output_usd_per_m":8,"cache_read_usd_per_m":0.5,"uptime_1d_pct":99.99,"as_of":"2026-10-05"},{"provider":"OpenAI","endpoint":"openai","quantization":null,"context_tokens":1047576,"input_usd_per_m":2,"output_usd_per_m":8,"cache_read_usd_per_m":0.5,"uptime_1d_pct":99.98,"as_of":"2026-10-05"},{"provider":"Azure","endpoint":"azure/swedencentral","quantization":null,"context_tokens":1047576,"input_usd_per_m":2.2,"output_usd_per_m":8.8,"cache_read_usd_per_m":0.55,"uptime_1d_pct":99.94,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"Azure","endpoint":"azure","quantization":null,"context_tokens":1047576,"input_usd_per_m":2,"output_usd_per_m":8,"cache_read_usd_per_m":0.5,"uptime_1d_pct":99.99,"as_of":"2026-10-05"},"providers_source":"OpenRouter endpoints API, one row per provider, refreshed daily","scores":[{"benchmark":"HELM — WildBench","benchmark_slug":"helm-wildbench","score":85.4,"unit":"%","category":"reasoning","source":"Stanford HELM","source_url":"https://crfm.stanford.edu/helm/","benchmark_url":"https://benchgecko.ai/benchmark/helm-wildbench"},{"benchmark":"HELM — IFEval","benchmark_slug":"helm-ifeval","score":83.8,"unit":"%","category":"language","source":"Stanford HELM","source_url":"https://crfm.stanford.edu/helm/","benchmark_url":"https://benchgecko.ai/benchmark/helm-ifeval"},{"benchmark":"MATH level 5","benchmark_slug":"math-level-5","score":83.01,"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":"HELM — MMLU-Pro","benchmark_slug":"helm-mmlu-pro","score":81.1,"unit":"%","category":"knowledge","source":"Stanford HELM","source_url":"https://crfm.stanford.edu/helm/","benchmark_url":"https://benchgecko.ai/benchmark/helm-mmlu-pro"},{"benchmark":"GeoBench","benchmark_slug":"geobench","score":72,"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":"HELM — GPQA","benchmark_slug":"helm-gpqa","score":65.9,"unit":"%","category":"knowledge","source":"Stanford HELM","source_url":"https://crfm.stanford.edu/helm/","benchmark_url":"https://benchgecko.ai/benchmark/helm-gpqa"},{"benchmark":"Fiction.LiveBench","benchmark_slug":"fiction-livebench","score":63.9,"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":"GPQA diamond","benchmark_slug":"gpqa-diamond","score":55.89,"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":"Aider polyglot","benchmark_slug":"aider-polyglot","score":52.4,"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":"SWE-Bench verified","benchmark_slug":"swe-bench-verified","score":48.54,"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"},{"benchmark":"Dtbench","benchmark_slug":"dtbench","score":47.12,"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":"HELM — Omni-MATH","benchmark_slug":"helm-omni-math","score":47.1,"unit":"%","category":"math","source":"Stanford HELM","source_url":"https://crfm.stanford.edu/helm/","benchmark_url":"https://benchgecko.ai/benchmark/helm-omni-math"},{"benchmark":"CadEval","benchmark_slug":"cadeval","score":42,"unit":"%","category":"coding","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/cadeval"},{"benchmark":"SWE-Bench Verified (Bash Only)","benchmark_slug":"swe-bench-verified-bash-only","score":39.58,"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":"WeirdML","benchmark_slug":"weirdml","score":39.04,"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":"OTIS Mock AIME 2024-2025","benchmark_slug":"otis-mock-aime-2024-2025","score":38.27,"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":"SimpleQA Verified","benchmark_slug":"simpleqa-verified","score":31.1,"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":"Lmca","benchmark_slug":"lmca","score":30.13,"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":"DeepResearch Bench","benchmark_slug":"deepresearch-bench","score":29.31,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/deepresearch-bench"},{"benchmark":"SimpleBench","benchmark_slug":"simplebench","score":12.4,"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":5.96,"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":"FrontierMath-2025-02-28-Private","benchmark_slug":"frontiermath-2025-02-28-private","score":5.52,"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":"ARC-AGI","benchmark_slug":"arc-agi","score":5.5,"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":"Chess Puzzles","benchmark_slug":"chess-puzzles","score":1.09,"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":"HLE","benchmark_slug":"hle","score":0.63,"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":0.42,"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-Tier-4-2025-07-01-Private","benchmark_slug":"frontiermath-tier-4-2025-07-01-private","score":0.1,"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-4-1","json":"https://benchgecko.ai/api/v1/models/gpt-4-1","price_history":"https://benchgecko.ai/api/v1/price-history/gpt-4-1","provider_prices":"https://benchgecko.ai/pricing/arbitrage/gpt-4-1"}}