{"source":"BenchGecko","url":"https://benchgecko.ai/model/claude-opus-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/claude-opus-4-5","cite":"Claude Opus 4.5 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/claude-opus-4-5","slug":"claude-opus-4-5","name":"Claude Opus 4.5","provider":{"name":"Anthropic","slug":"anthropic"},"model_type":"multimodal","release_date":"2025-11-24","is_open_source":false,"status":"active","context_window":200000,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","benchgecko_score":{"value":59,"rank":91,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":59,"list_price":{"input_usd_per_m":5,"output_usd_per_m":25,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":5,"output":25},"providers":[{"provider":"Amazon Bedrock","endpoint":"amazon-bedrock","quantization":null,"context_tokens":200000,"input_usd_per_m":5,"output_usd_per_m":25,"cache_read_usd_per_m":0.5,"uptime_1d_pct":99.98,"as_of":"2026-10-05"},{"provider":"Anthropic","endpoint":"anthropic","quantization":null,"context_tokens":200000,"input_usd_per_m":5,"output_usd_per_m":25,"cache_read_usd_per_m":0.5,"uptime_1d_pct":100,"as_of":"2026-10-05"},{"provider":"Azure","endpoint":"azure/global","quantization":null,"context_tokens":200000,"input_usd_per_m":5,"output_usd_per_m":25,"cache_read_usd_per_m":0.5,"uptime_1d_pct":null,"as_of":"2026-10-05"},{"provider":"Claude Platform on AWS","endpoint":"claude-on-aws","quantization":null,"context_tokens":200000,"input_usd_per_m":5,"output_usd_per_m":25,"cache_read_usd_per_m":0.5,"uptime_1d_pct":100,"as_of":"2026-10-05"},{"provider":"Google","endpoint":"google-vertex/global","quantization":null,"context_tokens":200000,"input_usd_per_m":5,"output_usd_per_m":25,"cache_read_usd_per_m":0.5,"uptime_1d_pct":100,"as_of":"2026-10-05"},{"provider":"Amazon Bedrock","endpoint":"amazon-bedrock/eu-west-1","quantization":null,"context_tokens":200000,"input_usd_per_m":5.5,"output_usd_per_m":27.5,"cache_read_usd_per_m":0.55,"uptime_1d_pct":100,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"Amazon Bedrock","endpoint":"amazon-bedrock","quantization":null,"context_tokens":200000,"input_usd_per_m":5,"output_usd_per_m":25,"cache_read_usd_per_m":0.5,"uptime_1d_pct":99.98,"as_of":"2026-10-05"},"providers_source":"OpenRouter endpoints API, one row per provider, refreshed daily","scores":[{"benchmark":"Chatbot Arena Elo — Overall","benchmark_slug":"arena-elo-overall","score":1469.77,"unit":"elo","category":"arena","source":"LMArena","source_url":"https://lmarena.ai/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/arena-elo-overall"},{"benchmark":"Chatbot Arena Elo — Coding","benchmark_slug":"arena-elo-coding","score":1468.46,"unit":"elo","category":"arena","source":"LMArena","source_url":"https://lmarena.ai/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/arena-elo-coding"},{"benchmark":"OTIS Mock AIME 2024-2025","benchmark_slug":"otis-mock-aime-2024-2025","score":86.1,"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":83.12,"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":"Cybench","benchmark_slug":"cybench","score":82,"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":"GPQA diamond","benchmark_slug":"gpqa-diamond","score":81.4,"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":80,"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":"SWE-Bench verified","benchmark_slug":"swe-bench-verified","score":76.65,"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":"GeoBench","benchmark_slug":"geobench","score":75,"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":"Metr Time Horizons","benchmark_slug":"metr-time-horizons","score":74.97,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/metr-time-horizons"},{"benchmark":"SWE-Bench Verified (Bash Only)","benchmark_slug":"swe-bench-verified-bash-only","score":74.4,"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":"OSWorld","benchmark_slug":"osworld","score":66.3,"unit":"%","category":"agentic","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/osworld"},{"benchmark":"WeirdML","benchmark_slug":"weirdml","score":63.74,"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":"Terminal Bench","benchmark_slug":"terminal-bench","score":63.1,"unit":"%","category":"coding","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/terminal-bench"},{"benchmark":"MCP Atlas","benchmark_slug":"seal-mcp-atlas","score":62.3,"unit":"%","category":"agentic","source":"Scale SEAL leaderboards","source_url":"https://scale.com/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/seal-mcp-atlas"},{"benchmark":"DeepResearch Bench","benchmark_slug":"deepresearch-bench","score":54.8,"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":54.4,"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":"Lmca","benchmark_slug":"lmca","score":52.31,"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":"SWE-Bench Pro (Public)","benchmark_slug":"seal-swe-bench-pro-public","score":45.89,"unit":"%","category":"agentic","source":"Scale SEAL leaderboards","source_url":"https://scale.com/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/seal-swe-bench-pro-public"},{"benchmark":"Gdpval","benchmark_slug":"gdpval","score":45.5,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/gdpval"},{"benchmark":"Balrog","benchmark_slug":"balrog","score":43.5,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/balrog"},{"benchmark":"SimpleQA Verified","benchmark_slug":"simpleqa-verified","score":41.8,"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":"ARC-AGI-2","benchmark_slug":"arc-agi-2","score":37.64,"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":"Proofbench","benchmark_slug":"proofbench","score":36,"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-Tiers-1-3-v2-Private","benchmark_slug":"frontiermath-tiers-1-3-v2-private","score":34.39,"unit":"%","category":"math","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/frontiermath-tiers-1-3-v2-private"},{"benchmark":"GSO-Bench","benchmark_slug":"gso-bench","score":26.5,"unit":"%","category":"coding","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/gso-bench"},{"benchmark":"SWE-Bench Pro (Private)","benchmark_slug":"seal-swe-bench-pro-private","score":23.44,"unit":"%","category":"agentic","source":"Scale SEAL leaderboards","source_url":"https://scale.com/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/seal-swe-bench-pro-private"},{"benchmark":"SciPredict","benchmark_slug":"seal-scipredict","score":23.05,"unit":"%","category":"knowledge","source":"Scale SEAL leaderboards","source_url":"https://scale.com/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/seal-scipredict"},{"benchmark":"HLE","benchmark_slug":"hle","score":21.43,"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":"Cl Bench","benchmark_slug":"cl-bench","score":21.1,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/cl-bench"},{"benchmark":"FrontierMath-2025-02-28-Private","benchmark_slug":"frontiermath-2025-02-28-private","score":20.69,"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":"APEX-Agents","benchmark_slug":"apex-agents","score":18.4,"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":"PostTrainBench","benchmark_slug":"posttrainbench","score":17.29,"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":"Ebr Bench","benchmark_slug":"ebr-bench","score":14.29,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/ebr-bench"},{"benchmark":"Mystery Game Puzzles","benchmark_slug":"mystery-game-puzzles","score":14.08,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/mystery-game-puzzles"},{"benchmark":"Fortress","benchmark_slug":"seal-fortress","score":13.56,"unit":"%","category":"safety","source":"Scale SEAL leaderboards","source_url":"https://scale.com/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/seal-fortress"},{"benchmark":"Chess Puzzles","benchmark_slug":"chess-puzzles","score":12,"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":"VPCT","benchmark_slug":"vpct","score":10,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/vpct"},{"benchmark":"FrontierMath-Tier-4-v2-Private","benchmark_slug":"frontiermath-tier-4-v2-private","score":4.88,"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":"FrontierMath-Tier-4-2025-07-01-Private","benchmark_slug":"frontiermath-tier-4-2025-07-01-private","score":4.17,"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"},{"benchmark":"Remote Labor Index","benchmark_slug":"remote-labor-index","score":3.75,"unit":"%","category":"general","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/remote-labor-index"},{"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":null,"links":{"page":"https://benchgecko.ai/model/claude-opus-4-5","json":"https://benchgecko.ai/api/v1/models/claude-opus-4-5","price_history":"https://benchgecko.ai/api/v1/price-history/claude-opus-4-5","provider_prices":"https://benchgecko.ai/pricing/arbitrage/claude-opus-4-5"}}