{"source":"BenchGecko","url":"https://benchgecko.ai/model/claude-mythos-preview","as_of":null,"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-mythos-preview","cite":"Claude Mythos Preview · benchmarks, pricing and providers. BenchGecko. https://benchgecko.ai/model/claude-mythos-preview","slug":"claude-mythos-preview","name":"Claude Mythos Preview","provider":{"name":"Anthropic","slug":"anthropic"},"model_type":"text","release_date":"2026-04-07","is_open_source":false,"status":"preview","context_window":1000000,"description":"Anthropic's most capable model · Claude Mythos Preview. Tops SWE-bench Verified (93.9%), GPQA Diamond (94.5%), USAMO (97.6%), and HLE with tools (64.7%). Adaptive thinking at max effort, context up to 1M tokens.","benchgecko_score":{"value":99.8,"rank":2,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":99.8,"list_price":{"input_usd_per_m":null,"output_usd_per_m":null,"source":"Provider list price","as_of":null},"pricing":{"input":null,"output":null},"providers":[],"cheapest_provider":null,"providers_source":null,"scores":[{"benchmark":"USAMO","benchmark_slug":"usamo","score":97.6,"unit":"%","category":"math","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/usamo"},{"benchmark":"GPQA diamond","benchmark_slug":"gpqa-diamond","score":94.5,"unit":"%","category":"knowledge","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/gpqa-diamond"},{"benchmark":"SWE-Bench verified","benchmark_slug":"swe-bench-verified","score":93.9,"unit":"%","category":"coding","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/swe-bench-verified"},{"benchmark":"CharXiv Reasoning (with tools)","benchmark_slug":"charxiv-reasoning-tools","score":93.2,"unit":"%","category":"reasoning","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/charxiv-reasoning-tools"},{"benchmark":"MMMLU","benchmark_slug":"mmmlu","score":92.7,"unit":"%","category":"knowledge","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/mmmlu"},{"benchmark":"SWE-bench Multilingual","benchmark_slug":"swe-bench-multilingual","score":87.3,"unit":"%","category":"coding","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/swe-bench-multilingual"},{"benchmark":"CharXiv Reasoning","benchmark_slug":"charxiv-reasoning","score":86.1,"unit":"%","category":"reasoning","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/charxiv-reasoning"},{"benchmark":"Terminal Bench","benchmark_slug":"terminal-bench","score":82,"unit":"%","category":"coding","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/terminal-bench"},{"benchmark":"GraphWalks BFS 256K-1M","benchmark_slug":"graphwalks-bfs-256k","score":80,"unit":"%","category":"reasoning","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/graphwalks-bfs-256k"},{"benchmark":"OSWorld","benchmark_slug":"osworld","score":79.6,"unit":"%","category":"agentic","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/osworld"},{"benchmark":"SWE-bench Pro","benchmark_slug":"swe-bench-pro","score":77.8,"unit":"%","category":"coding","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/swe-bench-pro"},{"benchmark":"HLE (with tools)","benchmark_slug":"hle-tools","score":64.7,"unit":"%","category":"reasoning","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/hle-tools"},{"benchmark":"SWE-bench Multimodal","benchmark_slug":"swe-bench-multimodal","score":59,"unit":"%","category":"coding","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/swe-bench-multimodal"},{"benchmark":"HLE","benchmark_slug":"hle","score":56.8,"unit":"%","category":"knowledge","source":"Public leaderboard","source_url":null,"benchmark_url":"https://benchgecko.ai/benchmark/hle"}],"gecko_tests":null,"links":{"page":"https://benchgecko.ai/model/claude-mythos-preview","json":"https://benchgecko.ai/api/v1/models/claude-mythos-preview","price_history":"https://benchgecko.ai/api/v1/price-history/claude-mythos-preview","provider_prices":null}}