{"source":"BenchGecko","url":"https://benchgecko.ai/model/qwen3-235b-a22b-thinking-2507","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/qwen3-235b-a22b-thinking-2507","cite":"Qwen3 235B A22B Thinking 2507 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/qwen3-235b-a22b-thinking-2507","slug":"qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507","provider":{"name":"Alibaba Qwen","slug":"alibaba"},"model_type":"text","release_date":"2025-07-25","is_open_source":true,"status":"active","context_window":131072,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","benchgecko_score":{"value":55.3,"rank":114,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":55.3,"list_price":{"input_usd_per_m":0.23,"output_usd_per_m":2.3,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":0.23,"output":2.3},"providers":[{"provider":"Alibaba","endpoint":"alibaba","quantization":null,"context_tokens":131072,"input_usd_per_m":0.23,"output_usd_per_m":2.3,"cache_read_usd_per_m":null,"uptime_1d_pct":99.56,"as_of":"2026-10-05"},{"provider":"Novita","endpoint":"novita/fp8","quantization":"fp8","context_tokens":131072,"input_usd_per_m":0.3,"output_usd_per_m":3,"cache_read_usd_per_m":null,"uptime_1d_pct":100,"as_of":"2026-10-05"},{"provider":"Venice","endpoint":"venice/fp8","quantization":"fp8","context_tokens":128000,"input_usd_per_m":0.45,"output_usd_per_m":3.5,"cache_read_usd_per_m":null,"uptime_1d_pct":100,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"Alibaba","endpoint":"alibaba","quantization":null,"context_tokens":131072,"input_usd_per_m":0.23,"output_usd_per_m":2.3,"cache_read_usd_per_m":null,"uptime_1d_pct":99.56,"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":1399.99,"unit":"elo","category":"arena","source":"LMArena","source_url":"https://lmarena.ai/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/arena-elo-overall"},{"benchmark":"OpenCompass — AIME2025","benchmark_slug":"oc-aime2025","score":90.9,"unit":"%","category":"math","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-aime2025"},{"benchmark":"OpenCompass — IFEval","benchmark_slug":"oc-ifeval","score":87.8,"unit":"%","category":"language","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-ifeval"},{"benchmark":"OTIS Mock AIME 2024-2025","benchmark_slug":"otis-mock-aime-2024-2025","score":86.65,"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":"Lech Mazur Writing","benchmark_slug":"lech-mazur-writing","score":84.95,"unit":"%","category":"knowledge","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/lech-mazur-writing"},{"benchmark":"OpenCompass — MMLU-Pro","benchmark_slug":"oc-mmlu-pro","score":83.5,"unit":"%","category":"knowledge","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-mmlu-pro"},{"benchmark":"OpenCompass — GPQA-Diamond","benchmark_slug":"oc-gpqa-diamond","score":79.8,"unit":"%","category":"knowledge","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-gpqa-diamond"},{"benchmark":"Fiction.LiveBench","benchmark_slug":"fiction-livebench","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/fiction-livebench"},{"benchmark":"GPQA diamond","benchmark_slug":"gpqa-diamond","score":73.4,"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":"LiveBench — Mathematics","benchmark_slug":"livebench-mathematics","score":73.39,"unit":"%","category":"math","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-mathematics"},{"benchmark":"OpenCompass — LiveCodeBenchV6","benchmark_slug":"oc-livecodebenchv6","score":70.6,"unit":"%","category":"coding","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-livecodebenchv6"},{"benchmark":"LiveBench — Language","benchmark_slug":"livebench-language","score":69.52,"unit":"%","category":"language","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-language"},{"benchmark":"LiveBench — Coding","benchmark_slug":"livebench-coding","score":68.97,"unit":"%","category":"coding","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-coding"},{"benchmark":"Dtbench","benchmark_slug":"dtbench","score":67.12,"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":"LiveBench — Reasoning","benchmark_slug":"livebench-reasoning","score":59.4,"unit":"%","category":"reasoning","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-reasoning"},{"benchmark":"LiveBench — Overall","benchmark_slug":"livebench-overall","score":52.97,"unit":"%","category":"knowledge","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-overall"},{"benchmark":"LiveBench — Data Analysis","benchmark_slug":"livebench-data-analysis","score":52.18,"unit":"%","category":"reasoning","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-data-analysis"},{"benchmark":"WeirdML","benchmark_slug":"weirdml","score":41.04,"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":"LiveBench — If","benchmark_slug":"livebench-if","score":40.64,"unit":"%","category":"language","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-if"},{"benchmark":"SimpleQA Verified","benchmark_slug":"simpleqa-verified","score":40.44,"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":34.48,"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":"OpenCompass — HLE","benchmark_slug":"oc-hle","score":18.5,"unit":"%","category":"knowledge","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-hle"},{"benchmark":"FrontierMath-2025-02-28-Private","benchmark_slug":"frontiermath-2025-02-28-private","score":14.88,"unit":"%","category":"math","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/frontiermath-2025-02-28-private"},{"benchmark":"Chess Puzzles","benchmark_slug":"chess-puzzles","score":7.41,"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":"LiveBench — Agentic Coding","benchmark_slug":"livebench-agentic-coding","score":6.67,"unit":"%","category":"coding","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-agentic-coding"},{"benchmark":"Mystery Game Puzzles","benchmark_slug":"mystery-game-puzzles","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/mystery-game-puzzles"},{"benchmark":"FrontierMath-Tier-4-2025-07-01-Private","benchmark_slug":"frontiermath-tier-4-2025-07-01-private","score":0,"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/qwen3-235b-a22b-thinking-2507","json":"https://benchgecko.ai/api/v1/models/qwen3-235b-a22b-thinking-2507","price_history":"https://benchgecko.ai/api/v1/price-history/qwen3-235b-a22b-thinking-2507","provider_prices":"https://benchgecko.ai/pricing/arbitrage/qwen3-235b-a22b-thinking-2507"}}