{"source":"BenchGecko","url":"https://benchgecko.ai/model/qwen3-235b-a22b-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-2507","cite":"Qwen3 235B A22B Instruct 2507 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/qwen3-235b-a22b-2507","slug":"qwen3-235b-a22b-2507","name":"Qwen3 235B A22B Instruct 2507","provider":{"name":"Alibaba Qwen","slug":"alibaba"},"model_type":"text","release_date":"2025-07-21","is_open_source":true,"status":"active","context_window":262144,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","benchgecko_score":{"value":44.9,"rank":172,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":44.9,"list_price":{"input_usd_per_m":0.09,"output_usd_per_m":0.55,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":0.09,"output":0.55},"providers":[{"provider":"GMICloud","endpoint":"gmicloud/fp8","quantization":"fp8","context_tokens":262144,"input_usd_per_m":0.0875,"output_usd_per_m":0.35,"cache_read_usd_per_m":0.0175,"uptime_1d_pct":99.21,"as_of":"2026-10-05"},{"provider":"DeepInfra","endpoint":"deepinfra/fp8","quantization":"fp8","context_tokens":262144,"input_usd_per_m":0.09,"output_usd_per_m":0.55,"cache_read_usd_per_m":null,"uptime_1d_pct":89.15,"as_of":"2026-10-05"},{"provider":"Novita","endpoint":"novita/fp8","quantization":"fp8","context_tokens":131072,"input_usd_per_m":0.09,"output_usd_per_m":0.58,"cache_read_usd_per_m":null,"uptime_1d_pct":95.15,"as_of":"2026-10-05"},{"provider":"Parasail","endpoint":"parasail/fp8","quantization":"fp8","context_tokens":131072,"input_usd_per_m":0.14,"output_usd_per_m":0.8,"cache_read_usd_per_m":0.05,"uptime_1d_pct":99.9,"as_of":"2026-10-05"},{"provider":"Alibaba","endpoint":"alibaba","quantization":null,"context_tokens":131072,"input_usd_per_m":0.1495,"output_usd_per_m":0.598,"cache_read_usd_per_m":null,"uptime_1d_pct":97.8,"as_of":"2026-10-05"},{"provider":"Venice","endpoint":"venice/fp8","quantization":"fp8","context_tokens":128000,"input_usd_per_m":0.15,"output_usd_per_m":0.75,"cache_read_usd_per_m":null,"uptime_1d_pct":88.97,"as_of":"2026-10-05"},{"provider":"Nebius","endpoint":"nebius/fp8","quantization":"fp8","context_tokens":262144,"input_usd_per_m":0.2,"output_usd_per_m":0.6,"cache_read_usd_per_m":null,"uptime_1d_pct":93.31,"as_of":"2026-10-05"},{"provider":"StreamLake","endpoint":"streamlake","quantization":null,"context_tokens":128000,"input_usd_per_m":0.21,"output_usd_per_m":0.84,"cache_read_usd_per_m":null,"uptime_1d_pct":99.39,"as_of":"2026-10-05"},{"provider":"Google","endpoint":"google-vertex/us-south1","quantization":null,"context_tokens":262144,"input_usd_per_m":0.22,"output_usd_per_m":0.88,"cache_read_usd_per_m":null,"uptime_1d_pct":99.82,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"GMICloud","endpoint":"gmicloud/fp8","quantization":"fp8","context_tokens":262144,"input_usd_per_m":0.0875,"output_usd_per_m":0.35,"cache_read_usd_per_m":0.0175,"uptime_1d_pct":99.21,"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":1422.4,"unit":"elo","category":"arena","source":"LMArena","source_url":"https://lmarena.ai/leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/arena-elo-overall"},{"benchmark":"OpenCompass — IFEval","benchmark_slug":"oc-ifeval","score":88.3,"unit":"%","category":"language","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-ifeval"},{"benchmark":"OpenCompass — MMLU-Pro","benchmark_slug":"oc-mmlu-pro","score":79.2,"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":75.5,"unit":"%","category":"knowledge","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-gpqa-diamond"},{"benchmark":"LiveBench — Coding","benchmark_slug":"livebench-coding","score":69.61,"unit":"%","category":"coding","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-coding"},{"benchmark":"OpenCompass — AIME2025","benchmark_slug":"oc-aime2025","score":69.5,"unit":"%","category":"math","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-aime2025"},{"benchmark":"LiveBench — Mathematics","benchmark_slug":"livebench-mathematics","score":68.03,"unit":"%","category":"math","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-mathematics"},{"benchmark":"LiveBench — Language","benchmark_slug":"livebench-language","score":66.07,"unit":"%","category":"language","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-language"},{"benchmark":"Dtbench","benchmark_slug":"dtbench","score":64,"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":"Aider polyglot","benchmark_slug":"aider-polyglot","score":59.6,"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":"LiveBench — Reasoning","benchmark_slug":"livebench-reasoning","score":58.43,"unit":"%","category":"reasoning","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-reasoning"},{"benchmark":"Fiction.LiveBench","benchmark_slug":"fiction-livebench","score":52.9,"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":"LiveBench — Overall","benchmark_slug":"livebench-overall","score":48.84,"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":44.72,"unit":"%","category":"reasoning","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-data-analysis"},{"benchmark":"OpenCompass — LiveCodeBenchV6","benchmark_slug":"oc-livecodebenchv6","score":43,"unit":"%","category":"coding","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-livecodebenchv6"},{"benchmark":"WeirdML","benchmark_slug":"weirdml","score":38.7,"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":"Lmca","benchmark_slug":"lmca","score":27.67,"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":"LiveBench — If","benchmark_slug":"livebench-if","score":21.72,"unit":"%","category":"language","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-if"},{"benchmark":"LiveBench — Agentic Coding","benchmark_slug":"livebench-agentic-coding","score":13.33,"unit":"%","category":"coding","source":"LiveBench","source_url":"https://livebench.ai","benchmark_url":"https://benchgecko.ai/benchmark/livebench-agentic-coding"},{"benchmark":"OpenCompass — HLE","benchmark_slug":"oc-hle","score":12.3,"unit":"%","category":"knowledge","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-hle"},{"benchmark":"ARC-AGI","benchmark_slug":"arc-agi","score":11,"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":"ARC-AGI-2","benchmark_slug":"arc-agi-2","score":1.25,"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"}],"gecko_tests":null,"links":{"page":"https://benchgecko.ai/model/qwen3-235b-a22b-2507","json":"https://benchgecko.ai/api/v1/models/qwen3-235b-a22b-2507","price_history":"https://benchgecko.ai/api/v1/price-history/qwen3-235b-a22b-2507","provider_prices":"https://benchgecko.ai/pricing/arbitrage/qwen3-235b-a22b-2507"}}