{"source":"BenchGecko","url":"https://benchgecko.ai/model/qwen3-8b","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/qwen3-8b","cite":"Qwen3 8B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/qwen3-8b","slug":"qwen3-8b","name":"Qwen3 8B","provider":{"name":"Alibaba Qwen","slug":"alibaba"},"model_type":"text","release_date":"2025-04-28","is_open_source":true,"status":"active","context_window":131072,"description":"Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math,...","benchgecko_score":{"value":36.3,"rank":215,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":36.3,"list_price":{"input_usd_per_m":0.117,"output_usd_per_m":0.455,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":0.117,"output":0.455},"providers":[{"provider":"Alibaba","endpoint":"alibaba","quantization":null,"context_tokens":131072,"input_usd_per_m":0.117,"output_usd_per_m":0.455,"cache_read_usd_per_m":null,"uptime_1d_pct":99.97,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"Alibaba","endpoint":"alibaba","quantization":null,"context_tokens":131072,"input_usd_per_m":0.117,"output_usd_per_m":0.455,"cache_read_usd_per_m":null,"uptime_1d_pct":99.97,"as_of":"2026-10-05"},"providers_source":"OpenRouter endpoints API, one row per provider, refreshed daily","scores":[{"benchmark":"OpenCompass — IFEval","benchmark_slug":"oc-ifeval","score":85.6,"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":72.1,"unit":"%","category":"knowledge","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-mmlu-pro"},{"benchmark":"OpenCompass — AIME2025","benchmark_slug":"oc-aime2025","score":66.2,"unit":"%","category":"math","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-aime2025"},{"benchmark":"Fiction.LiveBench","benchmark_slug":"fiction-livebench","score":62.1,"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":"OpenCompass — GPQA-Diamond","benchmark_slug":"oc-gpqa-diamond","score":59.7,"unit":"%","category":"knowledge","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-gpqa-diamond"},{"benchmark":"OTIS Mock AIME 2024-2025","benchmark_slug":"otis-mock-aime-2024-2025","score":56.07,"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":"OpenCompass — LiveCodeBenchV6","benchmark_slug":"oc-livecodebenchv6","score":50.1,"unit":"%","category":"coding","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-livecodebenchv6"},{"benchmark":"GPQA diamond","benchmark_slug":"gpqa-diamond","score":42.34,"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":"Dtbench","benchmark_slug":"dtbench","score":32.88,"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":"Lmca","benchmark_slug":"lmca","score":10.38,"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":5.5,"unit":"%","category":"knowledge","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-hle"},{"benchmark":"Chess Puzzles","benchmark_slug":"chess-puzzles","score":0.04,"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"}],"gecko_tests":null,"links":{"page":"https://benchgecko.ai/model/qwen3-8b","json":"https://benchgecko.ai/api/v1/models/qwen3-8b","price_history":"https://benchgecko.ai/api/v1/price-history/qwen3-8b","provider_prices":null}}