{"source":"BenchGecko","url":"https://benchgecko.ai/model/gemma-3-27b-it","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/gemma-3-27b-it","cite":"Gemma 3 27B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/gemma-3-27b-it","slug":"gemma-3-27b-it","name":"Gemma 3 27B","provider":{"name":"Google DeepMind","slug":"google"},"model_type":"multimodal","release_date":"2025-03-12","is_open_source":true,"status":"active","context_window":131072,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","benchgecko_score":{"value":22.7,"rank":272,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":22.7,"list_price":{"input_usd_per_m":0.08,"output_usd_per_m":0.45,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":0.08,"output":0.45},"providers":[{"provider":"DeepInfra","endpoint":"deepinfra/fp8","quantization":"fp8","context_tokens":131072,"input_usd_per_m":0.08,"output_usd_per_m":0.16,"cache_read_usd_per_m":null,"uptime_1d_pct":99.43,"as_of":"2026-10-05"},{"provider":"Parasail","endpoint":"parasail/fp8","quantization":"fp8","context_tokens":131072,"input_usd_per_m":0.08,"output_usd_per_m":0.45,"cache_read_usd_per_m":0.04,"uptime_1d_pct":99.94,"as_of":"2026-10-05"},{"provider":"Nebius","endpoint":"nebius/fp8","quantization":"fp8","context_tokens":110000,"input_usd_per_m":0.1,"output_usd_per_m":0.3,"cache_read_usd_per_m":null,"uptime_1d_pct":92.75,"as_of":"2026-10-05"},{"provider":"Novita","endpoint":"novita/bf16","quantization":"bf16","context_tokens":98304,"input_usd_per_m":0.119,"output_usd_per_m":0.2,"cache_read_usd_per_m":null,"uptime_1d_pct":95.7,"as_of":"2026-10-05"}],"cheapest_provider":{"provider":"DeepInfra","endpoint":"deepinfra/fp8","quantization":"fp8","context_tokens":131072,"input_usd_per_m":0.08,"output_usd_per_m":0.16,"cache_read_usd_per_m":null,"uptime_1d_pct":99.43,"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":1365.39,"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":81,"unit":"%","category":"language","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-ifeval"},{"benchmark":"Lech Mazur Writing","benchmark_slug":"lech-mazur-writing","score":79.9,"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":"MATH level 5","benchmark_slug":"math-level-5","score":74.04,"unit":"%","category":"math","source":"Epoch AI Benchmarking Hub","source_url":"https://epoch.ai/data/ai-benchmarking-dashboard","benchmark_url":"https://benchgecko.ai/benchmark/math-level-5"},{"benchmark":"OpenCompass — MMLU-Pro","benchmark_slug":"oc-mmlu-pro","score":67.8,"unit":"%","category":"knowledge","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-mmlu-pro"},{"benchmark":"GeoBench","benchmark_slug":"geobench","score":52,"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":"OpenCompass — GPQA-Diamond","benchmark_slug":"oc-gpqa-diamond","score":46.3,"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":33.3,"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":31.82,"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":"OpenCompass — LiveCodeBenchV6","benchmark_slug":"oc-livecodebenchv6","score":30.8,"unit":"%","category":"coding","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-livecodebenchv6"},{"benchmark":"OTIS Mock AIME 2024-2025","benchmark_slug":"otis-mock-aime-2024-2025","score":22.42,"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 — AIME2025","benchmark_slug":"oc-aime2025","score":22.4,"unit":"%","category":"math","source":"OpenCompass","source_url":"https://rank.opencompass.org.cn","benchmark_url":"https://benchgecko.ai/benchmark/oc-aime2025"},{"benchmark":"Dtbench","benchmark_slug":"dtbench","score":20.88,"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":14.45,"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":"Aider polyglot","benchmark_slug":"aider-polyglot","score":4.9,"unit":"%","category":"coding","source":"Aider leaderboards","source_url":"https://aider.chat/docs/leaderboards/","benchmark_url":"https://benchgecko.ai/benchmark/aider-polyglot"},{"benchmark":"OpenCompass — HLE","benchmark_slug":"oc-hle","score":4.2,"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,"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/gemma-3-27b-it","json":"https://benchgecko.ai/api/v1/models/gemma-3-27b-it","price_history":"https://benchgecko.ai/api/v1/price-history/gemma-3-27b-it","provider_prices":"https://benchgecko.ai/pricing/arbitrage/gemma-3-27b-it"}}