{"source":"BenchGecko","url":"https://benchgecko.ai/model/phi-4-mini-instruct","as_of":"2026-06-22","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/phi-4-mini-instruct","cite":"Phi 4 Mini Instruct · benchmarks, pricing and providers. BenchGecko, data as of 2026-06-22. https://benchgecko.ai/model/phi-4-mini-instruct","slug":"phi-4-mini-instruct","name":"Phi 4 Mini Instruct","provider":{"name":"Microsoft","slug":"microsoft"},"model_type":"text","release_date":"2025-10-17","is_open_source":true,"status":"active","context_window":131072,"description":"Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4...","benchgecko_score":{"value":48.4,"rank":156,"of":312,"method":"Normalized average of public benchmark scores","method_url":"https://benchgecko.ai/methodology"},"avg_score":48.4,"list_price":{"input_usd_per_m":0.08,"output_usd_per_m":0.35,"source":"Provider list price","as_of":"2026-06-22"},"pricing":{"input":0.08,"output":0.35},"providers":[],"cheapest_provider":null,"providers_source":null,"scores":[{"benchmark":"IFEval","benchmark_slug":"hf-ifeval","score":73.78,"unit":"%","category":"language","source":"Hugging Face Open LLM Leaderboard (archived)","source_url":"https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/hf-ifeval"},{"benchmark":"BBH (HuggingFace)","benchmark_slug":"hf-bbh","score":38.74,"unit":"%","category":"general","source":"Hugging Face Open LLM Leaderboard (archived)","source_url":"https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/hf-bbh"},{"benchmark":"MMLU-PRO","benchmark_slug":"hf-mmlu-pro","score":32.58,"unit":"%","category":"knowledge","source":"Hugging Face Open LLM Leaderboard (archived)","source_url":"https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/hf-mmlu-pro"},{"benchmark":"MATH Level 5","benchmark_slug":"hf-math-lvl5","score":16.99,"unit":"%","category":"math","source":"Hugging Face Open LLM Leaderboard (archived)","source_url":"https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/hf-math-lvl5"},{"benchmark":"GPQA","benchmark_slug":"hf-gpqa","score":7.94,"unit":"%","category":"knowledge","source":"Hugging Face Open LLM Leaderboard (archived)","source_url":"https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/hf-gpqa"},{"benchmark":"MUSR","benchmark_slug":"hf-musr","score":6.45,"unit":"%","category":"reasoning","source":"Hugging Face Open LLM Leaderboard (archived)","source_url":"https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard","benchmark_url":"https://benchgecko.ai/benchmark/hf-musr"},{"benchmark":"Artificial Analysis — Quality Index","benchmark_slug":"aa-quality-index","score":3.03,"unit":"index","category":"speed","source":"Artificial Analysis","source_url":"https://artificialanalysis.ai","benchmark_url":"https://benchgecko.ai/benchmark/aa-quality-index"}],"gecko_tests":null,"links":{"page":"https://benchgecko.ai/model/phi-4-mini-instruct","json":"https://benchgecko.ai/api/v1/models/phi-4-mini-instruct","price_history":"https://benchgecko.ai/api/v1/price-history/phi-4-mini-instruct","provider_prices":null}}