The AI tools index that doesn't waste your time.不浪费你时间的 AI 工具索引。
Model dossier模型档案

Phi 4

Phi 4 is an entry-tier model from Microsoft (Intelligence Score 38.5/100). Strongest in knowledge (77.1) and reasoning (32.8); best fit: knowledge QA and long-form writing. It trails in math (6.7). Budget-priced: $0.070 in / $0.140 out per 1M tokens. Open weights — self-hostable.

Phi 4 是 Microsoft 的入门梯队模型(智能评分 38.5/100)。 最强项是知识(77.1分),其次是推理(32.8分);适合知识问答与长文写作。 短板是数学(6.7分)。 定价属低价档:每百万 token 输入 $0.070 / 输出 $0.140。 开放权重,可自托管。

open weights开放权重

38.5
Intelligence Score · benchmark coverage 智能评分 · benchmark 覆盖 58%
⚠ Low coverage — score is based on limited benchmark data.⚠ 覆盖不足——评分基于有限的 benchmark 数据。
ReaCodKnoMatAgtPre
◈

Benchmark scoresBenchmark 成绩

5 entries 条
Benchmark基准Score成绩Index指数Dated日期Measured by测评方
Humanity's Last ExamReasoning3.97—3rd-party第三方source ↗
GPQA DiamondReasoning56.159—3rd-party第三方source ↗×3⚠±13.8
MMLU-ProKnowledge71.477—3rd-party第三方source ↗×2
AIME 2025Math6.77—3rd-party第三方source ↗×3⚠±56.2
↳ ⚡high62.9——vendor-reported厂商自报source ↗
LMArena (Chatbot Arena)Preference12568—3rd-party第三方source ↗×2
≡

Specs & pricing规格与价格

Provider厂商Microsoft
Released发布2025-01-10
Context window上下文16K tokens
Max output最大输出15K tokens
Modality模态text->text
Reasoning tiers推理档位not documented未见公开文档
API input price输入价格$0.070 / 1M tokens
API output price输出价格$0.140 / 1M tokens

How we score →评分方法 → · Catalog & pricing via the official OpenRouter API.模型目录与价格来自 OpenRouter 官方 API。