Phi-4 Mini Instruct

MicrosoftPhi開源權重MIT · 商用許可

描述

Phi 4 Mini Instruct is a lightweight (3.8B parameters) open model built upon synthetic data and filtered web data, focusing on high-quality reasoning. It supports a 128K token context length and is enhanced for instruction adherence and safety via supervised fine-tuning and direct preference optimization.

發布日期

2024-02-26

參數規模

3.8B

上下文長度

—

支援模態

—

能力雷達圖

general

coding

reasoning

science

agents

multimodal

排行榜排名

領域	#排名	分數	來源
程式碼能力榜	515	9.0	AA
通用能力榜	526	17.0	AA
科學能力	518	17.0	AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)

52.0%自報

Creativity

Social IQa

72.5%自報

Arena Hard

32.8%自報

Finance

MMLU

67.3%自報

TruthfulQA

66.4%自報

MMLU-Pro

52.8%自報

General

ARC-C

83.7%自報

OpenBookQA

79.2%自報

PIQA

77.6%自報

Multilingual MMLU

49.3%自報

Language

BoolQ

81.2%自報

BIG-Bench Hard

70.4%自報

Winogrande

67.0%自報

Math

MATH-500

94.6%自報

GSM8k

88.6%自報

MATH

64.0%自報

MGSM

63.9%自報

AIMEMAA

57.5%自報

Reasoning

HellaSwagAI2 (2019)

69.1%自報

AA 評測指數

(Artificial Analysis)

Math Index(Artificial Analysis)

6.7

Intelligence Index(Artificial Analysis)

5.7

Coding Index(Artificial Analysis)

3.8

Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))

0.7

Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))

0.5

Gpqa(NYU + Cohere + Anthropic (2023))

0.3

Ifbench(Google Research (2023))

0.2

Lcr(Artificial Analysis)

0.2

Livecodebench(UC Berkeley + MIT + Cornell (2024))

0.1

Scicode(UIUC + Argonne National Lab (2024))

0.1

Tau2(Sierra + U Toronto + Vector Institute (2025))

0.1

Aime 25(MAA (Mathematical Association of America))

0.1

Hle(Center for AI Safety + Scale AI (2025))

0.0

Aime(MAA (Mathematical Association of America))

0.0

Terminalbench V2 1

0.0

Terminalbench Hard(Stanford × Laude Institute (2026))

0.0

LLM Stats 分類評分

(LLM Stats (zeroeval))

Math

Psychology

Reasoning

General

Legal

Language

Finance

Healthcare

Physics

Creativity

Biology

Chemistry

Writing

定價

輸入價格免費

輸出價格免費

混合價格(3:1)免費

速度

Tokens/秒45.1

首Token延遲0.34s

首回答延遲0.34s

供應商價格排行

2 個供應商

最便宜: Azure Cognitive Services最貴: Azure

供應商輸入輸出

1Azure Cognitive Services最便宜

$0.075

$0.3

2Azure

$0.075

$0.3

比較該模型在不同 API 供應商之間的定價。

外部連結

LLM Stats Artificial Analysis