Skip to main content

Phi-4

MicrosoftPhiOpen WeightMIT · Commercial OK

Description

phi-4 is a state-of-the-art open model built to excel at advanced reasoning, coding, and knowledge tasks. It leverages a blend of synthetic data, filtered web data, academic texts, and supervised fine-tuning for precision, alignment, and safety.

Release Date
2024-12-12
Parameters
14.7B
Context Length
16K
Modalities
text

Capability Radar

28
general
17
coding
30
reasoning
36
scienceest.
0
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking390
14.0
AA
General Ranking415
23.0
AA
Math Reasoning267
30.0
AA
Reasoning25
83.0
LS
Science295
36.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA56.1%SR

Code

HumanEval82.6%SR

Creativity

Arena Hard75.4%SR

Factuality

SimpleQA3.0%SR

Finance

MMLU84.8%SR
MMLU-Pro70.4%SR

General

IFEval63.0%SR
PhiBench56.2%SR
LiveBench47.6%SR

Math

MGSM80.6%SR
MATH80.4%SR
DROP75.5%SR

Reasoning

HumanEval+82.8%SR

AA Evaluation Indices

Math Index
18.0
Coding Index
11.2
Intelligence Index
10.4
Math 500
0.8
Mmlu Pro
0.7
Gpqa
0.6
Scicode
0.3
Ifbench
0.2
Livecodebench
0.2
Aime 25
0.2
Aime
0.1
Hle
0.0
Terminalbench Hard
0.0
Lcr
0.0
Tau2
0.0

LLM Stats Category Scores

Writing
80
Code
80
Creativity
80
Finance
80
Healthcare
80
Language
80
Legal
80
Math
70
Reasoning
70
Structured Output
60
Biology
60
Chemistry
60
General
60
Instruction Following
60
Physics
60
Factuality
0

Pricing

Input Price$0.125 / 1M tokens
Output Price$0.5 / 1M tokens
Blended Price (3:1)$0.219 / 1M tokens

Speed

Tokens/sec38.5 tokens/s
Time to First Token0.51s
Time to Answer0.51s

Available Providers

(LS internal units)

No provider data available

External Sources