NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Phi-1.5
Microsoft logo

Phi-1.5

by Microsoft · Released Jan 2024

Open Source
17.2
avg score
Rank #287
Compare
Better than 8% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text
License
Open Source
Benchmarks
11 tested
Data as of
About

Tested on 11 benchmarks · BenchGecko score 17.2. Top scores: Winogrande (46.8%), HellaSwag (30.1%), ARC AI2 (25.9%).

Capabilities
reasoning
3.4
#213 globally
math
1.8
#275 globally
knowledge
20.8
#268 globally
language
20.3
#162 globally
general
7.5
#201 globally
Benchmark Scores
Compare All
Tested on 11 benchmarks · Ranked across 5 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
reasoningCompare reasoning →
MUSR

HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.

3.4·
mathCompare math →
MATH Level 5

HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.

1.8·
knowledgeCompare knowledge →
Winogrande

Commonsense coreference resolution. Tests understanding of pronoun references in ambiguous sentences.

46.8·
HellaSwag

Sentence completion requiring commonsense reasoning about physical and social situations. Tests real-world understanding.

30.1·
ARC AI2

AI2 Reasoning Challenge. Grade-school science questions requiring multi-step reasoning. Easy and Challenge sets test different difficulty levels.

25.9·
Quick compare:DeepSeek logovs DeepSeek Coder 6.7Bvs RedPajama-INCITE-7B-Basevs Magistral Small 1.1
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
DeepSeek logo
DeepSeek Coder 6.7B
DeepSeek
17.1n/a
RedPajama-INCITE-7B-Base
Unknown
17.4n/a
Magistral Small 1.1
Unknown
17.0n/a
Links
Info
MicrosoftPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Microsoft
Source Code
GitHubHugging Face
BenchGecko API
phi-1-5
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseOpen Source
  • Statusbenchmark-only
Available On
Microsoft logoMicrosoftn/a
Categories
reasoningmathknowledgelanguagegeneral
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
DeepSeek logoDeepSeek Coder 6.7B
17.1
RedPajama-INCITE-7B-Base
17.4
Magistral Small 1.1
17.0
Meta logoLlama 4 Scout
16.5
Phi-1.5 is an open-source text AI model by Microsoft, released in January 2024. It has an average benchmark score of 17.2.

Related Models

DeepSeek Coder 6.7B · DeepSeekRedPajama-INCITE-7B-Base · UnknownMagistral Small 1.1 · UnknownLlama 4 Scout · MetaMistral 7B Instruct v0.1 · Mistral AI

Benchmarks

WinograndeHellaSwagARC AI2IFEvalMMLU

Related Pages

Microsoft · ProviderMicrosoft · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • Phi-1.5 by Microsoft. BenchGecko score 17.2, rank 287 of 312 scored models (normalized average of public benchmark scores).
  • List price n/a input · n/a output per 1M tokens (as of 2026-04-09).

How to cite · data as of 2026-04-09

Phi-1.5 · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/phi-1-5

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP