NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Distilgpt2

Distilgpt2

by DistilBERT · Released Mar 2022

Open Source
8.3
avg score
Rank #304
Compare
Better than 3% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text-generation
License
Open Source
Benchmarks
6 tested
Data as of
About

Distilbert text generation model. 2664K downloads on HuggingFace.

Tested on 6 benchmarks · BenchGecko score 8.3. Top scores: MUSR (11.2%), IFEval (6.1%), BBH (HuggingFace) (2.8%).

Capabilities
reasoning
11.2
#171 globally
math
0.6
#284 globally
knowledge
1.7
#301 globally
language
6.1
#173 globally
general
2.8
#216 globally
Benchmark Scores
Compare All
Tested on 6 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.

11.2·
mathCompare math →
MATH Level 5

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

0.6·
knowledgeCompare knowledge →
MMLU-PRO

HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.

2.1·
GPQA

HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.

1.2·
Quick compare:OpenAI logovs Gpt2 LargeOpenAI logovs Gpt2 MediumAlibaba logovs Qwen2 0.5B Instruct
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
OpenAI logo
Gpt2 Large
OpenAI
7.9n/a
OpenAI logo
Gpt2 Medium
OpenAI
8.8n/a
Alibaba logo
Qwen2 0.5B Instruct
Alibaba
7.8n/a
Links
Info
DistilBERTPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@DistilBERT
Source Code
GitHubHugging Face
BenchGecko API
distilbert-distilgpt2
Specifications
  • Typetext-generation
  • ContextN/A
  • ReleasedMar 2022
  • LicenseOpen Source
  • StatusActive
Available On
DistilBERTn/a
Categories
reasoningmathknowledgelanguagegeneral
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
OpenAI logoGpt2 Large
7.9
OpenAI logoGpt2 Medium
8.8
Alibaba logoQwen2 0.5B Instruct
7.8
SmolLM2 135M
9.0
Distilgpt2 is an open-source text-generation AI model by DistilBERT, released in March 2022. It has an average benchmark score of 8.3.

Related Models

Gpt2 Large · OpenAIGpt2 Medium · OpenAIQwen2 0.5B Instruct · AlibabaSmolLM2 135M · Hugging Face TBSmolLM2 135M Instruct · Hugging Face TB

Benchmarks

MUSRIFEvalBBH (HuggingFace)MMLU-PROGPQA

Related Pages

DistilBERT · ProviderDistilBERT · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • Distilgpt2 by DistilBERT. BenchGecko score 8.3, rank 304 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

Distilgpt2 · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/distilbert-distilgpt2

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