NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Gpt2
OpenAI logo

Gpt2

by OpenAI · Released Mar 2022

Open Source
11.8
avg score
Rank #296
Compare
Better than 5% 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

Openai-community text generation model. 11682K downloads on HuggingFace.

Tested on 6 benchmarks · BenchGecko score 11.8. Top scores: IFEval (19.3%), MUSR (13.0%), BBH (HuggingFace) (2.7%).

Capabilities
reasoning
13.0
#161 globally
math
0.3
#286 globally
knowledge
1.5
#302 globally
language
19.3
#164 globally
general
2.7
#218 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.

13.0·
mathCompare math →
MATH Level 5

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

0.3·
knowledgeCompare knowledge →
MMLU-PRO

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

1.7·
GPQA

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

1.3·
Quick compare:Meta logovs Llama 3.2 1B InstructAlibaba logovs Qwen2 0.5BAlibaba logovs Qwen2.5 0.5B Instruct
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
Meta logo
Llama 3.2 1B Instruct
Meta
11.7$0.03/1M
Alibaba logo
Qwen2 0.5B
Alibaba
10.8n/a
Alibaba logo
Qwen2.5 0.5B Instruct
Alibaba
13.3n/a
Links
Info
OpenAIPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@OpenAI
Source Code
GitHubHugging Face
BenchGecko API
openai-community-gpt2
Specifications
  • Typetext-generation
  • ContextN/A
  • ReleasedMar 2022
  • LicenseOpen Source
  • StatusActive
Available On
OpenAI logoOpenAIn/a
Categories
reasoningmathknowledgelanguagegeneral
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
Meta logoLlama 3.2 1B Instruct
11.7
Alibaba logoQwen2 0.5B
10.8
Alibaba logoQwen2.5 0.5B Instruct
13.3
DeepSeek logoDeepSeek R1 Distill Qwen 1.5B
13.4
Gpt2 is an open-source text-generation AI model by OpenAI, released in March 2022. It has an average benchmark score of 11.8.

Related Models

Llama 3.2 1B Instruct · MetaQwen2 0.5B · AlibabaQwen2.5 0.5B Instruct · AlibabaDeepSeek R1 Distill Qwen 1.5B · DeepSeekNemotron 3 Super · NVIDIA

Benchmarks

IFEvalMUSRBBH (HuggingFace)MMLU-PROGPQA

Related Pages

OpenAI · ProviderOpenAI · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • Gpt2 by OpenAI. BenchGecko score 11.8, rank 296 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

Gpt2 · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/openai-community-gpt2

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