NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Gemma 2 2b
Google DeepMind logo

Gemma 2 2b

by Google DeepMind · Released Jul 2024

Open Source
18.4
avg score
Rank #283
Compare
Better than 9% 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

Google text generation model. 496K downloads on HuggingFace.

Tested on 6 benchmarks · BenchGecko score 18.4. Top scores: IFEval (20.2%), MMLU-PRO (13.5%), BBH (HuggingFace) (12.5%).

Capabilities
reasoning
11.3
#169 globally
math
3.0
#266 globally
knowledge
7.6
#291 globally
general
12.5
#187 globally
language
20.2
#163 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.

11.3·
mathCompare math →
MATH Level 5

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

3.0·
knowledgeCompare knowledge →
MMLU-PRO

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

13.5·
GPQA

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

1.7·
Quick compare:OpenAI logovs Cerebras-GPT-13BMistral AI logovs Mistral 7B Instruct v0.1vs Vicuna 7b V1.5
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
OpenAI logo
Cerebras-GPT-13B
OpenAI
18.2n/a
Mistral AI logo
Mistral 7B Instruct v0.1
Mistral AI
18.0$0.11/1M
Vicuna 7b V1.5
LMSYS
18.8n/a
Links
Info
Google DeepMindPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Google DeepMind
Source Code
GitHubHugging Face
BenchGecko API
google-gemma-2-2b
Specifications
  • Typetext-generation
  • ContextN/A
  • ReleasedJul 2024
  • LicenseOpen Source
  • StatusActive
Available On
Google DeepMind logoGoogle DeepMindn/a
Categories
reasoningmathknowledgegenerallanguage
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
OpenAI logoCerebras-GPT-13B
18.2
Mistral AI logoMistral 7B Instruct v0.1
18.0
Vicuna 7b V1.5
18.8
RedPajama-INCITE-7B-Base
17.4
Gemma 2 2b is an open-source text-generation AI model by Google DeepMind, released in July 2024. It has an average benchmark score of 18.4.

Related Models

Cerebras-GPT-13B · OpenAIMistral 7B Instruct v0.1 · Mistral AIVicuna 7b V1.5 · LMSYSRedPajama-INCITE-7B-Base · UnknownPhi-1.5 · Microsoft

Benchmarks

IFEvalMMLU-PROBBH (HuggingFace)MUSRMATH Level 5

Related Pages

Google DeepMind · ProviderGoogle DeepMind · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • Gemma 2 2b by Google DeepMind. BenchGecko score 18.4, rank 283 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

Gemma 2 2b · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/google-gemma-2-2b

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