18.8
avg score
Rank #207
Better than 10% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text-generation
License
Open Source
Benchmarks
6 tested
Data updated today
About
Google text generation model. 496K downloads on HuggingFace.
Tested on 6 benchmarks with 10.4% average. Top scores: IFEval (20.2%), MMLU-PRO (13.5%), BBH (HuggingFace) (12.5%).
Capabilities
reasoning
11.3
#126 globally
math
3.0
#198 globally
knowledge
7.6
#213 globally
general
12.5
#49 globally
language
20.2
#141 globally
Benchmark Scores
Compare AllTested on 6 benchmarks · Ranked across 5 categories
Score Distribution (all 231 models)
0255075100
▲ You are here
reasoningCompare reasoning →
MUSR
11.3—HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.
mathCompare math →
MATH Level 5
3.0—HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.
knowledgeCompare knowledge →
MMLU-PRO
13.5—HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.
GPQA
1.7—HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.
vs Mistral 7B Instruct v0.1 Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Info
Research
Documentation
Community
Source Code
BenchGecko API
google-gemma-2-2b
Specifications
- Typetext-generation
- ContextN/A
- ReleasedJul 2024
- LicenseOpen Source
- StatusActive
Available On
Google DeepMindTBDLearn More
Share & Export
Frequently Asked Questions
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 18.8.