41.8
avg score
Rank #168
Better than 39% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text-generation
License
Open Source
Benchmarks
12 tested
Data updated today
About
Google text generation model. 398K downloads on HuggingFace.
Tested on 12 benchmarks with 36.4% average. Top scores: Chatbot Arena Elo — Overall (1199.7%), JSQuAD (83.8%), JCommonsenseQA (78.2%).
Capabilities
reasoning
7.1
#177 globally
math
0.1
#253 globally
knowledge
10.2
#249 globally
general
18.0
#47 globally
language
59.1
#102 globally
Benchmark Scores
Compare AllTested on 12 benchmarks · Ranked across 6 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
reasoningCompare reasoning →
MUSR
7.1—HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.
mathCompare math →
MATH Level 5
0.1—HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.
knowledgeCompare knowledge →
MMLU-PRO
17.2—HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.
GPQA
3.2—HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Research
Documentation
Community
Source Code
BenchGecko API
google-gemma-2-2b-it
Specifications
- Typetext-generation
- ContextN/A
- ReleasedJul 2024
- LicenseOpen Source
- StatusActive
Available On
Learn More
Share & Export
Frequently Asked Questions
Gemma 2 2b It is an open-source text-generation AI model by Google DeepMind, released in July 2024. It has an average benchmark score of 41.8.