Gemma 3n E2B Instructed
Multimodal
Zero-eval
#2OpenAI MMLU
by Google
About
Gemma 3n E2B Instructed is a multimodal language model developed by Google. The model shows competitive results across 18 benchmarks. Notable strengths include HumanEval (66.5%), MMLU (60.1%), Global-MMLU-Lite (59.0%). As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2025, it represents Google's latest advancement in AI technology.
Timeline
AnnouncedJun 26, 2025
ReleasedJun 26, 2025
Knowledge CutoffJun 1, 2024
Specifications
Training Tokens11.0T
Capabilities
Multimodal
License & Family
License
Proprietary
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
18 benchmarks
Average Score
33.7%
Best Score
66.5%
High Performers (80%+)
0Top Categories
math
40.4%
code
33.2%
general
32.8%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
HumanEval
Rank #57 of 62
#54Gemma 3n E2B Instructed LiteRT (Preview)
66.5%
#55GPT-4
67.0%
#56GPT-3.5 Turbo
68.0%
#57Gemma 3n E2B Instructed
66.5%
#58Phi-3.5-mini-instruct
62.8%
#59Gemma 2 27B
51.8%
#60Gemma 3 1B
41.5%
MMLU
Rank #77 of 78
#74Gemma 3n E2B Instructed LiteRT (Preview)
60.1%
#75IBM Granite 4.0 Tiny Preview
60.4%
#76Llama 3.2 3B Instruct
63.4%
#77Gemma 3n E2B Instructed
60.1%
#78GPT OSS 120B
54.8%
Global-MMLU-Lite
Rank #12 of 14
#9Gemma 3n E2B Instructed LiteRT (Preview)
59.0%
#10Gemma 3n E4B Instructed LiteRT Preview
64.5%
#11Gemma 3n E4B Instructed
64.5%
#12Gemma 3n E2B Instructed
59.0%
#13Gemma 3 4B
54.5%
#14Gemma 3 1B
34.2%
MBPP
Rank #29 of 31
#26Gemma 3n E2B Instructed LiteRT (Preview)
56.6%
#27Gemma 2 27B
62.6%
#28Gemma 3 4B
63.2%
#29Gemma 3n E2B Instructed
56.6%
#30Gemma 2 9B
52.4%
#31Gemma 3 1B
35.2%
Global-MMLU
Rank #4 of 4
#1Gemma 3n E2B Instructed LiteRT (Preview)
55.1%
#2Gemma 3n E4B Instructed
60.3%
#3Gemma 3n E4B Instructed LiteRT Preview
60.3%
#4Gemma 3n E2B Instructed
55.1%
All Benchmark Results for Gemma 3n E2B Instructed
Complete list of benchmark scores with detailed information
HumanEval HumanEval benchmark | code | text | 0.67 | 66.5% | Self-reported |
MMLU MMLU benchmark | general | text | 0.60 | 60.1% | Self-reported |
Global-MMLU-Lite Global-MMLU-Lite benchmark | general | text | 0.59 | 59.0% | Self-reported |
MBPP MBPP benchmark | code | text | 56.60 | 56.6% | Self-reported |
Global-MMLU Global-MMLU benchmark | general | text | 0.55 | 55.1% | Self-reported |
MGSM MGSM benchmark | math | text | 0.53 | 53.1% | Self-reported |
WMT24++ WMT24++ benchmark | general | text | 0.43 | 42.7% | Self-reported |
MMLU-Pro MMLU-Pro benchmark | general | text | 0.41 | 40.5% | Self-reported |
Include Include benchmark | general | text | 0.39 | 38.6% | Self-reported |
HiddenMath HiddenMath benchmark | math | text | 0.28 | 27.7% | Self-reported |
Showing 1 to 10 of 18 benchmarks