Google

Gemma 3 27B

Multimodal
Zero-eval
#1MMMU (val)
#1WMT24++
#1BIG-Bench Extra Hard
+5 more

by Google

+
+
+
+
About

Gemma 3 27B represents the largest variant in the Gemma 3 family, developed to provide flagship-level open-source capabilities. Built with advanced training methodologies and 27 billion parameters, it offers researchers and developers access to powerful language understanding without proprietary restrictions.

+
+
+
+
Pricing Range
Input (per 1M)$0.10 -$0.11
Output (per 1M)$0.20 -$0.20
Providers2
+
+
+
+
Timeline
AnnouncedMar 12, 2025
ReleasedMar 12, 2025
+
+
+
+
Specifications
Training Tokens14.0T
Capabilities
Multimodal
+
+
+
+
License & Family
License
Gemma
Performance Overview
Performance metrics and category breakdown

Overall Performance

26 benchmarks
Average Score
65.4%
Best Score
95.9%
High Performers (80%+)
8

Performance Metrics

Max Context Window
262.1K
Avg Throughput
33.0 tok/s
Avg Latency
0ms
+
+
+
+
All Benchmark Results for Gemma 3 27B
Complete list of benchmark scores with detailed information
GSM8k
text
0.96
95.9%
Self-reported
IFEval
text
0.90
90.4%
Self-reported
MATH
text
0.89
89.0%
Self-reported
HumanEval
text
0.88
87.8%
Self-reported
BIG-Bench Hard
text
0.88
87.6%
Self-reported
DocVQA
multimodal
0.87
86.6%
Self-reported
AI2D
multimodal
0.84
84.5%
Self-reported
Natural2Code
text
0.84
84.5%
Self-reported
ChartQA
multimodal
0.78
78.0%
Self-reported
Global-MMLU-Lite
text
0.75
75.1%
Self-reported
Showing 1 to 10 of 26 benchmarks
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+