Google

Gemma 3 12B

by Googletext+image->text1 endpoint
Neura Intelligence Index
9.7/ 100
Rank
#325
Confidence
low
Benchmarks
2(5% coverage)

Overview

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Capabilities

Text generation
Image understanding
Tool use / Function calling
Structured output
Long context
Top-P sampling
Stop sequences
Deterministic seed

Modalities

Input
TextImage
Output
Text

Technical Specifications

Context Window
131.1K tokens
Max Output
16.4K tokens
Knowledge Cutoff
2024-08-31
Tokenizer
Gemini
Uptime (24h)
9978.1%
Parameters
12000000000B
License
gemmaOpen Weights
Country
🇺🇸US
Release Date
March 12, 20251y

Supported Parameters

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Benchmark Performance

general

BenchmarkScoreSource
SimpleQA
6.3
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
40.9
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.05
Output$0.15
Added
March 13, 2025
Last synced 9/18/2026