Back to Explore
Gemma 4 12B (Non-reasoning)
Google·Released 2026-06-03
Open SourceMultimodal
Comparison data ready73% coverage12/12 fields directly observedUpdated Jul 25, 2026, 6:01 AM
Related Models
Pricing
Input
$0.10
per 1M tokens
Output
$0.30
per 1M tokens
Blended
$0.15
per 1M tokens
Cheaper than 77% of models. Median price is $0.69/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.15
Monthly
$4.50
vs. Similar Models
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)Q:-0.1
$0.17+17%
Qwen3 VL 30B A3B (Reasoning)Q:+0.1
$0.75+400%
QwQ 32BQ:+0.2
$0.74+397%
Qwen3 235B A22B (Reasoning)Q:+0.2
$2.63+1650%
Performance
127
tokens/sec
Faster than 67% of models
1.36
seconds
Faster than 44% of models
1.36
seconds
Faster than 64% of models
Market Median
95 tok/s
33% faster
Median TTFT
1.19s
14% slower
Throughput/Dollar
848
tok/s per $/1M
Speed Comparison
Mistral Medium
128 tok/s+0%
Qwen3 VL 30B A3B (Reasoning)
127 tok/s-0%
Hy3-preview (Non-reasoning)
127 tok/s-0%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
66.1%
HLE
6.2%
LiveCodeBenchNot evaluated
SciCode
29.7%
TerminalBench Hard
11.4%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
45.2%
Long Context Recall
30.7%
Tau2
31.9%
Market AverageTop Score