Skip to content

Gemma 4 12B

GoogleOpen weightsReasoningProvisionalReleased Jun 3, 2026
Compare with Command A+Source scores ↗
Overall score
36.3
Rank 156 of 222 · 21.9–50.6
Context window
256K
256,000 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Instruction following#2590.1
  2. 2Math61.3
  3. 3Multimodal#4559.4
  4. 4Knowledge#13453.0
  5. 5Reasoning51.8
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (11)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Multimodal

MMMU-Pro69.1#41 of 48
ExtractBench (LlamaIndex)(lower is better)45.39#1 of 24
MathVision79.7#18 of 20
MedXpertQA (MM)48.7#8 of 8

Knowledge

GPQA78.8#63 of 117
MMLU-Pro77.2#41 of 67
HLE w/o tools5.2#43 of 43
MMMLU83.4#6 of 11

Coding

LiveCodeBench v672.0#31 of 46

Reasoning

MRCRv243.4#10 of 12

Math

AIME2677.5#25 of 29

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price———

Open weights

From the Hugging Face repository.

Parameters
12B
Licence
apache-2.0
Downloads (30 days)
73.6K

Speed

Measured by us through OpenRouter (median of trials).

Not available on OpenRouter, so we cannot measure it yet.

Related models

Same family

Similar score