Skip to content
ModelCap

Gemma 3 12B

Current board #67Arena #205Gated access

Google·google/gemma-3-12b-it

Gemma 3 12B is a language model published by Google. 1 OpenRouter endpoint is published in the latest snapshot. It accepts text, image input and returns text. The published context limit is 131K tokens. The catalogue declares support for tool use, structured outputs.

ModelCap Index · Current board
43.1#67
Measured · 52% support · score interval 43.1–54.7
Market Gravity
26.9
Secondary market signal
Input
$0.05
per 1M tokens
Output
$0.15
per 1M tokens
Context
131K
tokens
Providers
1
endpoint
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
DeepInfrabf16$0.05$0.15131Kbf16100.0%

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
deepinfra
live
$0.05$0.15131K343 ms50.4 tok/stools · structured
featherless-ai
live
——————

Reported evaluation leads (4)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
Idavidrein/gpqa
main
—36.5471
Unpinned
not published
Reported
Quarantined
Idavidrein/gpqa
diamond
—33.8384
Unpinned
not published
Reported
Quarantined
LEXam-Benchmark/LEXam
open_question
—41.29
Unpinned
not published
Reported
Quarantined
LEXam-Benchmark/LEXam
mcq_4_choices
—29.94
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
43.1
Measured · 3 public benchmark observations across 3 boards
Current board
#67
Public rank basis
Measured (measured)
Index support
52.1% · moderate
Index interval
43.1–54.7
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · google/google/gemma-3-12b-it · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata google/gemma-3-12b-it@96b6f1eccf38110c56df3a15bffe176da04bfd80 (not the evaluation revision)
Direct benchmark observations
3
Breadth-adjusted BES point estimate
48.9
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
48.9
Evidence status
confirmed · 84% mass
General preference
51.5
Coding
38.5
Agents & tools
38.0
Reasoning
—
Evidence breadth
97%
Evidence coverage
52%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
18.1
Liquidity (providers × uptime)
35.0
Open reach (HF downloads)
—
Surface (context / tools / modalities)
60.2
Freshness
14.2
  • · OpenRouter popularity #106
  • · 1 live provider
  • · Catalogue: context 131072, tools, modalities Text/Image
  • · First seen 2025-03-13

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
82.5
strong · 93% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
68.3
Deployability
82.5
Evaluation provenance
70.6

Missing: accessLegalClarity.resolvable-license-terms, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
26.9
OpenRouter weekly popularity
#106 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
Arena
Official rank
#205 of 385
Rating
1342.0
95% confidence interval
1332–1352
Votes
4K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
99%

Market Gravity breakdown

Usage55%
18.1

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
35.0

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
14.2

Time since first public availability, on a six-month half-life.

Specification

Context window
131K tokens
Max output
16K tokens
Inputs
Text, Image
Outputs
Text
Tokenizer
Gemini
Cached input tokens
Not offered
First seen on OpenRouter
13 Mar 2025
Knowledge cutoff
2024-08-31

Capabilities

  • Not supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Gated access. The weights are hosted behind an access request or acceptance step. Review the publisher's access requirements and license before use or redistribution.

Access
Gated access
Licence
gemma
Pinned revision
96b6f1eccf38
Parameters
12.2B
Architecture
Gemma3ForConditionalGeneration
Model type
gemma3
Hugging Face downloads (30d)
1.3M
Downloads (all time)
21.7M
Likes
798
Repository
google/gemma-3-12b-it
Repository updated
21 Mar 2025, 20:28 UTC
Base lineage
google/gemma-3-12b-pt