Model A

Google

42.72/100

Estimated · Public rank #169

90% interval 31.2–54.2

Gemma 4 12B vs Inkling-Small

Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B

Inkling-Small

Thinking Machines Lab

59.25/100

Supported · Public rank #69

90% interval 52.4–66.1

Decision reading

Inkling-Small has the higher public score estimate, 59.25 versus 42.72, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

5 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Share or export

Share on X LinkedInSocial card CSV JSON

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

Long documents
Prompts that approach the documented context limit
Inkling-Small
Inkling-Small has the larger documented context window.
Confidence: documented

Show secondary and unsupported calls

Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Gemma 4 12B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Gemma 4 12B is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

7 Gemma 4 12B only

5 Shared

20 Inkling-Small only

Shared results: 5
Gemma 4 12B only: 7
Inkling-Small only: 20
Like-for-like categories: 1 / 8

4 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Knowledge

Like-for-like

Gemma 4 12B: 38.9; Supported · #141/183
Inkling-Small: 56.5; Supported · #46/183
Basis: BenchAlign lane · 5 vs 6 public rows
Reading: Inkling-Small leads · intervals overlap

Agentic

Directional only

Gemma 4 12B: 44.9; Estimated · #87/152
Inkling-Small: 36.9; Supported · #128/152
Basis: BenchAlign lane · 0 vs 5 public rows
Reading: Directional only

Coding

Directional only

Gemma 4 12B: 44.0; Estimated · #95/151
Inkling-Small: 43.8; Supported · #97/151
Basis: BenchAlign lane · 1 vs 6 public rows
Reading: Directional only

Multimodal

Directional only

Gemma 4 12B: 26.1; #44/48
Inkling-Small: 48.8; #39/48
Basis: Provisional lane · 1 vs 2 weighted rows
Reading: Directional only

Instruction following

Directional only

Gemma 4 12B: 90.1; #21/123
Inkling-Small: 89.6; #25/123
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Directional only

Reasoning

Not comparable

Gemma 4 12B: 33.7; Unranked · 4 rankable rows
Inkling-Small: 42.7; Unranked · 3 rankable rows
Basis: Provisional lane · 1 vs 1 weighted rows
Reading: Not comparable

Math

Not comparable

Gemma 4 12B: 57.6; Unranked · 1 rankable row
Inkling-Small: 76.9; Unranked · 2 rankable rows
Basis: Provisional lane · 1 vs 2 weighted rows
Reading: Not comparable

Multilingual

Not comparable

Gemma 4 12B: Not ranked
Inkling-Small: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for Gemma 4 12B and Inkling-Small
Category	Gemma 4 12B	Inkling-Small	Basis	Reading
Knowledge	38.9Supported · #141/183	56.5Supported · #46/183	Like-for-likeBenchAlign lane · 5 vs 6 public rows	Inkling-Small leads · intervals overlap
Agentic	44.9Estimated · #87/152	36.9Supported · #128/152	Directional onlyBenchAlign lane · 0 vs 5 public rows	Directional only
Coding	44.0Estimated · #95/151	43.8Supported · #97/151	Directional onlyBenchAlign lane · 1 vs 6 public rows	Directional only
Multimodal	26.1#44/48	48.8#39/48	Directional onlyProvisional lane · 1 vs 2 weighted rows	Directional only
Instruction following	90.1#21/123	89.6#25/123	Directional onlyProvisional lane · 0 vs 1 weighted rows	Directional only
Reasoning	33.7Unranked · 4 rankable rows	42.7Unranked · 3 rankable rows	Not comparableProvisional lane · 1 vs 1 weighted rows	Not comparable
Math	57.6Unranked · 1 rankable row	76.9Unranked · 2 rankable rows	Not comparableProvisional lane · 1 vs 2 weighted rows	Not comparable
Multilingual	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

HLE w/o tools
Knowledge
Gemma 4 12B: 5.2%Inkling-Small: 31.6%Normalized gap 26.4Gemma 4 12B source Inkling-Small source
AIME26
Math
Gemma 4 12B: 77.5%Inkling-Small: 95.5%Normalized gap 18.0Gemma 4 12B source Inkling-Small source
GPQA
Knowledge
Gemma 4 12B: 78.8%Inkling-Small: 89.5%Normalized gap 10.7Gemma 4 12B source Inkling-Small source
MMMU-Pro
Multimodal
Gemma 4 12B: 69.1%Inkling-Small: 74%Normalized gap 4.9Gemma 4 12B source Inkling-Small source

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Gemma 4 12B: API rate not published; Fits in one request
Inkling-Small: $0.0013; Fits in one request

Gemma 4 12B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Gemma 4 12B: API rate not published; Fits in one request
Inkling-Small: $0.03332; Fits in one request

Gemma 4 12B has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Gemma 4 12B: API rate not published; Fits in one request; Cached-input rate unavailable
Inkling-Small: $0.0492; Fits in one request

Gemma 4 12B has no comparable published API token rate.

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

SpecificationGemma 4 12BInkling-Small

Context window

Maximum documented context; output-token limits may be lower.

Gemma 4 12B

256K

Google Gemma 4 model documentation

Inkling-Small

Gemma 4 12B

Reasoning

Inkling-Small

Hybrid

Weight access

Gemma 4 12B

Open Weight

Inkling-Small

Open Weight

License

Gemma 4 12B

Open Weight

Inkling-Small

Open Weight

Release date

Gemma 4 12B

2026-06-03

Inkling-Small

2026-07-30

If you already use one of these models

Deployment change: The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal: Inkling-Small has the higher public score estimate, 59.25 versus 42.72, but the 90% score intervals overlap.
Workload cost: A complete comparable API-rate estimate is not available for both models.
Context tradeoff: Inkling-Small has the larger documented window (1M).

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence32 rows

Agentic

Terminal-Bench 2.0
Gemma 4 12B—
Inkling-Small64.7%
Source
Not directly comparable
BrowseComp
Gemma 4 12B—
Inkling-Small77.4%
Source
Not directly comparable
MCP Atlas
Gemma 4 12B—
Inkling-Small79.6%
Source
Not directly comparable
Toolathlon-Verified
Gemma 4 12B—
Inkling-Small54.4%
Source
Not directly comparable
Terminal-Bench 2.1 (Vals)
Gemma 4 12B—
Inkling-Small55.1%
Source
Not directly comparable

Coding

LiveCodeBench v6
Gemma 4 12B72.0%
Source
Inkling-Small—
Not directly comparable
SWE-bench Verified
Gemma 4 12B—
Inkling-Small80.2%
Source
Not directly comparable
SWE-bench Pro
Gemma 4 12B—
Inkling-Small55.9%
Source
Not directly comparable
Terminal-Bench 2.0
Gemma 4 12B—
Inkling-Small64.7%
Source
Not directly comparable
SciCode
Gemma 4 12B—
Inkling-Small48.7%
Source
Not directly comparable
LiveCodeBench (Vals)
Gemma 4 12B—
Inkling-Small85.9%
Source
Not directly comparable
SWE-bench (Vals)
Gemma 4 12B—
Inkling-Small82.2%
Source
Not directly comparable

Reasoning

BBH
Gemma 4 12B53%
Source
Inkling-Small—
Not directly comparable
MRCRv2
Gemma 4 12B43.4%
Source
Inkling-Small—
Not directly comparable
ARC-AGI-2
Gemma 4 12B—
Inkling-Small40.1%
Source
Not directly comparable
CritPt
Gemma 4 12B—
Inkling-Small8.3%
Source
Not directly comparable

Knowledge

GPQA
Gemma 4 12B78.8%
Source
Inkling-Small89.5%
Source
Inkling-Small leads this result
GPQA-D
Gemma 4 12B78.8%
Source
Inkling-Small89.5%
Source
Inkling-Small leads this result
MMLU-Pro
Gemma 4 12B77.2%
Source
Inkling-Small—
Not directly comparable
HLE w/o tools
Gemma 4 12B5.2%
Source
Inkling-Small31.6%
Source
Inkling-Small leads this result
MMMLU
Gemma 4 12B83.4%
Source
Inkling-Small—
Not directly comparable
HLE
Gemma 4 12B—
Inkling-Small47.8%
Source
Not directly comparable
GPQA Diamond (Vals)
Gemma 4 12B—
Inkling-Small83.6%
Source
Not directly comparable
MMLU-Pro (Vals)
Gemma 4 12B—
Inkling-Small85.6%
Source
Not directly comparable

Math

AIME26
Gemma 4 12B77.5%
Source
Inkling-Small95.5%
Source
Inkling-Small leads this result
HMMT Feb 2026
Gemma 4 12B—
Inkling-Small90.2%
Source
Not directly comparable

Multimodal

MMMU-Pro
Gemma 4 12B69.1%
Source
Inkling-Small74%
Source
Inkling-Small leads this result
MathVision
Gemma 4 12B79.7%
Source
Inkling-Small—
Not directly comparable
MedXpertQA (MM)
Gemma 4 12B48.7%
Source
Inkling-Small—
Not directly comparable
CharXiv
Gemma 4 12B—
Inkling-Small81.3%
Source
Not directly comparable
CharXiv w/o tools
Gemma 4 12B—
Inkling-Small77.4%
Source
Not directly comparable

Instruction following

IFBench
Gemma 4 12B—
Inkling-Small82.2%
Source
Not directly comparable

Frequently asked questions

Which is better, Gemma 4 12B or Inkling-Small?

Inkling-Small has the higher public score estimate, 59.25 versus 42.72, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Gemma 4 12B or Inkling-Small?

Gemma 4 12B scores higher for coding on the public lane, 44 to 43.8. Gemma 4 12B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Gemma 4 12B or Inkling-Small?

Gemma 4 12B scores higher for agentic tasks on the public lane, 44.9 to 36.9. Gemma 4 12B is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, Gemma 4 12B or Inkling-Small?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Gemma 4 12B or Inkling-Small?

Inkling-Small has the larger documented context window: 1M, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 10, 2026

Watch Gemma 4 12B vs Inkling-Small

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.

Gemma 4 12B vs Inkling-Small

Which one for your work

Long documents

Coding work

Agentic work

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

What is actually comparable

Category results, on a stated basis

Knowledge

Agentic

Coding

Multimodal

Instruction following

Reasoning

Math

Multilingual

Shape of the matched evidence

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

Benchmark evidence

Agentic

Coding

Reasoning

Knowledge

Math

Multimodal

Instruction following

Frequently asked questions

Which is better, Gemma 4 12B or Inkling-Small?

Which is better for coding, Gemma 4 12B or Inkling-Small?

Which is better for agentic tasks, Gemma 4 12B or Inkling-Small?

Which costs less, Gemma 4 12B or Inkling-Small?

Which has the larger context window, Gemma 4 12B or Inkling-Small?

Related comparisons

Watch Gemma 4 12B vs Inkling-Small