Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start free brief
BenchLM
Model A
Gemma 4 12B

Google

47.3/100

Estimated · Public rank #151

90% interval 35.8–58.8

Gemma 4 12B vs Ornith-1.5-9B

Updated August 19, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
Ornith-1.5-9B

Ornith AI

37.0/100

Estimated · Public rank #205

90% interval 27.1–46.8

Decision reading

Gemma 4 12B has the higher public score estimate, 47.3 versus 36.95, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

3 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

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

    Ornith-1.5-9B

    Ornith-1.5-9B 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

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    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.

Shared results
3
Gemma 4 12B only
9
Ornith-1.5-9B only
13
Like-for-like categories
0 / 8

1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Knowledge

Directional only
Gemma 4 12B
77.5
Ornith-1.5-9B
29.1
Weighted basis
2 vs 2 rows
Reading
Directional only

Agentic

Not comparable
Gemma 4 12B
Not measured
Ornith-1.5-9B
56.4
Weighted basis
0 vs 1 rows
Reading
Not comparable

Coding

Not comparable
Gemma 4 12B
Not measured
Ornith-1.5-9B
61.7
Weighted basis
0 vs 2 rows
Reading
Not comparable

Reasoning

Not comparable
Gemma 4 12B
43.4
Ornith-1.5-9B
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Math

Not comparable
Gemma 4 12B
77.5
Ornith-1.5-9B
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Gemma 4 12B
Not measured
Ornith-1.5-9B
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Gemma 4 12B
69.1
Ornith-1.5-9B
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Gemma 4 12B
Not measured
Ornith-1.5-9B
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

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.

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
Ornith-1.5-9B
Self-hosted; infrastructure cost varies
Fits in one request

Gemma 4 12B has no comparable published API token rate. Ornith-1.5-9B 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
Ornith-1.5-9B
Self-hosted; infrastructure cost varies
Fits in one request

Gemma 4 12B has no comparable published API token rate. Ornith-1.5-9B 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
Ornith-1.5-9B
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable

Gemma 4 12B has no comparable published API token rate. Ornith-1.5-9B 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.

API model ID

Gemma 4 12B

Not sourced

Ornith-1.5-9B

Not sourced

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Gemma 4 12B

No comparable hosted API rate

Ornith-1.5-9B

No comparable hosted API rate

Ornith-1.5-9B model card

Reasoning profile

Gemma 4 12B

Reasoning

Ornith-1.5-9B

Reasoning

Weight access

Gemma 4 12B

Open Weight

Ornith-1.5-9B

Open Weight

License

Gemma 4 12B

Open Weight

Ornith-1.5-9B

Open Weight

Release date

Gemma 4 12B

2026-06-03

Ornith-1.5-9B

2026-08-18

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
Gemma 4 12B has the higher public score estimate, 47.3 versus 36.95, but the 90% score intervals overlap.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Ornith-1.5-9B has the larger documented window (262K).

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 evidence25 rows

Agentic

  • Terminal-Bench 2.1

    Gemma 4 12B—
    Ornith-1.5-9B46.2%
    Source

    Not directly comparable

  • HLE w/ tools

    Gemma 4 12B—
    Ornith-1.5-9B30.5%
    Source

    Not directly comparable

  • MCP Atlas

    Gemma 4 12B—
    Ornith-1.5-9B54.2%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Gemma 4 12B—
    Ornith-1.5-9B41.2%
    Source

    Not directly comparable

  • WideResearch

    Gemma 4 12B—
    Ornith-1.5-9B59.5%
    Source

    Not directly comparable

  • BrowseComp

    Gemma 4 12B—
    Ornith-1.5-9B56.4%
    Source

    Not directly comparable

  • Claw-Eval

    Gemma 4 12B—
    Ornith-1.5-9B66.5%
    Source

    Not directly comparable

Coding

  • LiveCodeBench v6

    Gemma 4 12B72.0%
    Source
    Ornith-1.5-9B—

    Not directly comparable

  • Terminal-Bench 2.1

    Gemma 4 12B—
    Ornith-1.5-9B46.2%
    Source

    Not directly comparable

  • SWE-bench Verified

    Gemma 4 12B—
    Ornith-1.5-9B70.6%
    Source

    Not directly comparable

  • SWE-bench Pro

    Gemma 4 12B—
    Ornith-1.5-9B47.5%
    Source

    Not directly comparable

  • SWE Multilingual

    Gemma 4 12B—
    Ornith-1.5-9B54.4%
    Source

    Not directly comparable

  • NL2Repo

    Gemma 4 12B—
    Ornith-1.5-9B32.4%
    Source

    Not directly comparable

Reasoning

  • BBH

    Gemma 4 12B53%
    Source
    Ornith-1.5-9B—

    Not directly comparable

  • MRCRv2

    Gemma 4 12B43.4%
    Source
    Ornith-1.5-9B—

    Not directly comparable

Knowledge

  • GPQA

    Gemma 4 12B78.8%
    Source
    Ornith-1.5-9B86.4%
    Source

    Ornith-1.5-9B leads this result

  • GPQA-D

    Gemma 4 12B78.8%
    Source
    Ornith-1.5-9B86.4%
    Source

    Ornith-1.5-9B leads this result

  • MMLU-Pro

    Gemma 4 12B77.2%
    Source
    Ornith-1.5-9B—

    Not directly comparable

  • HLE w/o tools

    Gemma 4 12B5.2%
    Source
    Ornith-1.5-9B20.2%
    Source

    Ornith-1.5-9B leads this result

  • MMMLU

    Gemma 4 12B83.4%
    Source
    Ornith-1.5-9B—

    Not directly comparable

  • HLE

    Gemma 4 12B—
    Ornith-1.5-9B20.2%
    Source

    Not directly comparable

Math

  • AIME26

    Gemma 4 12B77.5%
    Source
    Ornith-1.5-9B—

    Not directly comparable

Multimodal

  • MMMU-Pro

    Gemma 4 12B69.1%
    Source
    Ornith-1.5-9B—

    Not directly comparable

  • MathVision

    Gemma 4 12B79.7%
    Source
    Ornith-1.5-9B—

    Not directly comparable

  • MedXpertQA (MM)

    Gemma 4 12B48.7%
    Source
    Ornith-1.5-9B—

    Not directly comparable

Frequently asked questions

Which is better, Gemma 4 12B or Ornith-1.5-9B?

Gemma 4 12B has the higher public score estimate, 47.3 versus 36.95, 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 Ornith-1.5-9B?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

Which is better for agentic tasks, Gemma 4 12B or Ornith-1.5-9B?

The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.

Which costs less, Gemma 4 12B or Ornith-1.5-9B?

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 Ornith-1.5-9B?

Ornith-1.5-9B has the larger documented context window: 262K, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 19, 2026

Watch Gemma 4 12B vs Ornith-1.5-9B

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

Read a sample issue

Join 2,000+ readers.