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
Nemotron 3 Nano Omni 30B A3B

NVIDIA

43.6/100

Estimated · Public rank #166

90% interval 32.1–55.1

Nemotron 3 Nano Omni 30B A3B vs Sakana Fugu

Updated August 13, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
Sakana Fugu

Sakana AI

—

Evidence status unavailable

90% interval unavailable

Decision reading

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.

4 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

    Sakana Fugu

    Sakana Fugu 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

    The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.

    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
4
Nemotron 3 Nano Omni 30B A3B only
12
Sakana Fugu only
7
Like-for-like categories
1 / 8

2 categories use 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.

Multimodal

Like-for-like
Nemotron 3 Nano Omni 30B A3B
76.3
Sakana Fugu
85.1
Weighted basis
1 vs 1 rows
Reading
Sakana Fugu leads

Coding

Directional only
Nemotron 3 Nano Omni 30B A3B
32.0
Sakana Fugu
59.7
Weighted basis
1 vs 2 rows
Reading
Directional only

Knowledge

Directional only
Nemotron 3 Nano Omni 30B A3B
76.3
Sakana Fugu
95.5
Weighted basis
2 vs 1 rows
Reading
Directional only

Agentic

Not comparable
Nemotron 3 Nano Omni 30B A3B
Not measured
Sakana Fugu
80.2
Weighted basis
0 vs 1 rows
Reading
Not comparable

Reasoning

Not comparable
Nemotron 3 Nano Omni 30B A3B
Not measured
Sakana Fugu
86.6
Weighted basis
0 vs 1 rows
Reading
Not comparable

Math

Not comparable
Nemotron 3 Nano Omni 30B A3B
Not measured
Sakana Fugu
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Nemotron 3 Nano Omni 30B A3B
Not measured
Sakana Fugu
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Nemotron 3 Nano Omni 30B A3B
74.2
Sakana Fugu
Not measured
Weighted basis
1 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

Nemotron 3 Nano Omni 30B A3B
Self-hosted; infrastructure cost varies
Fits in one request
Sakana Fugu
API rate not published
Fits in one request

Nemotron 3 Nano Omni 30B A3B has no comparable published API token rate. Sakana Fugu has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Nemotron 3 Nano Omni 30B A3B
Self-hosted; infrastructure cost varies
Fits in one request
Sakana Fugu
API rate not published
Fits in one request

Nemotron 3 Nano Omni 30B A3B has no comparable published API token rate. Sakana Fugu has no comparable published API token rate.

Cache-heavy agent loop

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

Nemotron 3 Nano Omni 30B A3B
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable
Sakana Fugu
API rate not published
Fits in one request
Cached-input rate unavailable

Nemotron 3 Nano Omni 30B A3B has no comparable published API token rate. Sakana Fugu 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.

Context window

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

Nemotron 3 Nano Omni 30B A3B

256K

Sakana Fugu

1M

API model ID

Nemotron 3 Nano Omni 30B A3B

Not sourced

Sakana Fugu

Not sourced

Cached-input rate

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

Nemotron 3 Nano Omni 30B A3B

No comparable hosted API rate

Sakana Fugu

No comparable hosted API rate

Documented inputs

Nemotron 3 Nano Omni 30B A3B

Not sourced

Sakana Fugu

Not sourced

Documented outputs

Nemotron 3 Nano Omni 30B A3B

Not sourced

Sakana Fugu

Not sourced

Provider availability

Nemotron 3 Nano Omni 30B A3B

Not sourced

Sakana Fugu

Not sourced

Reasoning profile

Nemotron 3 Nano Omni 30B A3B

Reasoning

Sakana Fugu

Reasoning

Weight access

Nemotron 3 Nano Omni 30B A3B

Open Weight

Sakana Fugu

Proprietary

License

Nemotron 3 Nano Omni 30B A3B

Open Weight

Sakana Fugu

Proprietary

Release date

Nemotron 3 Nano Omni 30B A3B

2026-04-28

Sakana Fugu

2026-06-22

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
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Sakana Fugu 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 evidence23 rows

Agentic

  • OSWorld

    Nemotron 3 Nano Omni 30B A3B47.4%
    Source
    Sakana Fugu—

    Not directly comparable

  • τ²-bench results

    Nemotron 3 Nano Omni 30B A3B45.3%
    Source
    Sakana Fugu—

    Not directly comparable

  • Terminal-Bench 2.0

    Nemotron 3 Nano Omni 30B A3B—
    Sakana Fugu80.2%
    Source

    Not directly comparable

Coding

  • LiveCodeBench v5

    Nemotron 3 Nano Omni 30B A3B63.2%
    Source
    Sakana Fugu—

    Not directly comparable

  • SciCode

    Nemotron 3 Nano Omni 30B A3B32%
    Source
    Sakana Fugu60.1%
    Source

    Sakana Fugu leads this result

  • SWE-bench Pro

    Nemotron 3 Nano Omni 30B A3B—
    Sakana Fugu59%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Nemotron 3 Nano Omni 30B A3B—
    Sakana Fugu80.2%
    Source

    Not directly comparable

  • LiveCodeBench v6

    Nemotron 3 Nano Omni 30B A3B—
    Sakana Fugu92.9%
    Source

    Not directly comparable

  • LiveCodeBench Pro

    Nemotron 3 Nano Omni 30B A3B—
    Sakana Fugu87.8%
    Source

    Not directly comparable

Reasoning

  • MRCRv2

    Nemotron 3 Nano Omni 30B A3B—
    Sakana Fugu86.6%
    Source

    Not directly comparable

Knowledge

  • MMLU-Pro

    Nemotron 3 Nano Omni 30B A3B77.3%
    Source
    Sakana Fugu—

    Not directly comparable

  • GPQA

    Nemotron 3 Nano Omni 30B A3B72.2%
    Source
    Sakana Fugu95.5%
    Source

    Sakana Fugu leads this result

  • GPQA-D

    Nemotron 3 Nano Omni 30B A3B72.2%
    Source
    Sakana Fugu95.5%
    Source

    Sakana Fugu leads this result

  • HLE w/o tools

    Nemotron 3 Nano Omni 30B A3B—
    Sakana Fugu47.2%
    Source

    Not directly comparable

Math

  • AIME 2025

    Nemotron 3 Nano Omni 30B A3B82.1%
    Source
    Sakana Fugu—

    Not directly comparable

Multimodal

  • MMMU

    Nemotron 3 Nano Omni 30B A3B70.8%
    Source
    Sakana Fugu—

    Not directly comparable

  • MMLongBench-Doc

    Nemotron 3 Nano Omni 30B A3B57.5%
    Source
    Sakana Fugu—

    Not directly comparable

  • CharXiv

    Nemotron 3 Nano Omni 30B A3B76.3%
    Source
    Sakana Fugu85.1%
    Source

    Sakana Fugu leads this result

  • ScreenSpot Pro

    Nemotron 3 Nano Omni 30B A3B57.8%
    Source
    Sakana Fugu—

    Not directly comparable

  • Video-MME (w/o subtitle)

    Nemotron 3 Nano Omni 30B A3B72.2%
    Source
    Sakana Fugu—

    Not directly comparable

  • AI2D_TEST

    Nemotron 3 Nano Omni 30B A3B88.5%
    Source
    Sakana Fugu—

    Not directly comparable

  • RefCOCO (avg)

    Nemotron 3 Nano Omni 30B A3B90.5%
    Source
    Sakana Fugu—

    Not directly comparable

Instruction following

  • IFBench

    Nemotron 3 Nano Omni 30B A3B74.2%
    Source
    Sakana Fugu—

    Not directly comparable

Frequently asked questions

Which is better, Nemotron 3 Nano Omni 30B A3B or Sakana Fugu?

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Nemotron 3 Nano Omni 30B A3B or Sakana Fugu?

The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Nemotron 3 Nano Omni 30B A3B or Sakana Fugu?

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, Nemotron 3 Nano Omni 30B A3B or Sakana Fugu?

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, Nemotron 3 Nano Omni 30B A3B or Sakana Fugu?

Sakana Fugu has the larger documented context window: 1M, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 13, 2026

Watch Nemotron 3 Nano Omni 30B A3B vs Sakana Fugu

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

Read a sample issue

Join 2,000+ readers.