Skip to main content
BenchLM
Advertise

Model comparison

Ling 3.0 Flash FP8 vs Sakana Fugu-Ultra

Updated August 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Ling 3.0 Flash FP8

InclusionAI

—

Evidence status unavailable

90% interval unavailable

Sakana Fugu-Ultra

Sakana AI

—

Evidence status unavailable

90% interval unavailable

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

    Sakana Fugu-Ultra

    Sakana Fugu-Ultra 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
3
Ling 3.0 Flash FP8 only
1
Sakana Fugu-Ultra only
8
Like-for-like categories
1 / 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

Like-for-like
Ling 3.0 Flash FP8
84.0
Sakana Fugu-Ultra
95.5
Weighted basis
1 vs 1 rows
Reading
Sakana Fugu-Ultra leads

Coding

Directional only
Ling 3.0 Flash FP8
40.4
Sakana Fugu-Ultra
64.5
Weighted basis
1 vs 2 rows
Reading
Directional only

Agentic

Not comparable
Ling 3.0 Flash FP8
Not measured
Sakana Fugu-Ultra
82.1
Weighted basis
0 vs 1 rows
Reading
Not comparable

Reasoning

Not comparable
Ling 3.0 Flash FP8
Not measured
Sakana Fugu-Ultra
93.6
Weighted basis
0 vs 1 rows
Reading
Not comparable

Math

Not comparable
Ling 3.0 Flash FP8
Not measured
Sakana Fugu-Ultra
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Ling 3.0 Flash FP8
Not measured
Sakana Fugu-Ultra
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Ling 3.0 Flash FP8
Not measured
Sakana Fugu-Ultra
86.6
Weighted basis
0 vs 1 rows
Reading
Not comparable

Instruction following

Not comparable
Ling 3.0 Flash FP8
73.4
Sakana Fugu-Ultra
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

Ling 3.0 Flash FP8
API rate not published
Fits in one request
Sakana Fugu-Ultra
API rate not published
Fits in one request

Ling 3.0 Flash FP8 has no comparable published API token rate. Sakana Fugu-Ultra has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Ling 3.0 Flash FP8
API rate not published
Fits in one request
Sakana Fugu-Ultra
API rate not published
Fits in one request

Ling 3.0 Flash FP8 has no comparable published API token rate. Sakana Fugu-Ultra has no comparable published API token rate.

Cache-heavy agent loop

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

Ling 3.0 Flash FP8
API rate not published
Fits in one request
Cached-input rate unavailable
Sakana Fugu-Ultra
API rate not published
Fits in one request
Cached-input rate unavailable

Ling 3.0 Flash FP8 has no comparable published API token rate. Sakana Fugu-Ultra 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

Ling 3.0 Flash FP8

Not sourced

Sakana Fugu-Ultra

Not sourced

Cached-input rate

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

Ling 3.0 Flash FP8

No comparable hosted API rate

InclusionAI Ling 3.0 Flash FP8 model card

Sakana Fugu-Ultra

No comparable hosted API rate

Documented inputs

Ling 3.0 Flash FP8

Not sourced

Sakana Fugu-Ultra

Not sourced

Documented outputs

Ling 3.0 Flash FP8

Not sourced

Sakana Fugu-Ultra

Not sourced

Provider availability

Ling 3.0 Flash FP8

Not sourced

Sakana Fugu-Ultra

Not sourced

Reasoning profile

Ling 3.0 Flash FP8

Reasoning

Sakana Fugu-Ultra

Reasoning

Weight access

Ling 3.0 Flash FP8

Open Weight

Sakana Fugu-Ultra

Proprietary

License

Ling 3.0 Flash FP8

Open Weight

Sakana Fugu-Ultra

Proprietary

Release date

Ling 3.0 Flash FP8

2026-08-04

Sakana Fugu-Ultra

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-Ultra 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 evidence12 rows

Agentic

  • Terminal-Bench 2.0

    Ling 3.0 Flash FP8—
    Sakana Fugu-Ultra82.1%
    Source

    Not directly comparable

Coding

  • SciCode

    Ling 3.0 Flash FP840.4%
    Source
    Sakana Fugu-Ultra58.7%
    Source

    Sakana Fugu-Ultra leads this result

  • SWE-bench Pro

    Ling 3.0 Flash FP8—
    Sakana Fugu-Ultra73.7%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Ling 3.0 Flash FP8—
    Sakana Fugu-Ultra82.1%
    Source

    Not directly comparable

  • LiveCodeBench v6

    Ling 3.0 Flash FP8—
    Sakana Fugu-Ultra93.2%
    Source

    Not directly comparable

  • LiveCodeBench Pro

    Ling 3.0 Flash FP8—
    Sakana Fugu-Ultra90.8%
    Source

    Not directly comparable

Reasoning

  • MRCRv2

    Ling 3.0 Flash FP8—
    Sakana Fugu-Ultra93.6%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Ling 3.0 Flash FP884%
    Source
    Sakana Fugu-Ultra95.5%
    Source

    Sakana Fugu-Ultra leads this result

  • GPQA-D

    Ling 3.0 Flash FP884.0%
    Source
    Sakana Fugu-Ultra95.5%
    Source

    Sakana Fugu-Ultra leads this result

  • HLE w/o tools

    Ling 3.0 Flash FP8—
    Sakana Fugu-Ultra50%
    Source

    Not directly comparable

Multimodal

  • CharXiv

    Ling 3.0 Flash FP8—
    Sakana Fugu-Ultra86.6%
    Source

    Not directly comparable

Instruction following

  • IFBench

    Ling 3.0 Flash FP873.4%
    Source
    Sakana Fugu-Ultra—

    Not directly comparable

Frequently asked questions

Which is better, Ling 3.0 Flash FP8 or Sakana Fugu-Ultra?

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, Ling 3.0 Flash FP8 or Sakana Fugu-Ultra?

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, Ling 3.0 Flash FP8 or Sakana Fugu-Ultra?

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, Ling 3.0 Flash FP8 or Sakana Fugu-Ultra?

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, Ling 3.0 Flash FP8 or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the larger documented context window: 1M, compared with 262K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 4, 2026

Watch Ling 3.0 Flash FP8 vs Sakana Fugu-Ultra

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

Read a sample issue

Join 2,000+ readers.