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 the free Radar Brief
BenchLM
LiquidAI logo
Model A
LFM2.5-8B-A1B

LiquidAI

41.82/100

Estimated · Public rank #190

90% interval 30.3–53.3

LFM2.5-8B-A1B vs Nemotron 3 Ultra

Updated August 30, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

NVIDIA logo
Model B
Nemotron 3 Ultra

NVIDIA

46.32/100

Estimated · Public rank #162

90% interval 36.5–56.2

Decision reading

Nemotron 3 Ultra has the higher public score estimate, 46.32 versus 41.82, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

1 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

    Nemotron 3 Ultra

    Nemotron 3 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

    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

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. LFM2.5-8B-A1B does not fit this workload in one request. LFM2.5-8B-A1B has no comparable published API token rate. Nemotron 3 Ultra has no comparable published API token rate.

    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
1
LFM2.5-8B-A1B only
6
Nemotron 3 Ultra only
18
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.

Instruction following

Directional only
LFM2.5-8B-A1B
68.8
Nemotron 3 Ultra
81.7
Weighted basis
2 vs 1 rows
Reading
Directional only

Agentic

Not comparable
LFM2.5-8B-A1B
Not measured
Nemotron 3 Ultra
51.3
Weighted basis
0 vs 2 rows
Reading
Not comparable

Coding

Not comparable
LFM2.5-8B-A1B
Not measured
Nemotron 3 Ultra
58.3
Weighted basis
0 vs 2 rows
Reading
Not comparable

Reasoning

Not comparable
LFM2.5-8B-A1B
Not measured
Nemotron 3 Ultra
61.9
Weighted basis
0 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
LFM2.5-8B-A1B
Not measured
Nemotron 3 Ultra
53.8
Weighted basis
0 vs 3 rows
Reading
Not comparable

Math

Not comparable
LFM2.5-8B-A1B
50.0
Nemotron 3 Ultra
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
LFM2.5-8B-A1B
Not measured
Nemotron 3 Ultra
83.0
Weighted basis
0 vs 1 rows
Reading
Not comparable

Multimodal

Not comparable
LFM2.5-8B-A1B
Not measured
Nemotron 3 Ultra
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

LFM2.5-8B-A1B
Self-hosted; infrastructure cost varies
Fits in one request
Nemotron 3 Ultra
Self-hosted; infrastructure cost varies
Fits in one request

LFM2.5-8B-A1B has no comparable published API token rate. Nemotron 3 Ultra has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

LFM2.5-8B-A1B
Self-hosted; infrastructure cost varies
Fits in one request
Nemotron 3 Ultra
Self-hosted; infrastructure cost varies
Fits in one request

LFM2.5-8B-A1B has no comparable published API token rate. Nemotron 3 Ultra has no comparable published API token rate.

Cache-heavy agent loop

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

LFM2.5-8B-A1B
Self-hosted; infrastructure cost varies
Does not fit in one request
Cached-input rate unavailable
Nemotron 3 Ultra
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable

LFM2.5-8B-A1B does not fit this workload in one request. LFM2.5-8B-A1B has no comparable published API token rate. Nemotron 3 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.

Context window

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

LFM2.5-8B-A1B

128K

Nemotron 3 Ultra

1M

API model ID

LFM2.5-8B-A1B

Not sourced

Nemotron 3 Ultra

Not sourced

Cached-input rate

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

LFM2.5-8B-A1B

No comparable hosted API rate

Nemotron 3 Ultra

No comparable hosted API rate

Documented inputs

LFM2.5-8B-A1B

Not sourced

Nemotron 3 Ultra

Not sourced

Documented outputs

LFM2.5-8B-A1B

Not sourced

Nemotron 3 Ultra

Not sourced

Provider availability

LFM2.5-8B-A1B

Not sourced

Nemotron 3 Ultra

Not sourced

Reasoning profile

LFM2.5-8B-A1B

Reasoning

Nemotron 3 Ultra

Reasoning

Weight access

LFM2.5-8B-A1B

Open Weight

Nemotron 3 Ultra

Open Weight

License

LFM2.5-8B-A1B

Open Weight

Nemotron 3 Ultra

Open Weight

Release date

LFM2.5-8B-A1B

2026-05-28

Nemotron 3 Ultra

2026-06-04

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
Nemotron 3 Ultra has the higher public score estimate, 46.32 versus 41.82, but the 90% score intervals overlap.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Nemotron 3 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 evidence25 rows

Agentic

  • BFCL v4

    LFM2.5-8B-A1B49.7%
    Source
    Nemotron 3 Ultra—

    Not directly comparable

  • τ²-bench results

    LFM2.5-8B-A1B88.1%
    Source
    Nemotron 3 Ultra—

    Not directly comparable

  • Terminal-Bench 2.0

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra56.4%
    Source

    Not directly comparable

  • PinchBench

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra90.0%
    Source

    Not directly comparable

  • BrowseComp

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra44.4%
    Source

    Not directly comparable

  • τ³-bench results

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra70.9%
    Source

    Not directly comparable

  • HLE w/ tools

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra37.4%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra71.9%
    Source

    Not directly comparable

  • SWE Multilingual

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra67.7%
    Source

    Not directly comparable

  • LiveCodeBench v6

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra89.0%
    Source

    Not directly comparable

  • SciCode

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra44.6%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra56.4%
    Source

    Not directly comparable

Reasoning

  • CritPt

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra3.1%
    Source

    Not directly comparable

  • LongBench v2

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra61.9%
    Source

    Not directly comparable

Knowledge

  • GPQA

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra87%
    Source

    Not directly comparable

  • GPQA-D

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra87.0%
    Source

    Not directly comparable

  • HLE

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra26.7%
    Source

    Not directly comparable

  • HLE w/o tools

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra26.7%
    Source

    Not directly comparable

  • MMLU-Pro

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra86.8%
    Source

    Not directly comparable

Math

  • MATH-500

    LFM2.5-8B-A1B88.8%
    Source
    Nemotron 3 Ultra—

    Not directly comparable

  • AIME 2025

    LFM2.5-8B-A1B42.5%
    Source
    Nemotron 3 Ultra—

    Not directly comparable

  • AIME26

    LFM2.5-8B-A1B50.0%
    Source
    Nemotron 3 Ultra—

    Not directly comparable

Multilingual

  • MMLU-ProX

    LFM2.5-8B-A1B—
    Nemotron 3 Ultra83%
    Source

    Not directly comparable

Instruction following

  • IFEval

    LFM2.5-8B-A1B91.8%
    Source
    Nemotron 3 Ultra—

    Not directly comparable

  • IFBench

    LFM2.5-8B-A1B56.5%
    Source
    Nemotron 3 Ultra81.7%
    Source

    Nemotron 3 Ultra leads this result

Frequently asked questions

Which is better, LFM2.5-8B-A1B or Nemotron 3 Ultra?

Nemotron 3 Ultra has the higher public score estimate, 46.32 versus 41.82, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, LFM2.5-8B-A1B or Nemotron 3 Ultra?

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, LFM2.5-8B-A1B or Nemotron 3 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, LFM2.5-8B-A1B or Nemotron 3 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, LFM2.5-8B-A1B or Nemotron 3 Ultra?

Nemotron 3 Ultra has the larger documented context window: 1M, compared with 128K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 30, 2026

Watch LFM2.5-8B-A1B vs Nemotron 3 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.