Model A

Google

60.39/100

Supported · Public rank #66

90% interval 44.0–76.8

Gemma 4 31B vs Nemotron 3 Ultra

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

Model B

Nemotron 3 Ultra

NVIDIA

46.32/100

Estimated · Public rank #162

90% interval 36.5–56.2

Decision reading

Gemma 4 31B has the higher public score estimate, 60.39 versus 46.32, but the 90% score intervals overlap. Treat that as a lead, not a settled 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
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
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.

4 Gemma 4 31B only

4 Shared

15 Nemotron 3 Ultra only

Shared results: 4
Gemma 4 31B only: 4
Nemotron 3 Ultra only: 15
Like-for-like categories: 1 / 8

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

Gemma 4 31B: 52.9
Nemotron 3 Ultra: 53.8
Weighted basis: 3 vs 3 rows
Reading: Nemotron 3 Ultra leads

Agentic

Not comparable

Gemma 4 31B: Not measured
Nemotron 3 Ultra: 51.3
Weighted basis: 0 vs 2 rows
Reading: Not comparable

Coding

Not comparable

Gemma 4 31B: 41.6
Nemotron 3 Ultra: 58.3
Weighted basis: 1 vs 2 rows
Reading: Not comparable

Reasoning

Not comparable

Gemma 4 31B: Not measured
Nemotron 3 Ultra: 61.9
Weighted basis: 0 vs 1 rows
Reading: Not comparable

Math

Not comparable

Gemma 4 31B: Not measured
Nemotron 3 Ultra: Not measured
Weighted basis: 0 vs 0 rows
Reading: Not comparable

Multilingual

Not comparable

Gemma 4 31B: Not measured
Nemotron 3 Ultra: 83.0
Weighted basis: 0 vs 1 rows
Reading: Not comparable

Multimodal

Not comparable

Gemma 4 31B: 76.9
Nemotron 3 Ultra: Not measured
Weighted basis: 1 vs 0 rows
Reading: Not comparable

Instruction following

Not comparable

Gemma 4 31B: Not measured
Nemotron 3 Ultra: 81.7
Weighted basis: 0 vs 1 rows
Reading: Not comparable

Category averages with the server-provided evidence basis for Gemma 4 31B and Nemotron 3 Ultra
Category	Gemma 4 31B	Nemotron 3 Ultra	Weighted basis	Reading
Knowledge	52.9	53.8	Like-for-like3 vs 3 rows	Nemotron 3 Ultra leads
Agentic	Not measured	51.3	Not comparable0 vs 2 rows	Not comparable
Coding	41.6	58.3	Not comparable1 vs 2 rows	Not comparable
Reasoning	Not measured	61.9	Not comparable0 vs 1 rows	Not comparable
Math	Not measured	Not measured	Not comparable0 vs 0 rows	Not comparable
Multilingual	Not measured	83.0	Not comparable0 vs 1 rows	Not comparable
Multimodal	76.9	Not measured	Not comparable1 vs 0 rows	Not comparable
Instruction following	Not measured	81.7	Not comparable0 vs 1 rows	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.

GPQA
Knowledge
Gemma 4 31B: 84.3%Nemotron 3 Ultra: 87%Normalized gap 2.7Gemma 4 31B source Nemotron 3 Ultra source
MMLU-Pro
Knowledge
Gemma 4 31B: 85.2%Nemotron 3 Ultra: 86.8%Normalized gap 1.6Gemma 4 31B source Nemotron 3 Ultra source
HLE
Knowledge
Gemma 4 31B: 26.5%Nemotron 3 Ultra: 26.7%Normalized gap 0.2Gemma 4 31B source Nemotron 3 Ultra 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 31B: Self-hosted; infrastructure cost varies; Fits in one request
Nemotron 3 Ultra: Self-hosted; infrastructure cost varies; Fits in one request

Gemma 4 31B 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

Gemma 4 31B: Self-hosted; infrastructure cost varies; Fits in one request
Nemotron 3 Ultra: Self-hosted; infrastructure cost varies; Fits in one request

Gemma 4 31B 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

Gemma 4 31B: Self-hosted; infrastructure cost varies; Fits in one request; Cached-input rate unavailable
Nemotron 3 Ultra: Self-hosted; infrastructure cost varies; Fits in one request; Cached-input rate unavailable

Reasoning

Nemotron 3 Ultra

Reasoning

Weight access

Gemma 4 31B

Open Weight

Nemotron 3 Ultra

Open Weight

License

Gemma 4 31B

Open Weight

Nemotron 3 Ultra

Open Weight

Release date

Gemma 4 31B

2026-04-02

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: Gemma 4 31B has the higher public score estimate, 60.39 versus 46.32, 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.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Gemma 4 31B

API / mo$0

Self-host / mo$429

Break-even—

Nemotron 3 Ultra

API / mo$0

Self-host / moNot listed

Break-even—

Proprietary model — self-hosting not applicable.

Model the full break-even

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

Gert Labs
Gemma 4 31B35.26%
Source
Nemotron 3 Ultra—
Not directly comparable
Terminal-Bench 2.0
Gemma 4 31B—
Nemotron 3 Ultra56.4%
Source
Not directly comparable
PinchBench
Gemma 4 31B—
Nemotron 3 Ultra90.0%
Source
Not directly comparable
BrowseComp
Gemma 4 31B—
Nemotron 3 Ultra44.4%
Source
Not directly comparable
τ³-bench results
Gemma 4 31B—
Nemotron 3 Ultra70.9%
Source
Not directly comparable
HLE w/ tools
Gemma 4 31B—
Nemotron 3 Ultra37.4%
Source
Not directly comparable

Coding

SWE-Rebench
Gemma 4 31B41.6%
Source
Nemotron 3 Ultra—
Not directly comparable
React Native Evals
Gemma 4 31B75.2%
Source
Nemotron 3 Ultra—
Not directly comparable
SWE-bench Verified
Gemma 4 31B—
Nemotron 3 Ultra71.9%
Source
Not directly comparable
SWE Multilingual
Gemma 4 31B—
Nemotron 3 Ultra67.7%
Source
Not directly comparable
LiveCodeBench v6
Gemma 4 31B—
Nemotron 3 Ultra89.0%
Source
Not directly comparable
SciCode
Gemma 4 31B—
Nemotron 3 Ultra44.6%
Source
Not directly comparable
Terminal-Bench 2.0
Gemma 4 31B—
Nemotron 3 Ultra56.4%
Source
Not directly comparable

Reasoning

CritPt
Gemma 4 31B—
Nemotron 3 Ultra3.1%
Source
Not directly comparable
LongBench v2
Gemma 4 31B—
Nemotron 3 Ultra61.9%
Source
Not directly comparable

Knowledge

GPQA
Gemma 4 31B84.3%
Source
Nemotron 3 Ultra87%
Source
Nemotron 3 Ultra leads this result
MMLU-Pro
Gemma 4 31B85.2%
Source
Nemotron 3 Ultra86.8%
Source
Nemotron 3 Ultra leads this result
HLE
Gemma 4 31B26.5%
Source
Nemotron 3 Ultra26.7%
Source
Nemotron 3 Ultra leads this result
HLE w/o tools
Gemma 4 31B19.5%
Source
Nemotron 3 Ultra26.7%
Source
Nemotron 3 Ultra leads this result
GPQA-D
Gemma 4 31B—
Nemotron 3 Ultra87.0%
Source
Not directly comparable

Multilingual

MMLU-ProX
Gemma 4 31B—
Nemotron 3 Ultra83%
Source
Not directly comparable

Multimodal

MMMU-Pro
Gemma 4 31B76.9%
Source
Nemotron 3 Ultra—
Not directly comparable

Instruction following

IFBench
Gemma 4 31B—
Nemotron 3 Ultra81.7%
Source
Not directly comparable

Frequently asked questions

Which is better, Gemma 4 31B or Nemotron 3 Ultra?

Gemma 4 31B has the higher public score estimate, 60.39 versus 46.32, 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 31B 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, Gemma 4 31B 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, Gemma 4 31B 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, Gemma 4 31B or Nemotron 3 Ultra?

Nemotron 3 Ultra 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 30, 2026

Watch Gemma 4 31B 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.

Gemma 4 31B vs Nemotron 3 Ultra

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

Reasoning

Math

Multilingual

Multimodal

Instruction following

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

Self-host vs API cost

Benchmark evidence

Agentic

Coding

Reasoning

Knowledge

Multilingual

Multimodal

Instruction following

Frequently asked questions

Which is better, Gemma 4 31B or Nemotron 3 Ultra?

Which is better for coding, Gemma 4 31B or Nemotron 3 Ultra?

Which is better for agentic tasks, Gemma 4 31B or Nemotron 3 Ultra?

Which costs less, Gemma 4 31B or Nemotron 3 Ultra?

Which has the larger context window, Gemma 4 31B or Nemotron 3 Ultra?

Related comparisons

Watch Gemma 4 31B vs Nemotron 3 Ultra