Gemini 3.1 Pro vs Gemma 4 31B

Updated September 30, 2026. Rank says Gemini 3.1 Pro is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Decision reading

Gemini 3.1 Pro has the higher public score estimate, 64.51 versus 40.39, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 4 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A

Gemini 3.1 Pro

Google

64.51/100

Estimated · Public rank #33

90% interval 58.4–70.6

Model B

Gemma 4 31B

Google

40.39/100

Estimated · Public rank #121

90% interval 16.0–64.8

Shared results: 4
Gemini 3.1 Pro only: 25
Gemma 4 31B only: 4
Like-for-like categories: 2 / 8

Estimated: Gemini 3.1 Pro and Gemma 4 31BHow the comparison works

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.

Coding work
Code generation, repair, and software-engineering tasks
Gemini 3.1 Pro
Gemini 3.1 Pro leads on the public coding lane, 42.5 to 35, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Long documents
Prompts that approach the documented context limit
Gemini 3.1 Pro
Gemini 3.1 Pro has the larger documented context window.
Confidence: documented

Show secondary and unsupported calls

Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Gemma 4 31B is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
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

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

Pick the job you would use them for

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

42.5Gemini 3.1 Pro35.0Gemma 4 31B

Like-for-like · BenchAlign v5.7

Gemini 3.1 Pro leads the like-for-like coding row, although the 90% intervals overlap.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboard Shortlist models for this job

Same basis rules as the category table below

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.

HLE w/o toolsKnowledge
Normalized gap 25.9
Gemini 3.1 Pro:45.4%
Gemma 4 31B:19.5%
Gemini 3.1 Pro source Gemma 4 31B source
MMMU-ProMultimodal
Normalized gap 7.0
Gemini 3.1 Pro:83.9%
Gemma 4 31B:76.9%
Gemini 3.1 Pro source Gemma 4 31B source

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.7 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Coding

Like-for-like

Gemini 3.1 Pro: 42.5; Supported · #59/144
Gemma 4 31B: 35.0; Supported · #81/144
Basis: BenchAlign v5.7 lane · 6 vs 2 public rows
Reading: Gemini 3.1 Pro leads · intervals overlap

Knowledge

Like-for-like

Gemini 3.1 Pro: 66.6; Supported · #21/170
Gemma 4 31B: 39.1; Supported · #103/170
Basis: BenchAlign v5.7 lane · 6 vs 4 public rows
Reading: Gemini 3.1 Pro leads

Agentic

Directional only

Gemini 3.1 Pro: 38.5; Supported · #59/119
Gemma 4 31B: 21.8; Estimated · #98/119
Basis: BenchAlign v5.7 lane · 6 vs 1 public rows
Reading: Directional only

Multimodal

Directional only

Gemini 3.1 Pro: 80.1; #13/49
Gemma 4 31B: 59.5; #31/49
Basis: Provisional lane · 2 vs 1 weighted rows
Reading: Directional only

Reasoning

Not comparable

Gemini 3.1 Pro: 54.5; Unranked · 2 rankable rows
Gemma 4 31B: 70.2; Unranked · 2 rankable rows
Basis: Provisional lane · 2 vs 0 weighted rows
Reading: Not comparable

Multilingual

Not comparable

Gemini 3.1 Pro: Not ranked
Gemma 4 31B: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Instruction following

Not comparable

Gemini 3.1 Pro: Not ranked
Gemma 4 31B: 91.5; #12/124
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Math

Not comparable

Gemini 3.1 Pro: 54.2; Unranked · 2 rankable rows
Gemma 4 31B: Not ranked
Basis: Provisional lane · 2 vs 0 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for Gemini 3.1 Pro and Gemma 4 31B
Category	Gemini 3.1 Pro	Gemma 4 31B	Basis	Reading
Coding	42.5Supported · #59/144	35.0Supported · #81/144	Like-for-likeBenchAlign v5.7 lane · 6 vs 2 public rows	Gemini 3.1 Pro leads · intervals overlap
Knowledge	66.6Supported · #21/170	39.1Supported · #103/170	Like-for-likeBenchAlign v5.7 lane · 6 vs 4 public rows	Gemini 3.1 Pro leads
Agentic	38.5Supported · #59/119	21.8Estimated · #98/119	Directional onlyBenchAlign v5.7 lane · 6 vs 1 public rows	Directional only
Multimodal	80.1#13/49	59.5#31/49	Directional onlyProvisional lane · 2 vs 1 weighted rows	Directional only
Reasoning	54.5Unranked · 2 rankable rows	70.2Unranked · 2 rankable rows	Not comparableProvisional lane · 2 vs 0 weighted rows	Not comparable
Multilingual	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Instruction following	Not ranked	91.5#12/124	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Math	54.2Unranked · 2 rankable rows	Not ranked	Not comparableProvisional lane · 2 vs 0 weighted rows	Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

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

Gemini 3.1 Pro: $0.008; Fits in one request
Gemma 4 31B: Self-hosted; infrastructure cost varies; Fits in one request

Gemma 4 31B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Gemini 3.1 Pro: $0.136; Fits in one request
Gemma 4 31B: Self-hosted; infrastructure cost varies; Fits in one request

Gemma 4 31B has no comparable published API token rate.

Cache-heavy agent loop

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

Gemini 3.1 Pro: $0.2; Fits in one request
Gemma 4 31B: Self-hosted; infrastructure cost varies; Fits in one request; Cached-input rate unavailable

Gemma 4 31B has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Reasoning

Weight access

Gemini 3.1 Pro

Proprietary

Gemma 4 31B

Open Weight

License

Gemini 3.1 Pro

Proprietary

Gemma 4 31B

Open Weight

Release date

Gemini 3.1 Pro

2026-02-19

Gemma 4 31B

2026-04-02

If you already use one of these models

Deployment change: Both entries list Google as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal: Gemini 3.1 Pro has the higher public score estimate, 64.51 versus 40.39, but the 90% score intervals overlap.
Workload cost: A complete comparable API-rate estimate is not available for both models.
Context tradeoff: Gemini 3.1 Pro has the larger documented window (1M).

Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Gemini 3.1 Pro or Gemma 4 31B?

Gemini 3.1 Pro has the higher public score estimate, 64.51 versus 40.39, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Gemini 3.1 Pro or Gemma 4 31B?

Gemini 3.1 Pro leads the public coding lane, 42.5 to 35, with Supported evidence for both models, although the 90% intervals overlap.

Which is better for agentic tasks, Gemini 3.1 Pro or Gemma 4 31B?

Gemini 3.1 Pro scores higher for agentic tasks on the public lane, 38.5 to 21.8. Gemma 4 31B is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, Gemini 3.1 Pro or Gemma 4 31B?

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, Gemini 3.1 Pro or Gemma 4 31B?

Gemini 3.1 Pro has the larger documented context window: 1M, compared with 256K.

Self-host vs API cost

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

Gemini 3.1 Pro

API / mo$10,500

Self-host / moNot listed

Break-even—

Proprietary model — self-hosting not applicable.

Gemma 4 31B

API / mo$0

Self-host / mo$429

Break-even—

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 evidence33 rows

Agentic

Claw-Eval
Gemini 3.1 Pro57.8%
Source
Gemma 4 31B—
Not directly comparable
DeepSearchQA
Gemini 3.1 Pro69.7%
Source
Gemma 4 31B—
Not directly comparable
τ²-bench results
Gemini 3.1 Pro95.6%
Source
Gemma 4 31B—
Not directly comparable
Gert Labs
Shared source
Gemini 3.1 Pro56.87%
Gemma 4 31B35.26%
Gemini 3.1 Pro leads this result
ResearchClawBench
Gemini 3.1 Pro13.3%
Source
Gemma 4 31B—
Not directly comparable
Terminal-Bench 2.1 (Vals)
Gemini 3.1 Pro70.8%
Source
Gemma 4 31B—
Not directly comparable

Coding

LiveCodeBench Pro
Gemini 3.1 Pro82.9%
Source
Gemma 4 31B—
Not directly comparable
React Native Evals
Shared source
Gemini 3.1 Pro78.9%
Gemma 4 31B75.2%
Gemini 3.1 Pro leads this result
Vibe Code Bench
Gemini 3.1 Pro32.03%
Source
Gemma 4 31B—
Not directly comparable
LiveCodeBench (Vals)
Gemini 3.1 Pro88.5%
Source
Gemma 4 31B—
Not directly comparable
SWE-bench (Vals)
Gemini 3.1 Pro78.8%
Source
Gemma 4 31B—
Not directly comparable
PostTrainBench v1.1
Gemini 3.1 Pro22.0%
Source
Gemma 4 31B—
Not directly comparable
SWE-Rebench
Gemini 3.1 Pro—
Gemma 4 31B41.6%
Source
Not directly comparable

Reasoning

ARC-AGI-2
Gemini 3.1 Pro77.1%
Source
Gemma 4 31B—
Not directly comparable
ARC-AGI-3
Gemini 3.1 Pro0.4%
Source
Gemma 4 31B—
Not directly comparable

Multimodal

MMMU-Pro
Gemini 3.1 Pro83.9%
Source
Gemma 4 31B76.9%
Source
Gemini 3.1 Pro leads this result
CharXiv
Gemini 3.1 Pro80.2%
Source
Gemma 4 31B—
Not directly comparable
ERQA
Gemini 3.1 Pro69.4%
Source
Gemma 4 31B—
Not directly comparable
SimpleVQA
Gemini 3.1 Pro72.4%
Source
Gemma 4 31B—
Not directly comparable
ScreenSpot Pro
Gemini 3.1 Pro84.4%
Source
Gemma 4 31B—
Not directly comparable
ZeroBench
Gemini 3.1 Pro29.0%
Source
Gemma 4 31B—
Not directly comparable
MedXpertQA (MM)
Gemini 3.1 Pro81.3%
Source
Gemma 4 31B—
Not directly comparable

Knowledge

GPQA-D
Gemini 3.1 Pro94.3%
Source
Gemma 4 31B—
Not directly comparable
HLE w/o tools
Gemini 3.1 Pro45.4%
Source
Gemma 4 31B19.5%
Source
Gemini 3.1 Pro leads this result
HealthBench Hard
Gemini 3.1 Pro20.6%
Source
Gemma 4 31B—
Not directly comparable
MedXpertQA (Text)
Gemini 3.1 Pro71.5%
Source
Gemma 4 31B—
Not directly comparable
GPQA Diamond (Vals)
Gemini 3.1 Pro95.5%
Source
Gemma 4 31B—
Not directly comparable
MMLU-Pro (Vals)
Gemini 3.1 Pro91.0%
Source
Gemma 4 31B—
Not directly comparable
GPQA
Gemini 3.1 Pro—
Gemma 4 31B84.3%
Source
Not directly comparable
MMLU-Pro
Gemini 3.1 Pro—
Gemma 4 31B85.2%
Source
Not directly comparable
HLE
Gemini 3.1 Pro—
Gemma 4 31B26.5%
Source
Not directly comparable

Math

FrontierMath v2 (Tiers 1-3)
Gemini 3.1 Pro36.900%
Source
Gemma 4 31B—
Not directly comparable
FrontierMath v2 (Tier 4)
Gemini 3.1 Pro16.700%
Source
Gemma 4 31B—
Not directly comparable

33 public results · 4 shared

Related comparisons

Compare API pricing Read the methodology Open the model selector

Watch Gemini 3.1 Pro vs Gemma 4 31B

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

Read a sample issue

Join 2,000+ readers.

Last updated September 30, 2026

Gemini 3.1 Pro vs Gemma 4 31B

Decision reading

Which one for your work

Coding work

Long documents

Agentic work

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

Which one for a specific job

What is actually comparable

Shape of the matched evidence

Category results, on a stated basis

Coding

Knowledge

Agentic

Multimodal

Reasoning

Multilingual

Instruction following

Math

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

If you already use one of these models

Questions

Which is better, Gemini 3.1 Pro or Gemma 4 31B?

Which is better for coding, Gemini 3.1 Pro or Gemma 4 31B?

Which is better for agentic tasks, Gemini 3.1 Pro or Gemma 4 31B?

Which costs less, Gemini 3.1 Pro or Gemma 4 31B?

Which has the larger context window, Gemini 3.1 Pro or Gemma 4 31B?

Self-host vs API cost

Benchmark evidence

Agentic

Coding

Reasoning

Multimodal

Knowledge

Math

Related comparisons

Watch Gemini 3.1 Pro vs Gemma 4 31B