Knowledge
Directional only- Gemma 4 31B
- 52.9
- Gemma 4 E4B
- 67.4
- Weighted basis
- 3 vs 2 rows
- Reading
- Directional only
Gemma 4 31B vs Gemma 4 E4B
Updated August 15, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload. This is a same-family comparison, so migration details appear when the source data supports them.
Decision reading
Gemma 4 31B has the higher public score estimate, 60.15 versus 43.25, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
2 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
Gemma 4 31B
Gemma 4 31B 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. Gemma 4 E4B does not fit this workload in one request. Gemma 4 31B has no comparable published API token rate. Gemma 4 E4B 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.
6 Gemma 4 31B only
2 Shared
- Shared results
- 2
- Gemma 4 31B only
- 6
- Gemma 4 E4B only
- 0
- 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.
Agentic
Not comparable- Gemma 4 31B
- Not measured
- Gemma 4 E4B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Coding
Not comparable- Gemma 4 31B
- 41.6
- Gemma 4 E4B
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- Gemma 4 31B
- Not measured
- Gemma 4 E4B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- Gemma 4 31B
- Not measured
- Gemma 4 E4B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Gemma 4 31B
- Not measured
- Gemma 4 E4B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Gemma 4 31B
- 76.9
- Gemma 4 E4B
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Gemma 4 31B
- Not measured
- Gemma 4 E4B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Gemma 4 31B | Gemma 4 E4B | Weighted basis | Reading |
|---|---|---|---|---|
| Knowledge | 52.9 | 67.4 | Directional only3 vs 2 rows | Directional only |
| Agentic | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Coding | 41.6 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Math | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | 76.9 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 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
MMLU-Pro
Knowledge
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
- Gemma 4 E4B
- Self-hosted; infrastructure cost varies
- Fits in one request
Gemma 4 31B has no comparable published API token rate. Gemma 4 E4B 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
- Gemma 4 E4B
- Self-hosted; infrastructure cost varies
- Fits in one request
Gemma 4 31B has no comparable published API token rate. Gemma 4 E4B 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
- Gemma 4 E4B
- Self-hosted; infrastructure cost varies
- Does not fit in one request
- Cached-input rate unavailable
Gemma 4 E4B does not fit this workload in one request. Gemma 4 31B has no comparable published API token rate. Gemma 4 E4B 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.
SpecificationGemma 4 31BGemma 4 E4B
Context window
Maximum documented context; output-token limits may be lower.
Gemma 4 31B
Gemma 4 E4B
API model ID
Gemma 4 31B
gemma-4-31b-it
Google Gemma Gemini API guideGemma 4 E4B
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Gemma 4 31B
No comparable hosted API rate
Gemma 4 E4B
No comparable hosted API rate
Documented inputs
Gemma 4 31B
text, image
Google Gemma 4 model documentationGemma 4 E4B
text, image, audio, video
Google Gemma 4 model documentationDocumented outputs
Gemma 4 31B
Gemma 4 E4B
Provider availability
Gemma 4 31B
Generally Available · Gemini API, Google AI Studio, open weights
Google Gemma Gemini API guideGemma 4 E4B
Open Weights · open weights
Google gemma-4-E4B model cardReasoning profile
Gemma 4 31B
Reasoning
Gemma 4 E4B
Reasoning
Weight access
Gemma 4 31B
Open Weight
Gemma 4 E4B
Open Weight
License
Gemma 4 31B
Open Weight
Gemma 4 E4B
Open Weight
Release date
Gemma 4 31B
2026-04-02
Gemma 4 E4B
2026-04-02
If you are choosing between sibling variants
- Deployment change
- Both entries list Google as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Gemma 4 31B has the higher public score estimate, 60.15 versus 43.25, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Gemma 4 31B has the larger documented window (256K).
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—
Gemma 4 E4B
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence8 rows
Agentic
Gert Labs
Gemma 4 31B35.26%SourceGemma 4 E4B—Not directly comparable
Coding
Knowledge
GPQA
Shared sourceGemma 4 31B84.3%Gemma 4 E4B58.6%Gemma 4 31B leads this result
MMLU-Pro
Gemma 4 31B85.2%SourceGemma 4 E4B69.4%SourceGemma 4 31B leads this result
HLE
Gemma 4 31B26.5%SourceGemma 4 E4B—Not directly comparable
HLE w/o tools
Gemma 4 31B19.5%SourceGemma 4 E4B—Not directly comparable
Multimodal
MMMU-Pro
Gemma 4 31B76.9%SourceGemma 4 E4B—Not directly comparable
Frequently asked questions
Which is better, Gemma 4 31B or Gemma 4 E4B?
Gemma 4 31B has the higher public score estimate, 60.15 versus 43.25, 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 Gemma 4 E4B?
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 Gemma 4 E4B?
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 Gemma 4 E4B?
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 Gemma 4 E4B?
Gemma 4 31B has the larger documented context window: 256K, compared with 128K.
Related comparisons
Last updated August 15, 2026
Watch Gemma 4 31B vs Gemma 4 E4B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.