Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Step 3.7 Flash is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Gemma 4 31B vs Step 3.7 Flash
Updated October 14, 2026. Rank says Step 3.7 Flash is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Decision reading
Step 3.7 Flash has the higher public point estimate, 43.74 versus 39.95. Their conditional score ranges overlap. These ranges do not establish rank confidence. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 1
- Gemma 4 31B only
- 9
- Step 3.7 Flash only
- 10
- Like-for-like categories
- 0 / 8
Estimated: Gemma 4 31B and Step 3.7 Flash. Conditional ranges do not establish rank confidence.How 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.
No workload recommendation clears the current evidence threshold.
Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.
Show secondary and unsupported calls
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Gemma 4 31B and Step 3.7 Flash are scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limitedLong documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documentedChat 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-ratesCache-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: rate-fallbackRepository 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.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
31.7Gemma 4 31B30.2Step 3.7 Flash
Directional only · BenchAlign v5.8
Gemma 4 31B has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
9 Gemma 4 31B only
1 Shared
10 Step 3.7 Flash only
4 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.8 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.
Agentic
Directional only- Gemma 4 31B
- 19.9
- Estimated · #106/125
- Step 3.7 Flash
- 37.3
- Estimated · #73/125
- Basis
- BenchAlign v5.8 lane · 1 vs 7 public rows
- Reading
- Directional only
Coding
Directional only- Gemma 4 31B
- 31.7
- Supported · #89/149
- Step 3.7 Flash
- 30.2
- Estimated · #95/149
- Basis
- BenchAlign v5.8 lane · 3 vs 2 public rows
- Reading
- Directional only
Knowledge
Directional only- Gemma 4 31B
- 41.0
- Supported · #111/181
- Step 3.7 Flash
- 45.0
- Estimated · #95/181
- Basis
- BenchAlign v5.8 lane · 4 vs 0 public rows
- Reading
- Directional only
Instruction following
Directional only- Gemma 4 31B
- 92.9
- #15/144
- Step 3.7 Flash
- 82.1
- #54/144
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Reasoning
Not comparable- Gemma 4 31B
- 66.6
- Unranked · 3 rankable rows
- Step 3.7 Flash
- 76.5
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Gemma 4 31B
- 74.3
- #26/54
- Step 3.7 Flash
- 75.4
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Gemma 4 31B
- Not ranked
- Step 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Gemma 4 31B
- Not ranked
- Step 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Gemma 4 31B | Step 3.7 Flash | Basis | Reading |
|---|---|---|---|---|
| Agentic | 19.9Estimated · #106/125 | 37.3Estimated · #73/125 | Directional onlyBenchAlign v5.8 lane · 1 vs 7 public rows | Directional only |
| Coding | 31.7Supported · #89/149 | 30.2Estimated · #95/149 | Directional onlyBenchAlign v5.8 lane · 3 vs 2 public rows | Directional only |
| Knowledge | 41.0Supported · #111/181 | 45.0Estimated · #95/181 | Directional onlyBenchAlign v5.8 lane · 4 vs 0 public rows | Directional only |
| Instruction following | 92.9#15/144 | 82.1#54/144 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Reasoning | 66.6Unranked · 3 rankable rows | 76.5Unranked · 2 rankable rows | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multimodal | 74.3#26/54 | 75.4Unranked · 3 rankable rows | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) 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
- Gemma 4 31B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Step 3.7 Flash
- $0.00077
- Fits in one request
Gemma 4 31B 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
- Step 3.7 Flash
- $0.01345
- 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
- Gemma 4 31B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
- Step 3.7 Flash
- $0.0555
- Fits in one request
- Cached input priced at the published list-input rate
Step 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate. 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
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGemma 4 31BStep 3.7 Flash
Context window
Maximum documented context; output-token limits may be lower.
Gemma 4 31B
Step 3.7 Flash
256K
API model ID
Gemma 4 31B
gemma-4-31b-it
Google Gemma Gemini API guideStep 3.7 Flash
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
Step 3.7 Flash
Not published
Documented inputs
Gemma 4 31B
text, image
Google Gemma 4 model documentationStep 3.7 Flash
Not sourced
Documented outputs
Gemma 4 31B
Step 3.7 Flash
Not sourced
Provider availability
Gemma 4 31B
Generally Available · Gemini API, Google AI Studio, open weights
Google Gemma Gemini API guideStep 3.7 Flash
Not sourced
Reasoning profile
Gemma 4 31B
Reasoning
Step 3.7 Flash
Reasoning
Weight access
Gemma 4 31B
Open Weight
Step 3.7 Flash
Open Weight
License
Gemma 4 31B
Open Weight
Step 3.7 Flash
Open Weight
Release date
Gemma 4 31B
2026-04-02
Step 3.7 Flash
2026-05-29
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
- Step 3.7 Flash has the higher public point estimate, 43.74 versus 39.95. Their conditional score ranges overlap. These ranges do not establish rank confidence.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Both models list 256K.
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Gemma 4 31B or Step 3.7 Flash?
Step 3.7 Flash has the higher public point estimate, 43.74 versus 39.95. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Gemma 4 31B or Step 3.7 Flash?
Gemma 4 31B scores higher for coding on the public lane, 31.7 to 30.2. Step 3.7 Flash is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Gemma 4 31B or Step 3.7 Flash?
Step 3.7 Flash scores higher for agentic tasks on the public lane, 37.3 to 19.9. Gemma 4 31B and Step 3.7 Flash are 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, Gemma 4 31B or Step 3.7 Flash?
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 Step 3.7 Flash?
Both models list the same context window, 256K.
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—
Step 3.7 Flash
API / mo$1,012
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 evidence20 rows
Agentic
Gert Labs
Shared sourceGemma 4 31B35.26%Step 3.7 Flash51.57%Step 3.7 Flash leads this result
Terminal-Bench 2.1
Gemma 4 31B—Step 3.7 Flash59.5%SourceNot directly comparable
BrowseComp
Gemma 4 31B—Step 3.7 Flash75.8%SourceNot directly comparable
DeepSearchQA
Gemma 4 31B—Step 3.7 Flash92.8%SourceNot directly comparable
Toolathlon
Gemma 4 31B—Step 3.7 Flash49.5%SourceNot directly comparable
Claw-Eval
Gemma 4 31B—Step 3.7 Flash67.1%SourceNot directly comparable
HLE w/ tools
Gemma 4 31B—Step 3.7 Flash47.2%SourceNot directly comparable
Coding
LiveCodeBench v6
Gemma 4 31B80.0%SourceStep 3.7 Flash—Not directly comparable
SWE-Rebench
Gemma 4 31B41.6%SourceStep 3.7 Flash—Not directly comparable
React Native Evals
Gemma 4 31B75.2%SourceStep 3.7 Flash—Not directly comparable
SWE-bench Pro
Gemma 4 31B—Step 3.7 Flash56.3%SourceNot directly comparable
Terminal-Bench 2.1
Gemma 4 31B—Step 3.7 Flash59.5%SourceNot directly comparable
Reasoning
MRCRv2
Gemma 4 31B66.4%SourceStep 3.7 Flash—Not directly comparable
Multimodal
Knowledge
20 public results · 1 shared
Watch Gemma 4 31B vs Step 3.7 Flash
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,500+ readers.
Last updated October 14, 2026