Skip to main content

Model comparison

Gemma 4 31B vs Step 3.7 Flash

Data verified

Head-to-head evidence from 18 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

61/100
Margin
10.2pts
← winning
50.76/100
0 category wins1 category wins

BenchAlign evidence: Gemma 4 31B supported; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemma 4 31B and Step 3.7 Flash share 18 comparable benchmark results. 1 of 8 categories are comparable. 12 results are unique to Gemma 4 31B; 12 to Step 3.7 Flash.

Updated July 16, 2026
Shared results
18
Gemma 4 31B only
12
Step 3.7 Flash only
12
Comparable categories
1 / 8

Pick Gemma 4 31B if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if coding is the priority.

Confidence note. This is a partial-evidence comparison with 18 shared benchmark results across 6 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Gemma 4 31B is clearly ahead on the provisional aggregate, 62 to 57. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Step 3.7 Flash is also the more expensive model on tokens at $0.20 input / $1.15 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Gemma 4 31B. That is roughly Infinityx on output cost alone.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Gemma 4 31B and Step 3.7 Flash
CategoryGemma 4 31BΔStep 3.7 Flash
CodingGemma 4 31B41.6Margin 14.7Step 3.7 Flash56.3
AgenticGemma 4 31BNot measuredMarginNo overlapStep 3.7 Flash66.4
KnowledgeGemma 4 31B53.3MarginNo overlapStep 3.7 FlashNot measured
MultimodalGemma 4 31B76.9MarginNo overlapStep 3.7 FlashNot measured

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGemma 4 31BStep 3.7 FlashComparison
Input / output priceUSD per 1M tokensGemma 4 31B$0 input / $0 outputStep 3.7 Flash$0.2 input / $1.15 outputGemma 4 31B has the lower combined listed price.
Generation speedtokens per secondGemma 4 31BNot availableStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemma 4 31BNot availableStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemma 4 31B256KStep 3.7 Flash256KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkGemma 4 31BStep 3.7 FlashResult
AA Agentic IndexSource 14.4%21.5%Step 3.7 Flash leads
τ²-bench resultsSource 59.9%98.5%Step 3.7 Flash leads
GDPval-AASource 15.2%25.9%Step 3.7 Flash leads
GDPval-AASource 8041017Step 3.7 Flash leads
Gert LabsSource 35.26%51.57%Step 3.7 Flash leads
AA EnterpriseOps-GymSource 28.3%Not comparable
AA Harvey LABSource 0.0%Not comparable
AA ITBenchSource 37.3%Not comparable
AA Tau3 BankingSource 15.1%Not comparable
Terminal-Bench 2.0Source 59.5%Not comparable
BrowseCompSource 75.8%Not comparable
DeepSearchQASource 92.8%Not comparable
ToolathlonSource 49.5%Not comparable
Claw-EvalSource 67.1%Not comparable
HLE w/ toolsSource 47.2%Not comparable
APEX-Agents-AASource 14.8%Not comparable
CodingStep 3.7 Flash wins
BenchmarkGemma 4 31BStep 3.7 FlashResult
SWE-RebenchSource 41.6%Not comparable
React Native EvalsSource 75.2%Not comparable
AA Coding IndexSource 43.4%39.6%Gemma 4 31B leads
Terminal-Bench HardSource 36.4%35.6%Gemma 4 31B leads
AA-SciCodeSource 43.4%40.0%Gemma 4 31B leads
SWE-bench ProSource 56.3%Not comparable
Terminal-Bench 2.0Source 59.5%Not comparable
Reasoning
BenchmarkGemma 4 31BStep 3.7 FlashResult
AA-LCRSource 62.0%63.7%Step 3.7 Flash leads
CritPtSource 1.4%2.3%Step 3.7 Flash leads
Knowledge
BenchmarkGemma 4 31BStep 3.7 FlashResult
GPQASource 84.3%Not comparable
MMLU-ProSource 85.2%Not comparable
HLESource 26.5%Not comparable
HLE w/o toolsSource 19.5%Not comparable
Artificial Analysis Intelligence IndexSource 29.4%30.3%Step 3.7 Flash leads
AA-GPQA DiamondSource 85.7%80.9%Gemma 4 31B leads
AA-HLESource 22.7%19.9%Gemma 4 31B leads
AA-Omniscience IndexSource -45.4%-37.5%Step 3.7 Flash leads
AA-Omniscience AccuracySource 19.9%25.4%Step 3.7 Flash leads
AA-Omniscience Hallucination RateSource 81.6%84.4%Gemma 4 31B leads
AA Openness IndexSource 38.9%Not comparable
Multimodal
BenchmarkGemma 4 31BStep 3.7 FlashResult
MMMU-ProSource 76.9%Not comparable
AA-MMMU-ProSource 73.4%75.3%Step 3.7 Flash leads
SimpleVQASource 79.2%Not comparable
V*Source 95.3%Not comparable
Design Arena WebsiteSource 1218Not comparable
Inst. Following
BenchmarkGemma 4 31BStep 3.7 FlashResult
AA-IFBenchSource 75.6%67.3%Gemma 4 31B leads
Frequently Asked Questions (2)

Which is better, Gemma 4 31B or Step 3.7 Flash?

Gemma 4 31B is ahead on BenchLM's provisional leaderboard, 62 to 57.

Which is better for coding, Gemma 4 31B or Step 3.7 Flash?

Step 3.7 Flash has the edge for coding in this comparison, averaging 56.3 versus 41.6. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

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.
Model the full break-even

Related Comparisons

Last updated: July 16, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.