Skip to main content

Model comparison

Gemma 4 31B vs Soofi S 30B-A3B

Data verified

Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use BenchLM's provisional ranking lane.

61/100
Margin
16.0pts
← winning
Soofi Project
45/100
1 category wins0 category wins

Evidence parity. Gemma 4 31B and Soofi S 30B-A3B share 2 comparable benchmark results. 1 of 8 categories are comparable. 28 results are unique to Gemma 4 31B; 6 to Soofi S 30B-A3B.

Updated July 15, 2026
Shared results
2
Gemma 4 31B only
28
Soofi S 30B-A3B only
6
Comparable categories
1 / 8

Pick Gemma 4 31B if you want the stronger benchmark profile. Soofi S 30B-A3B only becomes the better choice if you need the larger 1M context window or you would rather avoid the extra latency and token burn of a reasoning model.

Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 1 evidence category; 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, 61 to 45. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Gemma 4 31B's sharpest advantage is in knowledge, where it averages 53.3 against 49.9. The single biggest benchmark swing on the page is GPQA, 84.3% to 43.4%.

Gemma 4 31B is the reasoning model in the pair, while Soofi S 30B-A3B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Soofi S 30B-A3B gives you the larger context window at 1M, compared with 256K for Gemma 4 31B.

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 Soofi S 30B-A3B
CategoryGemma 4 31BΔSoofi S 30B-A3B
KnowledgeGemma 4 31B53.3Margin 3.4Soofi S 30B-A3B49.9
CodingGemma 4 31B41.6MarginNo overlapSoofi S 30B-A3BNot measured
MultimodalGemma 4 31B76.9MarginNo overlapSoofi S 30B-A3BNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Gemma 4 31BB · Soofi S 30B-A3B
  1. GPQA

    Knowledge
    Source ↗
    A 84.3%B 43.4%
    Winner: Gemma 4 31BΔ 40.9
    GPQA: Gemma 4 31B scored 84.3%; Soofi S 30B-A3B scored 43.4%. Gemma 4 31B wins this benchmark.
  2. MMLU-Pro

    Knowledge
    Source ↗
    A 85.2%B 51.4%
    Winner: Gemma 4 31BΔ 33.8
    MMLU-Pro: Gemma 4 31B scored 85.2%; Soofi S 30B-A3B scored 51.4%. Gemma 4 31B wins this benchmark.

Operational comparison

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

MetricGemma 4 31BSoofi S 30B-A3BComparison
Input / output priceUSD per 1M tokensGemma 4 31B$0 input / $0 outputSoofi S 30B-A3B$0 input / $0 outputListed prices are equal.
Generation speedtokens per secondGemma 4 31BNot availableSoofi S 30B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemma 4 31BNot availableSoofi S 30B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemma 4 31B256KSoofi S 30B-A3B1MSoofi S 30B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGemma 4 31BSoofi S 30B-A3BResult
AA Agentic IndexSource 14.4%Not comparable
τ²-bench resultsSource 59.9%Not comparable
GDPval-AASource 15.2%Not comparable
GDPval-AASource 804Not comparable
Gert LabsSource 35.26%Not comparable
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
Coding
BenchmarkGemma 4 31BSoofi S 30B-A3BResult
SWE-RebenchSource 41.6%Not comparable
React Native EvalsSource 75.2%Not comparable
AA Coding IndexSource 43.4%Not comparable
Terminal-Bench HardSource 36.4%Not comparable
AA-SciCodeSource 43.4%Not comparable
HumanEvalSource 73.8%Not comparable
Reasoning
BenchmarkGemma 4 31BSoofi S 30B-A3BResult
AA-LCRSource 62.0%Not comparable
CritPtSource 1.4%Not comparable
BBHSource 78.8%Not comparable
DROPSource 66.5%Not comparable
KnowledgeGemma 4 31B wins
BenchmarkGemma 4 31BSoofi S 30B-A3BResult
GPQASource 84.3%43.4%Gemma 4 31B leads
MMLU-ProSource 85.2%51.4%Gemma 4 31B leads
HLESource 26.5%Not comparable
HLE w/o toolsSource 19.5%Not comparable
Artificial Analysis Intelligence IndexSource 29.4%Not comparable
AA-GPQA DiamondSource 85.7%Not comparable
AA-HLESource 22.7%Not comparable
AA-Omniscience IndexSource -45.4%Not comparable
AA-Omniscience AccuracySource 19.9%Not comparable
AA-Omniscience Hallucination RateSource 81.6%Not comparable
AA Openness IndexSource 38.9%Not comparable
GPQA-DSource 43.4%Not comparable
AGIEvalSource 66.9%Not comparable
Math
BenchmarkGemma 4 31BSoofi S 30B-A3BResult
GSM8KSource 86.1%Not comparable
Multimodal
BenchmarkGemma 4 31BSoofi S 30B-A3BResult
MMMU-ProSource 76.9%Not comparable
AA-MMMU-ProSource 73.4%Not comparable
Inst. Following
BenchmarkGemma 4 31BSoofi S 30B-A3BResult
AA-IFBenchSource 75.6%Not comparable
Frequently Asked Questions (2)

Which is better, Gemma 4 31B or Soofi S 30B-A3B?

Gemma 4 31B is ahead on BenchLM's provisional leaderboard, 61 to 45. The biggest single separator in this matchup is GPQA, where the scores are 84.3% and 43.4%.

Which is better for knowledge tasks, Gemma 4 31B or Soofi S 30B-A3B?

Gemma 4 31B has the edge for knowledge tasks in this comparison, averaging 53.3 versus 49.9. Inside this category, GPQA 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
Soofi S 30B-A3B
API / mo$0
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Model the full break-even

Related Comparisons

Last updated: July 15, 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.