Skip to main content

Model comparison

Gemma 4 12B vs Soofi S 30B-A3B

Data verified

Head-to-head evidence from 4 shared benchmark results across 2 categories. Overall scores shown here use BenchLM's provisional ranking lane.

48/100
Margin
3.0pts
← winning
Soofi Project
45/100
1 category wins0 category wins

Evidence parity. Gemma 4 12B and Soofi S 30B-A3B share 4 comparable benchmark results. 1 of 8 categories are comparable. 21 results are unique to Gemma 4 12B; 4 to Soofi S 30B-A3B.

Updated July 15, 2026
Shared results
4
Gemma 4 12B only
21
Soofi S 30B-A3B only
4
Comparable categories
1 / 8

Pick Gemma 4 12B 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 4 shared benchmark results across 2 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 12B has the cleaner provisional overall profile here, landing at 48 versus 45. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Gemma 4 12B's sharpest advantage is in knowledge, where it averages 77.5 against 49.9. The single biggest benchmark swing on the page is GPQA, 78.8% to 43.4%.

Gemma 4 12B 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 12B.

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 12B and Soofi S 30B-A3B
CategoryGemma 4 12BΔSoofi S 30B-A3B
KnowledgeGemma 4 12B77.5Margin 27.6Soofi S 30B-A3B49.9
ReasoningGemma 4 12B43.4MarginNo overlapSoofi S 30B-A3BNot measured
MathGemma 4 12B77.5MarginNo overlapSoofi S 30B-A3BNot measured
MultimodalGemma 4 12B69.1MarginNo overlapSoofi S 30B-A3BNot measured

Decisive benchmark drivers

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

More
A · Gemma 4 12BB · Soofi S 30B-A3B
  1. GPQA

    Knowledge
    Source ↗
    A 78.8%B 43.4%
    Winner: Gemma 4 12BΔ 35.4
    GPQA: Gemma 4 12B scored 78.8%; Soofi S 30B-A3B scored 43.4%. Gemma 4 12B wins this benchmark.
  2. MMLU-Pro

    Knowledge
    Source ↗
    A 77.2%B 51.4%
    Winner: Gemma 4 12BΔ 25.8
    MMLU-Pro: Gemma 4 12B scored 77.2%; Soofi S 30B-A3B scored 51.4%. Gemma 4 12B wins this benchmark.

Operational comparison

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

MetricGemma 4 12BSoofi S 30B-A3BComparison
Input / output priceUSD per 1M tokensGemma 4 12BNot availableSoofi S 30B-A3B$0 input / $0 outputA complete price comparison is not available.
Generation speedtokens per secondGemma 4 12BNot availableSoofi S 30B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemma 4 12BNot availableSoofi S 30B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemma 4 12B256KSoofi S 30B-A3B1MSoofi S 30B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGemma 4 12BSoofi S 30B-A3BResult
τ²-bench resultsSource 36.3%Not comparable
Coding
BenchmarkGemma 4 12BSoofi S 30B-A3BResult
LiveCodeBench v6Source 72.0%Not comparable
Terminal-Bench HardSource 18.2%Not comparable
AA-SciCodeSource 38.2%Not comparable
HumanEvalSource 73.8%Not comparable
Reasoning
BenchmarkGemma 4 12BSoofi S 30B-A3BResult
BBHSource 53%78.8%Soofi S 30B-A3B leads
MRCRv2Source 43.4%Not comparable
AA-LCRSource 55.3%Not comparable
CritPtSource 0.0%Not comparable
DROPSource 66.5%Not comparable
KnowledgeGemma 4 12B wins
BenchmarkGemma 4 12BSoofi S 30B-A3BResult
GPQASource 78.8%43.4%Gemma 4 12B leads
GPQA-DSource 78.8%43.4%Gemma 4 12B leads
MMLU-ProSource 77.2%51.4%Gemma 4 12B leads
HLE w/o toolsSource 5.2%Not comparable
MMMLUSource 83.4%Not comparable
Artificial Analysis Intelligence IndexSource 22.0%Not comparable
AA-GPQA DiamondSource 75.3%Not comparable
AA-HLESource 14.8%Not comparable
AA-Omniscience IndexSource -51.9%Not comparable
AA-Omniscience AccuracySource 16.0%Not comparable
AA-Omniscience Hallucination RateSource 80.8%Not comparable
AGIEvalSource 66.9%Not comparable
Math
BenchmarkGemma 4 12BSoofi S 30B-A3BResult
AIME26Source 77.5%Not comparable
GSM8KSource 86.1%Not comparable
Multimodal
BenchmarkGemma 4 12BSoofi S 30B-A3BResult
MMMU-ProSource 69.1%Not comparable
MathVisionSource 79.7%Not comparable
MedXpertQA (MM)Source 48.7%Not comparable
AA-MMMU-ProSource 69.7%Not comparable
Inst. Following
BenchmarkGemma 4 12BSoofi S 30B-A3BResult
AA-IFBenchSource 73.5%Not comparable
Frequently Asked Questions (2)

Which is better, Gemma 4 12B or Soofi S 30B-A3B?

Gemma 4 12B is ahead on BenchLM's provisional leaderboard, 48 to 45. The biggest single separator in this matchup is GPQA, where the scores are 78.8% and 43.4%.

Which is better for knowledge tasks, Gemma 4 12B or Soofi S 30B-A3B?

Gemma 4 12B has the edge for knowledge tasks in this comparison, averaging 77.5 versus 49.9. Inside this category, GPQA is the benchmark that creates the most daylight between them.

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.