Skip to main content

Model comparison

Gemma 4 26B A4B vs Soofi S 30B-A3B

Data verified

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

56/100
Margin
11.0pts
← winning
Soofi Project
45/100
0 category wins1 category wins

Evidence parity. Gemma 4 26B A4B and Soofi S 30B-A3B share 1 comparable benchmark result. 1 of 8 categories are comparable. 20 results are unique to Gemma 4 26B A4B; 7 to Soofi S 30B-A3B.

Updated July 15, 2026
Shared results
1
Gemma 4 26B A4B only
20
Soofi S 30B-A3B only
7
Comparable categories
1 / 8

Pick Gemma 4 26B A4B if you want the stronger benchmark profile. Soofi S 30B-A3B only becomes the better choice if knowledge is the priority or you need the larger 1M context window.

Confidence note. This is a partial-evidence comparison with 1 shared benchmark result 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 26B A4B is clearly ahead on the provisional aggregate, 56 to 45. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Gemma 4 26B A4B 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 26B A4B.

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 26B A4B and Soofi S 30B-A3B
CategoryGemma 4 26B A4BΔSoofi S 30B-A3B
KnowledgeGemma 4 26B A4B43.8Margin 6.1Soofi S 30B-A3B49.9
MultimodalGemma 4 26B A4B73.8MarginNo overlapSoofi S 30B-A3BNot measured

Decisive benchmark drivers

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

More
A · Gemma 4 26B A4BB · Soofi S 30B-A3B
  1. MMLU-Pro

    Knowledge
    Source ↗
    A 82.6%B 51.4%
    Winner: Gemma 4 26B A4BΔ 31.2
    MMLU-Pro: Gemma 4 26B A4B scored 82.6%; Soofi S 30B-A3B scored 51.4%. Gemma 4 26B A4B wins this benchmark.

Operational comparison

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

MetricGemma 4 26B A4BSoofi S 30B-A3BComparison
Input / output priceUSD per 1M tokensGemma 4 26B A4B$0 input / $0 outputSoofi S 30B-A3B$0 input / $0 outputListed prices are equal.
Generation speedtokens per secondGemma 4 26B A4BNot availableSoofi S 30B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemma 4 26B A4BNot availableSoofi S 30B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemma 4 26B A4B256KSoofi S 30B-A3B1MSoofi S 30B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGemma 4 26B A4BSoofi S 30B-A3BResult
AA Agentic IndexSource 11.0%Not comparable
τ²-bench resultsSource 43.6%Not comparable
GDPval-AASource 13.1%Not comparable
GDPval-AASource 761Not comparable
Coding
BenchmarkGemma 4 26B A4BSoofi S 30B-A3BResult
AA Coding IndexSource 39.3%Not comparable
Terminal-Bench HardSource 13.6%Not comparable
AA-SciCodeSource 40.0%Not comparable
HumanEvalSource 73.8%Not comparable
Reasoning
BenchmarkGemma 4 26B A4BSoofi S 30B-A3BResult
AA-LCRSource 55.7%Not comparable
CritPtSource 0.0%Not comparable
BBHSource 78.8%Not comparable
DROPSource 66.5%Not comparable
KnowledgeSoofi S 30B-A3B wins
BenchmarkGemma 4 26B A4BSoofi S 30B-A3BResult
MMLU-ProSource 82.6%51.4%Gemma 4 26B A4B leads
HLESource 17.2%Not comparable
HLE w/o toolsSource 8.7%Not comparable
Artificial Analysis Intelligence IndexSource 25.7%Not comparable
AA-GPQA DiamondSource 79.2%Not comparable
AA-HLESource 18.3%Not comparable
AA-Omniscience IndexSource -48.1%Not comparable
AA-Omniscience AccuracySource 18.2%Not comparable
AA-Omniscience Hallucination RateSource 80.9%Not comparable
GPQASource 43.4%Not comparable
GPQA-DSource 43.4%Not comparable
AGIEvalSource 66.9%Not comparable
Math
BenchmarkGemma 4 26B A4BSoofi S 30B-A3BResult
GSM8KSource 86.1%Not comparable
Multimodal
BenchmarkGemma 4 26B A4BSoofi S 30B-A3BResult
MMMU-ProSource 73.8%Not comparable
AA-MMMU-ProSource 69.2%Not comparable
Inst. Following
BenchmarkGemma 4 26B A4BSoofi S 30B-A3BResult
AA-IFBenchSource 72.4%Not comparable
Frequently Asked Questions (2)

Which is better, Gemma 4 26B A4B or Soofi S 30B-A3B?

Gemma 4 26B A4B is ahead on BenchLM's provisional leaderboard, 56 to 45. The biggest single separator in this matchup is MMLU-Pro, where the scores are 82.6% and 51.4%.

Which is better for knowledge tasks, Gemma 4 26B A4B or Soofi S 30B-A3B?

Soofi S 30B-A3B has the edge for knowledge tasks in this comparison, averaging 49.9 versus 43.8. Inside this category, MMLU-Pro 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.