Skip to main content

Model comparison

Exaone 4.0 32B 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.

LG AI Research
51/100
Margin
6.0pts
← winning
Soofi Project
45/100
1 category wins0 category wins

Evidence parity. Exaone 4.0 32B and Soofi S 30B-A3B share 1 comparable benchmark result. 1 of 8 categories are comparable. 13 results are unique to Exaone 4.0 32B; 7 to Soofi S 30B-A3B.

Updated July 15, 2026
Shared results
1
Exaone 4.0 32B only
13
Soofi S 30B-A3B only
7
Comparable categories
1 / 8

Pick Exaone 4.0 32B 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 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

Exaone 4.0 32B is clearly ahead on the provisional aggregate, 51 to 45. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Exaone 4.0 32B's sharpest advantage is in knowledge, where it averages 81.8 against 49.9. The single biggest benchmark swing on the page is MMLU-Pro, 81.8% to 51.4%.

Exaone 4.0 32B 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 128K for Exaone 4.0 32B.

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 Exaone 4.0 32B and Soofi S 30B-A3B
CategoryExaone 4.0 32BΔSoofi S 30B-A3B
KnowledgeExaone 4.0 32B81.8Margin 31.9Soofi S 30B-A3B49.9

Decisive benchmark drivers

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

More
A · Exaone 4.0 32BB · Soofi S 30B-A3B
  1. MMLU-Pro

    Knowledge
    Source ↗
    A 81.8%B 51.4%
    Winner: Exaone 4.0 32BΔ 30.4
    MMLU-Pro: Exaone 4.0 32B scored 81.8%; Soofi S 30B-A3B scored 51.4%. Exaone 4.0 32B wins this benchmark.

Operational comparison

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

MetricExaone 4.0 32BSoofi S 30B-A3BComparison
Input / output priceUSD per 1M tokensExaone 4.0 32BNot availableSoofi S 30B-A3B$0 input / $0 outputA complete price comparison is not available.
Generation speedtokens per secondExaone 4.0 32BNot availableSoofi S 30B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenExaone 4.0 32BNot availableSoofi S 30B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensExaone 4.0 32B128KSoofi S 30B-A3B1MSoofi S 30B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkExaone 4.0 32BSoofi S 30B-A3BResult
τ²-bench resultsSource 4.1%Not comparable
Coding
BenchmarkExaone 4.0 32BSoofi S 30B-A3BResult
Terminal-Bench HardSource 1.5%Not comparable
AA-SciCodeSource 25.2%Not comparable
HumanEvalSource 73.8%Not comparable
Reasoning
BenchmarkExaone 4.0 32BSoofi S 30B-A3BResult
AA-LCRSource 8.0%Not comparable
CritPtSource 0.0%Not comparable
BBHSource 78.8%Not comparable
DROPSource 66.5%Not comparable
KnowledgeExaone 4.0 32B wins
BenchmarkExaone 4.0 32BSoofi S 30B-A3BResult
MMLU-ProSource 81.8%51.4%Exaone 4.0 32B leads
Artificial Analysis Intelligence IndexSource 6.0%Not comparable
AA-GPQA DiamondSource 62.8%Not comparable
AA-HLESource 4.9%Not comparable
AA-Omniscience IndexSource -62.3%Not comparable
AA-Omniscience AccuracySource 10.4%Not comparable
AA-Omniscience Hallucination RateSource 81.0%Not comparable
GPQASource 43.4%Not comparable
GPQA-DSource 43.4%Not comparable
AGIEvalSource 66.9%Not comparable
Math
BenchmarkExaone 4.0 32BSoofi S 30B-A3BResult
AIME 2025Source 85.3%Not comparable
GSM8KSource 86.1%Not comparable
Inst. Following
BenchmarkExaone 4.0 32BSoofi S 30B-A3BResult
AA-IFBenchSource 33.5%Not comparable
Frequently Asked Questions (2)

Which is better, Exaone 4.0 32B or Soofi S 30B-A3B?

Exaone 4.0 32B is ahead on BenchLM's provisional leaderboard, 51 to 45. The biggest single separator in this matchup is MMLU-Pro, where the scores are 81.8% and 51.4%.

Which is better for knowledge tasks, Exaone 4.0 32B or Soofi S 30B-A3B?

Exaone 4.0 32B has the edge for knowledge tasks in this comparison, averaging 81.8 versus 49.9. 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.