Skip to main content
BenchLM
Advertise

Model comparison

Soofi S 30B-A3B vs ZAYA1-74B-Preview

Data verified

Head-to-head evidence from 3 shared benchmark results across 1 category. Overall scores shown here use BenchLM's provisional ranking lane.

Soofi S 30B-A3B
Soofi Project
45/100
Margin
11.0pts
winning →
56/100
0 category wins1 category wins

Evidence parity. Soofi S 30B-A3B and ZAYA1-74B-Preview share 3 comparable benchmark results. 1 of 8 categories are comparable. 5 results are unique to Soofi S 30B-A3B; 4 to ZAYA1-74B-Preview.

Updated July 15, 2026
Shared results
3
Soofi S 30B-A3B only
5
ZAYA1-74B-Preview only
4
Comparable categories
1 / 8

Pick ZAYA1-74B-Preview 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 3 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

ZAYA1-74B-Preview 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.

ZAYA1-74B-Preview's sharpest advantage is in knowledge, where it averages 66.1 against 49.9. The single biggest benchmark swing on the page is MMLU-Pro, 51.4% to 68.1%.

ZAYA1-74B-Preview 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 ZAYA1-74B-Preview.

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 Soofi S 30B-A3B and ZAYA1-74B-Preview
CategorySoofi S 30B-A3BΔZAYA1-74B-Preview
KnowledgeSoofi S 30B-A3B49.9Margin→ 16.2ZAYA1-74B-Preview66.1
CodingSoofi S 30B-A3BNot measuredMarginNo overlapZAYA1-74B-Preview53.2
MathSoofi S 30B-A3BNot measuredMarginNo overlapZAYA1-74B-Preview76.4

Decisive benchmark drivers

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

More
A · Soofi S 30B-A3BB · ZAYA1-74B-Preview

  1. MMLU-Pro

    Knowledge
    Source ↗
    A 51.4%B 68.1%
    Winner: ZAYA1-74B-PreviewΔ 16.7
    MMLU-Pro: Soofi S 30B-A3B scored 51.4%; ZAYA1-74B-Preview scored 68.1%. ZAYA1-74B-Preview wins this benchmark.

  2. GPQA

    Knowledge
    Source ↗
    A 43.4%B 57.3%
    Winner: ZAYA1-74B-PreviewΔ 13.9
    GPQA: Soofi S 30B-A3B scored 43.4%; ZAYA1-74B-Preview scored 57.3%. ZAYA1-74B-Preview wins this benchmark.

Operational comparison

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

MetricSoofi S 30B-A3BZAYA1-74B-PreviewComparison
Input / output priceUSD per 1M tokensSoofi S 30B-A3B$0 input / $0 outputZAYA1-74B-Preview$0 input / $0 outputListed prices are equal.
Generation speedtokens per secondSoofi S 30B-A3BNot availableZAYA1-74B-PreviewNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenSoofi S 30B-A3BNot availableZAYA1-74B-PreviewNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensSoofi S 30B-A3B1MZAYA1-74B-Preview256KSoofi S 30B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkSoofi S 30B-A3BZAYA1-74B-PreviewResult
τ²-bench AirlineSource —56.1%Not comparable
Coding
BenchmarkSoofi S 30B-A3BZAYA1-74B-PreviewResult
HumanEvalSource 73.8%—Not comparable
LiveCodeBench v6Source —65.7%Not comparable
SWE-bench VerifiedSource —53.2%Not comparable
Reasoning
BenchmarkSoofi S 30B-A3BZAYA1-74B-PreviewResult
BBHSource 78.8%—Not comparable
DROPSource 66.5%—Not comparable
KnowledgeZAYA1-74B-Preview wins
BenchmarkSoofi S 30B-A3BZAYA1-74B-PreviewResult
GPQASource 43.4%57.3%ZAYA1-74B-Preview leads
GPQA-DSource 43.4%57.3%ZAYA1-74B-Preview leads
MMLU-ProSource 51.4%68.1%ZAYA1-74B-Preview leads
AGIEvalSource 66.9%—Not comparable
Math
BenchmarkSoofi S 30B-A3BZAYA1-74B-PreviewResult
GSM8KSource 86.1%—Not comparable
AIME26Source —76.4%Not comparable
Frequently Asked Questions (2)

Which is better, Soofi S 30B-A3B or ZAYA1-74B-Preview?

ZAYA1-74B-Preview is ahead on BenchLM's provisional leaderboard, 56 to 45. The biggest single separator in this matchup is MMLU-Pro, where the scores are 51.4% and 68.1%.

Which is better for knowledge tasks, Soofi S 30B-A3B or ZAYA1-74B-Preview?

ZAYA1-74B-Preview has the edge for knowledge tasks in this comparison, averaging 66.1 versus 49.9. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Soofi Project Compare Pricing Methodology Find Your Best LLM Overall Rankings
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.