Model comparison

Qwen3.6-27B vs Soofi S 30B-A3B

Data verified July 15, 2026

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

Qwen3.6-27B

Alibaba

65/100

Margin

20.0pts

← winning

Soofi S 30B-A3B

Soofi Project

45/100

1 category wins0 category wins

Verified leaderboard positions: Qwen3.6-27B #26; Soofi S 30B-A3B unranked

Evidence parity. Qwen3.6-27B and Soofi S 30B-A3B share 2 comparable benchmark results. 1 of 8 categories are comparable. 53 results are unique to Qwen3.6-27B; 6 to Soofi S 30B-A3B.

Updated July 15, 2026

Shared results: 2
Qwen3.6-27B only: 53
Soofi S 30B-A3B only: 6
Comparable categories: 1 / 8

Pick Qwen3.6-27B 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

Qwen3.6-27B is clearly ahead on the provisional aggregate, 65 to 45. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.6-27B's sharpest advantage is in knowledge, where it averages 53.6 against 49.9. The single biggest benchmark swing on the page is GPQA, 87.8% to 43.4%.

Qwen3.6-27B 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 262K for Qwen3.6-27B.

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 Qwen3.6-27B and Soofi S 30B-A3B
Category	Qwen3.6-27B	Δ	Soofi S 30B-A3B
Knowledge	Qwen3.6-27B53.6	Margin← 3.7	Soofi S 30B-A3B49.9
Agentic	Qwen3.6-27B59.3	MarginNo overlap	Soofi S 30B-A3BNot measured
Coding	Qwen3.6-27B70.6	MarginNo overlap	Soofi S 30B-A3BNot measured
Math	Qwen3.6-27B89.2	MarginNo overlap	Soofi S 30B-A3BNot measured
Multimodal	Qwen3.6-27B76.7	MarginNo overlap	Soofi S 30B-A3BNot measured

Decisive benchmark drivers

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

A · Qwen3.6-27BB · Soofi S 30B-A3B

GPQA
Knowledge
Source ↗
A 87.8%B 43.4%
Winner: Qwen3.6-27BΔ 44.4
GPQA: Qwen3.6-27B scored 87.8%; Soofi S 30B-A3B scored 43.4%. Qwen3.6-27B wins this benchmark.
MMLU-Pro
Knowledge
Source ↗
A 86.2%B 51.4%
Winner: Qwen3.6-27BΔ 34.8
MMLU-Pro: Qwen3.6-27B scored 86.2%; Soofi S 30B-A3B scored 51.4%. Qwen3.6-27B wins this benchmark.

Operational comparison

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

Metric	Qwen3.6-27B	Soofi S 30B-A3B	Comparison
Input / output priceUSD per 1M tokens	Qwen3.6-27B$0 input / $0 output	Soofi S 30B-A3B$0 input / $0 output	Listed prices are equal.
Generation speedtokens per second	Qwen3.6-27BNot available	Soofi S 30B-A3BNot available	A complete speed comparison is not available.
First-answer latencyseconds to first token	Qwen3.6-27BNot available	Soofi S 30B-A3BNot available	A complete latency comparison is not available.
Context windowmaximum listed tokens	Qwen3.6-27B262K	Soofi S 30B-A3B1M	Soofi S 30B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic

10 benchmarks

Benchmark	Qwen3.6-27B	Soofi S 30B-A3B	Result
Terminal-Bench 2.0Source	59.3%	—	Not comparable
Claw-EvalSource	72.4%	—	Not comparable
QwenClawBenchSource	53.4%	—	Not comparable
QwenWebBenchSource	1487	—	Not comparable
AndroidWorldSource	70.3%	—	Not comparable
AA Agentic IndexSource	27.0%	—	Not comparable
τ²-bench resultsSource	94.2%	—	Not comparable
GDPval-AASource	32.0%	—	Not comparable
GDPval-AASource	1140	—	Not comparable
Gert LabsSource	54.84%	—	Not comparable

Coding

10 benchmarks

Benchmark	Qwen3.6-27B	Soofi S 30B-A3B	Result
SWE-bench VerifiedSource	77.2%	—	Not comparable
SWE MultilingualSource	71.3%	—	Not comparable
SWE-bench ProSource	53.5%	—	Not comparable
Terminal-Bench 2.0Source	59.3%	—	Not comparable
LiveCodeBenchSource	83.9%	—	Not comparable
NL2RepoSource	36.2%	—	Not comparable
AA Coding IndexSource	53.7%	—	Not comparable
Terminal-Bench HardSource	34.8%	—	Not comparable
AA-SciCodeSource	39.8%	—	Not comparable
HumanEvalSource	—	73.8%	Not comparable

Reasoning

4 benchmarks

Benchmark	Qwen3.6-27B	Soofi S 30B-A3B	Result
AA-LCRSource	68.7%	—	Not comparable
CritPtSource	1.1%	—	Not comparable
BBHSource	—	78.8%	Not comparable
DROPSource	—	66.5%	Not comparable

KnowledgeQwen3.6-27B wins

14 benchmarks

Benchmark	Qwen3.6-27B	Soofi S 30B-A3B	Result
MMLU-ProSource	86.2%	51.4%	Qwen3.6-27B leads
MMLU-ReduxSource	93.5%	—	Not comparable
SuperGPQASource	66%	—	Not comparable
C-EvalSource	91.4%	—	Not comparable
GPQASource	87.8%	43.4%	Qwen3.6-27B leads
HLESource	24%	—	Not comparable
Artificial Analysis Intelligence IndexSource	37.0%	—	Not comparable
AA-GPQA DiamondSource	84.2%	—	Not comparable
AA-HLESource	21.6%	—	Not comparable
AA-Omniscience IndexSource	-19.8%	—	Not comparable
AA-Omniscience AccuracySource	19.2%	—	Not comparable
AA-Omniscience Hallucination RateSource	48.3%	—	Not comparable
GPQA-DSource	—	43.4%	Not comparable
AGIEvalSource	—	66.9%	Not comparable

Math

6 benchmarks

Benchmark	Qwen3.6-27B	Soofi S 30B-A3B	Result
HMMT Feb 2025Source	93.8%	—	Not comparable
HMMT Nov 2025Source	90.7%	—	Not comparable
HMMT Feb 2026Source	84.3%	—	Not comparable
MMAnswerBenchSource	80.8%	—	Not comparable
AIME26Source	94.1%	—	Not comparable
GSM8KSource	—	86.1%	Not comparable

Multimodal

16 benchmarks

Benchmark	Qwen3.6-27B	Soofi S 30B-A3B	Result
MMMUSource	82.9%	—	Not comparable
MMMU-ProSource	75.8%	—	Not comparable
RealWorldQASource	84.1%	—	Not comparable
DynaMathSource	85.6%	—	Not comparable
MStarSource	81.4%	—	Not comparable
SimpleVQASource	56.1%	—	Not comparable
CharXivSource	78.4%	—	Not comparable
CC-OCRSource	81.2%	—	Not comparable
CountBenchSource	97.8%	—	Not comparable
RefCOCO (avg)Source	92.5%	—	Not comparable
ERQASource	62.5%	—	Not comparable
Video-MME (with subtitle)Source	87.7%	—	Not comparable
VideoMMMUSource	84.4%	—	Not comparable
MLVU (M-Avg)Source	86.6%	—	Not comparable
V*Source	94.7%	—	Not comparable
AA-MMMU-ProSource	74.6%	—	Not comparable

Inst. Following

1 benchmarks

Benchmark	Qwen3.6-27B	Soofi S 30B-A3B	Result
AA-IFBenchSource	67.6%	—	Not comparable

Frequently Asked Questions (2)

Which is better, Qwen3.6-27B or Soofi S 30B-A3B?

Qwen3.6-27B is ahead on BenchLM's provisional leaderboard, 65 to 45. The biggest single separator in this matchup is GPQA, where the scores are 87.8% and 43.4%.

Which is better for knowledge tasks, Qwen3.6-27B or Soofi S 30B-A3B?

Qwen3.6-27B has the edge for knowledge tasks in this comparison, averaging 53.6 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.

Qwen3.6-27B

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

Explore More

Alibaba 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.