Skip to main content

Model comparison

GPT-4.1 mini 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.

42/100
Margin
3.0pts
winning →
Soofi Project
45/100
1 category wins0 category wins

Evidence parity. GPT-4.1 mini and Soofi S 30B-A3B share 1 comparable benchmark result. 1 of 8 categories are comparable. 22 results are unique to GPT-4.1 mini; 7 to Soofi S 30B-A3B.

Updated July 15, 2026
Shared results
1
GPT-4.1 mini only
22
Soofi S 30B-A3B only
7
Comparable categories
1 / 8

Pick Soofi S 30B-A3B if you want the stronger benchmark profile. GPT-4.1 mini only becomes the better choice if knowledge is the priority.

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

Soofi S 30B-A3B has the cleaner provisional overall profile here, landing at 45 versus 42. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

GPT-4.1 mini is also the more expensive model on tokens at $0.40 input / $1.60 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Soofi S 30B-A3B. That is roughly Infinityx on output cost alone.

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 GPT-4.1 mini and Soofi S 30B-A3B
CategoryGPT-4.1 miniΔSoofi S 30B-A3B
KnowledgeGPT-4.1 mini64.2Margin 14.3Soofi S 30B-A3B49.9
CodingGPT-4.1 mini23.6MarginNo overlapSoofi S 30B-A3BNot measured
MathGPT-4.1 mini4.5MarginNo overlapSoofi S 30B-A3BNot measured
Inst. FollowingGPT-4.1 mini88.5MarginNo overlapSoofi S 30B-A3BNot measured

Decisive benchmark drivers

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

More
A · GPT-4.1 miniB · Soofi S 30B-A3B
  1. GPQA

    Knowledge
    Source ↗
    A 64.2%B 43.4%
    Winner: GPT-4.1 miniΔ 20.8
    GPQA: GPT-4.1 mini scored 64.2%; Soofi S 30B-A3B scored 43.4%. GPT-4.1 mini wins this benchmark.

Operational comparison

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

MetricGPT-4.1 miniSoofi S 30B-A3BComparison
Input / output priceUSD per 1M tokensGPT-4.1 mini$0.4 input / $1.6 outputSoofi S 30B-A3B$0 input / $0 outputSoofi S 30B-A3B has the lower combined listed price.
Generation speedtokens per secondGPT-4.1 mini80 tok/sSoofi S 30B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGPT-4.1 mini0.76 sSoofi S 30B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGPT-4.1 mini1MSoofi S 30B-A3B1MListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkGPT-4.1 miniSoofi S 30B-A3BResult
AA Agentic IndexSource 1.7%Not comparable
τ²-bench resultsSource 52.9%Not comparable
GDPval-AASource 0.1%Not comparable
GDPval-AASource 503Not comparable
Coding
BenchmarkGPT-4.1 miniSoofi S 30B-A3BResult
SWE-bench VerifiedSource 23.6%Not comparable
AA Coding IndexSource 20.2%Not comparable
Terminal-Bench HardSource 7.6%Not comparable
AA-SciCodeSource 40.4%Not comparable
HumanEvalSource 73.8%Not comparable
Reasoning
BenchmarkGPT-4.1 miniSoofi S 30B-A3BResult
AA-LCRSource 42.3%Not comparable
CritPtSource 0.0%Not comparable
BBHSource 78.8%Not comparable
DROPSource 66.5%Not comparable
KnowledgeGPT-4.1 mini wins
BenchmarkGPT-4.1 miniSoofi S 30B-A3BResult
MMLUSource 87.5%Not comparable
GPQASource 64.2%43.4%GPT-4.1 mini leads
Artificial Analysis Intelligence IndexSource 14.8%Not comparable
AA-GPQA DiamondSource 66.4%Not comparable
AA-HLESource 4.6%Not comparable
AA-Omniscience IndexSource -50.1%Not comparable
AA-Omniscience AccuracySource 17.5%Not comparable
AA-Omniscience Hallucination RateSource 82.0%Not comparable
GPQA-DSource 43.4%Not comparable
MMLU-ProSource 51.4%Not comparable
AGIEvalSource 66.9%Not comparable
Math
BenchmarkGPT-4.1 miniSoofi S 30B-A3BResult
FrontierMath v2 (Tiers 1-3)Source 4.483%Not comparable
GSM8KSource 86.1%Not comparable
Multimodal
BenchmarkGPT-4.1 miniSoofi S 30B-A3BResult
AA-MMMU-ProSource 58.7%Not comparable
Design Arena WebsiteSource 1032Not comparable
Inst. Following
BenchmarkGPT-4.1 miniSoofi S 30B-A3BResult
IFEvalSource 88.5%Not comparable
AA-IFBenchSource 38.3%Not comparable
Frequently Asked Questions (2)

Which is better, GPT-4.1 mini or Soofi S 30B-A3B?

Soofi S 30B-A3B is ahead on BenchLM's provisional leaderboard, 45 to 42. The biggest single separator in this matchup is GPQA, where the scores are 64.2% and 43.4%.

Which is better for knowledge tasks, GPT-4.1 mini or Soofi S 30B-A3B?

GPT-4.1 mini has the edge for knowledge tasks in this comparison, averaging 64.2 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.