Skip to main content

Model comparison

GPT-5.4 nano 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.

60/100
Margin
15.0pts
← winning
Soofi Project
45/100
0 category wins1 category wins

Evidence parity. GPT-5.4 nano and Soofi S 30B-A3B share 1 comparable benchmark result. 1 of 8 categories are comparable. 29 results are unique to GPT-5.4 nano; 7 to Soofi S 30B-A3B.

Updated July 15, 2026
Shared results
1
GPT-5.4 nano only
29
Soofi S 30B-A3B only
7
Comparable categories
1 / 8

Pick GPT-5.4 nano if you want the stronger benchmark profile. Soofi S 30B-A3B only becomes the better choice if knowledge is the priority or you want the cheaper token bill.

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

GPT-5.4 nano is clearly ahead on the provisional aggregate, 60 to 45. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.4 nano is also the more expensive model on tokens at $0.20 input / $1.25 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. GPT-5.4 nano 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 400K for GPT-5.4 nano.

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-5.4 nano and Soofi S 30B-A3B
CategoryGPT-5.4 nanoΔSoofi S 30B-A3B
KnowledgeGPT-5.4 nano43.8Margin 6.1Soofi S 30B-A3B49.9
AgenticGPT-5.4 nano42.9MarginNo overlapSoofi S 30B-A3BNot measured
MathGPT-5.4 nano21.0MarginNo overlapSoofi S 30B-A3BNot measured
MultimodalGPT-5.4 nano66.1MarginNo overlapSoofi S 30B-A3BNot measured

Decisive benchmark drivers

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

More
A · GPT-5.4 nanoB · Soofi S 30B-A3B
  1. GPQA

    Knowledge
    Source ↗
    A 82.8%B 43.4%
    Winner: GPT-5.4 nanoΔ 39.4
    GPQA: GPT-5.4 nano scored 82.8%; Soofi S 30B-A3B scored 43.4%. GPT-5.4 nano wins this benchmark.

Operational comparison

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

MetricGPT-5.4 nanoSoofi S 30B-A3BComparison
Input / output priceUSD per 1M tokensGPT-5.4 nano$0.2 input / $1.25 outputSoofi S 30B-A3B$0 input / $0 outputSoofi S 30B-A3B has the lower combined listed price.
Generation speedtokens per secondGPT-5.4 nano191 tok/sSoofi S 30B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGPT-5.4 nano3.64 sSoofi S 30B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGPT-5.4 nano400KSoofi S 30B-A3B1MSoofi S 30B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGPT-5.4 nanoSoofi S 30B-A3BResult
Terminal-Bench 2.0Source 46.3%Not comparable
OSWorld-VerifiedSource 39%Not comparable
MCP AtlasSource 56.1%Not comparable
ToolathlonSource 35.5%Not comparable
τ²-bench resultsSource 92.5%Not comparable
AA Agentic IndexSource 27.5%Not comparable
APEX-Agents-AASource 24.9%Not comparable
GDPval-AASource 30.0%Not comparable
GDPval-AASource 1100Not comparable
Coding
BenchmarkGPT-5.4 nanoSoofi S 30B-A3BResult
Vibe Code BenchSource 26.10%Not comparable
AA Coding IndexSource 56.1%Not comparable
Terminal-Bench HardSource 42.4%Not comparable
AA-SciCodeSource 46.9%Not comparable
HumanEvalSource 73.8%Not comparable
Reasoning
BenchmarkGPT-5.4 nanoSoofi S 30B-A3BResult
AA-LCRSource 66.0%Not comparable
CritPtSource 9.3%Not comparable
BBHSource 78.8%Not comparable
DROPSource 66.5%Not comparable
KnowledgeSoofi S 30B-A3B wins
BenchmarkGPT-5.4 nanoSoofi S 30B-A3BResult
GPQASource 82.8%43.4%GPT-5.4 nano leads
HLESource 37.7%Not comparable
HLE w/o toolsSource 24.3%Not comparable
Artificial Analysis Intelligence IndexSource 38.2%Not comparable
AA-GPQA DiamondSource 81.7%Not comparable
AA-HLESource 26.5%Not comparable
AA-Omniscience IndexSource -29.5%Not comparable
AA-Omniscience AccuracySource 25.4%Not comparable
AA-Omniscience Hallucination RateSource 73.6%Not comparable
GPQA-DSource 43.4%Not comparable
MMLU-ProSource 51.4%Not comparable
AGIEvalSource 66.9%Not comparable
Math
BenchmarkGPT-5.4 nanoSoofi S 30B-A3BResult
FrontierMath v2 (Tiers 1-3)Source 25.860%Not comparable
FrontierMath v2 (Tier 4)Source 6.250%Not comparable
GSM8KSource 86.1%Not comparable
Multimodal
BenchmarkGPT-5.4 nanoSoofi S 30B-A3BResult
MMMU-ProSource 66.1%Not comparable
MMMU-Pro w/ PythonSource 69.5%Not comparable
AA-MMMU-ProSource 65.4%Not comparable
Inst. Following
BenchmarkGPT-5.4 nanoSoofi S 30B-A3BResult
AA-IFBenchSource 75.9%Not comparable
Frequently Asked Questions (2)

Which is better, GPT-5.4 nano or Soofi S 30B-A3B?

GPT-5.4 nano is ahead on BenchLM's provisional leaderboard, 60 to 45. The biggest single separator in this matchup is GPQA, where the scores are 82.8% and 43.4%.

Which is better for knowledge tasks, GPT-5.4 nano 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, 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.