Skip to main content

Model comparison

Sakana Fugu vs Soofi S 30B-A3B

Data verified

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

Sakana AI
75/100
Margin
30.0pts
← winning
Soofi Project
45/100
1 category wins0 category wins

Evidence parity. Sakana Fugu and Soofi S 30B-A3B share 2 comparable benchmark results. 1 of 8 categories are comparable. 9 results are unique to Sakana Fugu; 6 to Soofi S 30B-A3B.

Updated July 15, 2026
Shared results
2
Sakana Fugu only
9
Soofi S 30B-A3B only
6
Comparable categories
1 / 8

Pick Sakana Fugu if you want the stronger benchmark profile. Soofi S 30B-A3B only becomes the better choice if 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

Sakana Fugu is clearly ahead on the provisional aggregate, 75 to 45. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Sakana Fugu's sharpest advantage is in knowledge, where it averages 95.5 against 49.9. The single biggest benchmark swing on the page is GPQA, 95.5% to 43.4%.

Sakana Fugu 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.

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 Sakana Fugu and Soofi S 30B-A3B
CategorySakana FuguΔSoofi S 30B-A3B
KnowledgeSakana Fugu95.5Margin 45.6Soofi S 30B-A3B49.9
AgenticSakana Fugu80.2MarginNo overlapSoofi S 30B-A3BNot measured
CodingSakana Fugu59.3MarginNo overlapSoofi S 30B-A3BNot measured
ReasoningSakana Fugu86.6MarginNo overlapSoofi S 30B-A3BNot measured
MultimodalSakana Fugu85.1MarginNo overlapSoofi S 30B-A3BNot measured

Decisive benchmark drivers

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

More
A · Sakana FuguB · Soofi S 30B-A3B
  1. GPQA

    Knowledge
    Source ↗
    A 95.5%B 43.4%
    Winner: Sakana FuguΔ 52.1
    GPQA: Sakana Fugu scored 95.5%; Soofi S 30B-A3B scored 43.4%. Sakana Fugu wins this benchmark.

Operational comparison

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

MetricSakana FuguSoofi S 30B-A3BComparison
Input / output priceUSD per 1M tokensSakana FuguNot availableSoofi S 30B-A3B$0 input / $0 outputA complete price comparison is not available.
Generation speedtokens per secondSakana FuguNot availableSoofi S 30B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenSakana FuguNot availableSoofi S 30B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensSakana Fugu1MSoofi S 30B-A3B1MListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkSakana FuguSoofi S 30B-A3BResult
Terminal-Bench 2.0Source 80.2%Not comparable
Coding
BenchmarkSakana FuguSoofi S 30B-A3BResult
SWE-bench ProSource 59%Not comparable
Terminal-Bench 2.0Source 80.2%Not comparable
LiveCodeBench v6Source 92.9%Not comparable
LiveCodeBench ProSource 87.8%Not comparable
SciCodeSource 60.1%Not comparable
HumanEvalSource 73.8%Not comparable
Reasoning
BenchmarkSakana FuguSoofi S 30B-A3BResult
MRCRv2Source 86.6%Not comparable
BBHSource 78.8%Not comparable
DROPSource 66.5%Not comparable
KnowledgeSakana Fugu wins
BenchmarkSakana FuguSoofi S 30B-A3BResult
GPQASource 95.5%43.4%Sakana Fugu leads
GPQA-DSource 95.5%43.4%Sakana Fugu leads
HLE w/o toolsSource 47.2%Not comparable
MMLU-ProSource 51.4%Not comparable
AGIEvalSource 66.9%Not comparable
Math
BenchmarkSakana FuguSoofi S 30B-A3BResult
GSM8KSource 86.1%Not comparable
Multimodal
BenchmarkSakana FuguSoofi S 30B-A3BResult
CharXivSource 85.1%Not comparable
Frequently Asked Questions (2)

Which is better, Sakana Fugu or Soofi S 30B-A3B?

Sakana Fugu is ahead on BenchLM's provisional leaderboard, 75 to 45. The biggest single separator in this matchup is GPQA, where the scores are 95.5% and 43.4%.

Which is better for knowledge tasks, Sakana Fugu or Soofi S 30B-A3B?

Sakana Fugu has the edge for knowledge tasks in this comparison, averaging 95.5 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.