Skip to main content

Model comparison

Sakana Fugu-Ultra vs Step 3.7 Flash

Data verified

Head-to-head evidence from 3 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

N/A
No comparison
50.87/100
2 category wins0 category wins

Public leaderboard positions: Sakana Fugu-Ultra unranked (Not scored); Step 3.7 Flash #110 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Sakana Fugu-Ultra and Step 3.7 Flash share 3 comparable benchmark results. 2 of 8 categories are comparable. 8 results are unique to Sakana Fugu-Ultra; 26 to Step 3.7 Flash.

Updated July 23, 2026
Shared results
3
Sakana Fugu-Ultra only
8
Step 3.7 Flash only
26
Comparable categories
2 / 8

Treat this as a split decision. Sakana Fugu-Ultra makes more sense if agentic is the priority or you need the larger 1M context window; Step 3.7 Flash is the better fit if its strengths line up with your actual workload.

Confidence note. This is a partial-evidence comparison with 3 shared benchmark results across 2 evidence categories; 2 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-Ultra and Step 3.7 Flash finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.

Sakana Fugu-Ultra gives you the larger context window at 1M, compared with 256K for Step 3.7 Flash.

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-Ultra and Step 3.7 Flash
CategorySakana Fugu-UltraΔStep 3.7 Flash
AgenticSakana Fugu-Ultra82.1Margin 15.7Step 3.7 Flash66.4
CodingSakana Fugu-Ultra64.5Margin 8.2Step 3.7 Flash56.3
ReasoningSakana Fugu-Ultra93.6MarginNo overlapStep 3.7 FlashNot measured
KnowledgeSakana Fugu-Ultra95.5MarginNo overlapStep 3.7 FlashNot measured
MultimodalSakana Fugu-Ultra86.6MarginNo overlapStep 3.7 FlashNot measured

Decisive benchmark drivers

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

More
A · Sakana Fugu-UltraB · Step 3.7 Flash
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 82.1%B 59.5%
    Winner: Sakana Fugu-UltraΔ 22.6
    Terminal-Bench 2.0: Sakana Fugu-Ultra scored 82.1%; Step 3.7 Flash scored 59.5%. Sakana Fugu-Ultra wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 73.7%B 56.3%
    Winner: Sakana Fugu-UltraΔ 17.4
    SWE-bench Pro: Sakana Fugu-Ultra scored 73.7%; Step 3.7 Flash scored 56.3%. Sakana Fugu-Ultra wins this benchmark.

Operational comparison

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

MetricSakana Fugu-UltraStep 3.7 FlashComparison
Input / output priceUSD per 1M tokensSakana Fugu-UltraNot availableStep 3.7 Flash$0.2 input / $1.15 outputA complete price comparison is not available.
Generation speedtokens per secondSakana Fugu-UltraNot availableStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenSakana Fugu-UltraNot availableStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensSakana Fugu-Ultra1MStep 3.7 Flash256KSakana Fugu-Ultra lists the larger context window.

Benchmark Deep Dive

AgenticSakana Fugu-Ultra wins
BenchmarkSakana Fugu-UltraStep 3.7 FlashResult
Terminal-Bench 2.0Source 82.1%59.5%Sakana Fugu-Ultra leads
BrowseCompSource 75.8%Not comparable
DeepSearchQASource 92.8%Not comparable
GDPval-AASource 25.9%Not comparable
ToolathlonSource 49.5%Not comparable
Claw-EvalSource 67.1%Not comparable
HLE w/ toolsSource 47.2%Not comparable
Gert LabsSource 51.57%Not comparable
AA Agentic IndexSource 21.5%Not comparable
τ²-bench resultsSource 98.5%Not comparable
GDPval-AASource 1017Not comparable
APEX-Agents-AASource 14.8%Not comparable
CodingSakana Fugu-Ultra wins
BenchmarkSakana Fugu-UltraStep 3.7 FlashResult
SWE-bench ProSource 73.7%56.3%Sakana Fugu-Ultra leads
Terminal-Bench 2.0Source 82.1%59.5%Sakana Fugu-Ultra leads
LiveCodeBench v6Source 93.2%Not comparable
LiveCodeBench ProSource 90.8%Not comparable
SciCodeSource 58.7%Not comparable
AA Coding IndexSource 39.6%Not comparable
AA-SciCodeSource 40.0%Not comparable
Reasoning
BenchmarkSakana Fugu-UltraStep 3.7 FlashResult
MRCRv2Source 93.6%Not comparable
AA-LCRSource 63.7%Not comparable
CritPtSource 2.3%Not comparable
Knowledge
BenchmarkSakana Fugu-UltraStep 3.7 FlashResult
GPQASource 95.5%Not comparable
GPQA-DSource 95.5%Not comparable
HLE w/o toolsSource 50%Not comparable
Artificial Analysis Intelligence IndexSource 30.3%Not comparable
AA-GPQA DiamondSource 80.9%Not comparable
AA-HLESource 19.9%Not comparable
AA-Omniscience IndexSource -37.5%Not comparable
AA-Omniscience AccuracySource 25.4%Not comparable
AA-Omniscience Hallucination RateSource 84.4%Not comparable
Multimodal
BenchmarkSakana Fugu-UltraStep 3.7 FlashResult
CharXivSource 86.6%Not comparable
SimpleVQASource 79.2%Not comparable
V*Source 95.3%Not comparable
AA-MMMU-ProSource 75.3%Not comparable
Design Arena WebsiteSource 1211Not comparable
Inst. Following
BenchmarkSakana Fugu-UltraStep 3.7 FlashResult
AA-IFBenchSource 67.3%Not comparable
Frequently Asked Questions (3)

Which is better, Sakana Fugu-Ultra or Step 3.7 Flash?

Sakana Fugu-Ultra and Step 3.7 Flash are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.

Which is better for coding, Sakana Fugu-Ultra or Step 3.7 Flash?

Sakana Fugu-Ultra has the edge for coding in this comparison, averaging 64.5 versus 56.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Sakana Fugu-Ultra or Step 3.7 Flash?

Sakana Fugu-Ultra has the edge for agentic tasks in this comparison, averaging 82.1 versus 66.4. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.