Skip to main content

Model comparison

Sakana Fugu-Ultra vs ZAYA1-8B

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
Zyphra
N/A
1 category wins0 category wins

Evidence parity. Sakana Fugu-Ultra and ZAYA1-8B share 3 comparable benchmark results. 1 of 8 categories are comparable. 8 results are unique to Sakana Fugu-Ultra; 8 to ZAYA1-8B.

Updated July 23, 2026
Shared results
3
Sakana Fugu-Ultra only
8
ZAYA1-8B only
8
Comparable categories
1 / 8

Treat this as a split decision. Sakana Fugu-Ultra makes more sense if knowledge is the priority or you need the larger 1M context window; ZAYA1-8B 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; 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-Ultra and ZAYA1-8B 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 131K for ZAYA1-8B.

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 ZAYA1-8B
CategorySakana Fugu-UltraΔZAYA1-8B
KnowledgeSakana Fugu-Ultra95.5Margin 21.9ZAYA1-8B73.6
AgenticSakana Fugu-Ultra82.1MarginNo overlapZAYA1-8BNot measured
CodingSakana Fugu-Ultra64.5MarginNo overlapZAYA1-8BNot measured
ReasoningSakana Fugu-Ultra93.6MarginNo overlapZAYA1-8BNot measured
MathSakana Fugu-UltraNot measuredMarginNo overlapZAYA1-8B80.4
MultimodalSakana Fugu-Ultra86.6MarginNo overlapZAYA1-8BNot measured
Inst. FollowingSakana Fugu-UltraNot measuredMarginNo overlapZAYA1-8B64.1

Decisive benchmark drivers

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

More
A · Sakana Fugu-UltraB · ZAYA1-8B
  1. GPQA

    Knowledge
    Source ↗
    A 95.5%B 71%
    Winner: Sakana Fugu-UltraΔ 24.5
    GPQA: Sakana Fugu-Ultra scored 95.5%; ZAYA1-8B scored 71%. 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-UltraZAYA1-8BComparison
Input / output priceUSD per 1M tokensSakana Fugu-UltraNot availableZAYA1-8B$0 input / $0 outputA complete price comparison is not available.
Generation speedtokens per secondSakana Fugu-UltraNot availableZAYA1-8BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenSakana Fugu-UltraNot availableZAYA1-8BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensSakana Fugu-Ultra1MZAYA1-8B131KSakana Fugu-Ultra lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkSakana Fugu-UltraZAYA1-8BResult
Terminal-Bench 2.0Source 82.1%Not comparable
BFCL v4Source 39.2%Not comparable
Coding
BenchmarkSakana Fugu-UltraZAYA1-8BResult
SWE-bench ProSource 73.7%Not comparable
Terminal-Bench 2.0Source 82.1%Not comparable
LiveCodeBench v6Source 93.2%65.8%Sakana Fugu-Ultra leads
LiveCodeBench ProSource 90.8%Not comparable
SciCodeSource 58.7%Not comparable
Reasoning
BenchmarkSakana Fugu-UltraZAYA1-8BResult
MRCRv2Source 93.6%Not comparable
KnowledgeSakana Fugu-Ultra wins
BenchmarkSakana Fugu-UltraZAYA1-8BResult
GPQASource 95.5%71%Sakana Fugu-Ultra leads
GPQA-DSource 95.5%71.0%Sakana Fugu-Ultra leads
HLE w/o toolsSource 50%Not comparable
MMLU-ProSource 74.2%Not comparable
Math
BenchmarkSakana Fugu-UltraZAYA1-8BResult
AIME26Source 89.1%Not comparable
HMMT Feb 2026Source 71.6%Not comparable
IMOAnswerBenchSource 59.3%Not comparable
ApexSource 32.2%Not comparable
Multimodal
BenchmarkSakana Fugu-UltraZAYA1-8BResult
CharXivSource 86.6%Not comparable
Inst. Following
BenchmarkSakana Fugu-UltraZAYA1-8BResult
IFEvalSource 85.6%Not comparable
IFBenchSource 52.6%Not comparable
Frequently Asked Questions (2)

Which is better, Sakana Fugu-Ultra or ZAYA1-8B?

Sakana Fugu-Ultra and ZAYA1-8B 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 knowledge tasks, Sakana Fugu-Ultra or ZAYA1-8B?

Sakana Fugu-Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 73.6. Inside this category, GPQA 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.