Model comparison

Qwen3.5 397B vs Sakana Fugu-Ultra

Data verified July 23, 2026

Head-to-head evidence from 5 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Qwen3.5 397B

Alibaba

57.01/100

No comparison

Sakana Fugu-Ultra

Sakana AI

N/A

1 category wins4 category wins

Public leaderboard positions: Qwen3.5 397B #71 (Estimated); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Qwen3.5 397B and Sakana Fugu-Ultra share 5 comparable benchmark results. 5 of 8 categories are comparable. 50 results are unique to Qwen3.5 397B; 6 to Sakana Fugu-Ultra.

Updated July 23, 2026

Shared results: 5
Qwen3.5 397B only: 50
Sakana Fugu-Ultra only: 6
Comparable categories: 5 / 8

Treat this as a split decision. Qwen3.5 397B makes more sense if coding is the priority or you would rather avoid the extra latency and token burn of a reasoning model; Sakana Fugu-Ultra is the better fit if knowledge is the priority or you need the larger 1M context window.

Confidence note. This is a partial-evidence comparison with 5 shared benchmark results across 4 evidence categories; 5 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Qwen3.5 397B and Sakana Fugu-Ultra 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 is the reasoning model in the pair, while Qwen3.5 397B 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. Sakana Fugu-Ultra gives you the larger context window at 1M, compared with 128K for Qwen3.5 397B.

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 Qwen3.5 397B and Sakana Fugu-Ultra
Category	Qwen3.5 397B	Δ	Sakana Fugu-Ultra
Knowledge	Qwen3.5 397B56.6	Margin→ 38.9	Sakana Fugu-Ultra95.5
Reasoning	Qwen3.5 397B63.2	Margin→ 30.4	Sakana Fugu-Ultra93.6
Agentic	Qwen3.5 397B56.5	Margin→ 25.6	Sakana Fugu-Ultra82.1
Multimodal	Qwen3.5 397B79.6	Margin→ 7.0	Sakana Fugu-Ultra86.6
Coding	Qwen3.5 397B66.5	Margin← 2.0	Sakana Fugu-Ultra64.5
Math	Qwen3.5 397B90.6	MarginNo overlap	Sakana Fugu-UltraNot measured
Multilingual	Qwen3.5 397B84.7	MarginNo overlap	Sakana Fugu-UltraNot measured
Inst. Following	Qwen3.5 397B92.6	MarginNo overlap	Sakana Fugu-UltraNot measured

Decisive benchmark drivers

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

A · Qwen3.5 397BB · Sakana Fugu-Ultra

Terminal-Bench 2.0
Agentic
Source ↗
A 52.5%B 82.1%
Winner: Sakana Fugu-UltraΔ 29.6
Terminal-Bench 2.0: Qwen3.5 397B scored 52.5%; Sakana Fugu-Ultra scored 82.1%. Sakana Fugu-Ultra wins this benchmark.
SWE-bench Pro
Coding
Source ↗
A 50.9%B 73.7%
Winner: Sakana Fugu-UltraΔ 22.8
SWE-bench Pro: Qwen3.5 397B scored 50.9%; Sakana Fugu-Ultra scored 73.7%. Sakana Fugu-Ultra wins this benchmark.
GPQA
Knowledge
Source ↗
A 88.4%B 95.5%
Winner: Sakana Fugu-UltraΔ 7.1
GPQA: Qwen3.5 397B scored 88.4%; Sakana Fugu-Ultra scored 95.5%. Sakana Fugu-Ultra wins this benchmark.
CharXiv
Multimodal
Source ↗
A 80.8%B 86.6%
Winner: Sakana Fugu-UltraΔ 5.8
CharXiv: Qwen3.5 397B scored 80.8%; Sakana Fugu-Ultra scored 86.6%. Sakana Fugu-Ultra wins this benchmark.

Operational comparison

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

Metric	Qwen3.5 397B	Sakana Fugu-Ultra	Comparison
Input / output priceUSD per 1M tokens	Qwen3.5 397B$0.6 input / $3.6 output	Sakana Fugu-UltraNot available	A complete price comparison is not available.
Generation speedtokens per second	Qwen3.5 397B96 tok/s	Sakana Fugu-UltraNot available	A complete speed comparison is not available.
First-answer latencyseconds to first token	Qwen3.5 397B2.44 s	Sakana Fugu-UltraNot available	A complete latency comparison is not available.
Context windowmaximum listed tokens	Qwen3.5 397B128K	Sakana Fugu-Ultra1M	Sakana Fugu-Ultra lists the larger context window.

Benchmark Deep Dive

AgenticSakana Fugu-Ultra wins

18 benchmarks

Benchmark	Qwen3.5 397B	Sakana Fugu-Ultra	Result
Terminal-Bench 2.0Source	52.5%	82.1%	Sakana Fugu-Ultra leads
BrowseCompSource	62%	—	Not comparable
Claw-EvalSource	56.8%	—	Not comparable
QwenClawBenchSource	51.8%	—	Not comparable
τ³-bench resultsSource	68.4%	—	Not comparable
VITA-BenchSource	43.7%	—	Not comparable
DeepPlanningSource	37.6%	—	Not comparable
ToolathlonSource	36.3%	—	Not comparable
MCP AtlasSource	46.1%	—	Not comparable
MCP-TasksSource	74.2%	—	Not comparable
WideResearchSource	74.0%	—	Not comparable
τ²-bench resultsSource	95.6%	—	Not comparable
Gert LabsSource	46.76%	—	Not comparable
ResearchClawBenchSource	14.2%	—	Not comparable
AA Agentic IndexSource	19.9%	—	Not comparable
APEX-Agents-AASource	15.3%	—	Not comparable
GDPval-AASource	23.1%	—	Not comparable
GDPval-AASource	962	—	Not comparable

CodingQwen3.5 397B wins

8 benchmarks

Benchmark	Qwen3.5 397B	Sakana Fugu-Ultra	Result
SWE-bench VerifiedSource	76.2%	—	Not comparable
LiveCodeBench v6Source	83.6%	93.2%	Sakana Fugu-Ultra leads
SWE-bench ProSource	50.9%	73.7%	Sakana Fugu-Ultra leads
AA-SciCodeSource	42.0%	—	Not comparable
AA Coding IndexSource	48.2%	—	Not comparable
Terminal-Bench 2.0Source	—	82.1%	Not comparable
LiveCodeBench ProSource	—	90.8%	Not comparable
SciCodeSource	—	58.7%	Not comparable

ReasoningSakana Fugu-Ultra wins

5 benchmarks

Benchmark	Qwen3.5 397B	Sakana Fugu-Ultra	Result
LongBench v2Source	63.2%	—	Not comparable
AI-NeedleSource	68.7%	—	Not comparable
AA-LCRSource	65.7%	—	Not comparable
CritPtSource	1.7%	—	Not comparable
MRCRv2Source	—	93.6%	Not comparable

KnowledgeSakana Fugu-Ultra wins

14 benchmarks

Benchmark	Qwen3.5 397B	Sakana Fugu-Ultra	Result
GPQASource	88.4%	95.5%	Sakana Fugu-Ultra leads
SuperGPQASource	70.4%	—	Not comparable
MMLU-ProSource	87.8%	—	Not comparable
MMLU-ReduxSource	94.9%	—	Not comparable
C-EvalSource	93%	—	Not comparable
HLESource	28.7%	—	Not comparable
Artificial Analysis Intelligence IndexSource	33.7%	—	Not comparable
AA-GPQA DiamondSource	89.3%	—	Not comparable
AA-HLESource	27.3%	—	Not comparable
AA-Omniscience IndexSource	-29.8%	—	Not comparable
AA-Omniscience AccuracySource	31.4%	—	Not comparable
AA-Omniscience Hallucination RateSource	89.1%	—	Not comparable
GPQA-DSource	—	95.5%	Not comparable
HLE w/o toolsSource	—	50%	Not comparable

Math

5 benchmarks

Benchmark	Qwen3.5 397B	Sakana Fugu-Ultra	Result
AIME26Source	93.3%	—	Not comparable
HMMT Feb 2025Source	94.8%	—	Not comparable
HMMT Nov 2025Source	92.7%	—	Not comparable
HMMT Feb 2026Source	87.9%	—	Not comparable
MMAnswerBenchSource	80.9%	—	Not comparable

Multilingual

2 benchmarks

Benchmark	Qwen3.5 397B	Sakana Fugu-Ultra	Result
MMLU-ProXSource	84.7%	—	Not comparable
NOVA-63Source	59.1%	—	Not comparable

MultimodalSakana Fugu-Ultra wins

7 benchmarks

Benchmark	Qwen3.5 397B	Sakana Fugu-Ultra	Result
MMMU-ProSource	79%	—	Not comparable
MathVisionSource	88.6%	—	Not comparable
CharXivSource	80.8%	86.6%	Sakana Fugu-Ultra leads
VideoMMMUSource	84.7%	—	Not comparable
ScreenSpot ProSource	65.6%	—	Not comparable
V*Source	95.8%	—	Not comparable
AA-MMMU-ProSource	77.3%	—	Not comparable

Inst. Following

2 benchmarks

Benchmark	Qwen3.5 397B	Sakana Fugu-Ultra	Result
IFEvalSource	92.6%	—	Not comparable
AA-IFBenchSource	78.8%	—	Not comparable

Frequently Asked Questions (6)

Which is better, Qwen3.5 397B or Sakana Fugu-Ultra?

Qwen3.5 397B and Sakana Fugu-Ultra 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, Qwen3.5 397B or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 56.6. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3.5 397B or Sakana Fugu-Ultra?

Qwen3.5 397B has the edge for coding in this comparison, averaging 66.5 versus 64.5. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for reasoning, Qwen3.5 397B or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for reasoning in this comparison, averaging 93.6 versus 63.2. Qwen3.5 397B stays close enough that the answer can still flip depending on your workload.

Which is better for agentic tasks, Qwen3.5 397B or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for agentic tasks in this comparison, averaging 82.1 versus 56.5. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Qwen3.5 397B or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for multimodal and grounded tasks in this comparison, averaging 86.6 versus 79.6. Inside this category, CharXiv is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Alibaba Compare Pricing Methodology Find Your Best LLM Overall Rankings

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.