Skip to main content
BenchLM
Advertise

Model comparison

Qwen3.6-27B vs Sakana Fugu-Ultra

Data verified

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

53.82/100
No comparison
N/A
1 category wins3 category wins

Public leaderboard positions: Qwen3.6-27B #93 (Estimated); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Qwen3.6-27B and Sakana Fugu-Ultra share 5 comparable benchmark results. 4 of 8 categories are comparable. 49 results are unique to Qwen3.6-27B; 6 to Sakana Fugu-Ultra.

Updated July 23, 2026
Shared results
5
Qwen3.6-27B only
49
Sakana Fugu-Ultra only
6
Comparable categories
4 / 8

Treat this as a split decision. Qwen3.6-27B makes more sense if coding is the priority; 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; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Qwen3.6-27B 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 gives you the larger context window at 1M, compared with 262K for Qwen3.6-27B.

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 Qwen3.6-27B and Sakana Fugu-Ultra
CategoryQwen3.6-27BΔSakana Fugu-Ultra
KnowledgeQwen3.6-27B53.3Margin→ 42.2Sakana Fugu-Ultra95.5
AgenticQwen3.6-27B59.3Margin→ 22.8Sakana Fugu-Ultra82.1
CodingQwen3.6-27B77.5Margin← 13.0Sakana Fugu-Ultra64.5
MultimodalQwen3.6-27B76.7Margin→ 9.9Sakana Fugu-Ultra86.6
ReasoningQwen3.6-27BNot measuredMarginNo overlapSakana Fugu-Ultra93.6
MathQwen3.6-27B89.2MarginNo overlapSakana Fugu-UltraNot measured

Decisive benchmark drivers

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

More
A · Qwen3.6-27BB · Sakana Fugu-Ultra

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 59.3%B 82.1%
    Winner: Sakana Fugu-UltraΔ 22.8
    Terminal-Bench 2.0: Qwen3.6-27B scored 59.3%; Sakana Fugu-Ultra scored 82.1%. Sakana Fugu-Ultra wins this benchmark.

  2. SWE-bench Pro

    Coding
    Source ↗
    A 53.5%B 73.7%
    Winner: Sakana Fugu-UltraΔ 20.2
    SWE-bench Pro: Qwen3.6-27B scored 53.5%; Sakana Fugu-Ultra scored 73.7%. Sakana Fugu-Ultra wins this benchmark.

  3. CharXiv

    Multimodal
    Source ↗
    A 78.4%B 86.6%
    Winner: Sakana Fugu-UltraΔ 8.2
    CharXiv: Qwen3.6-27B scored 78.4%; Sakana Fugu-Ultra scored 86.6%. Sakana Fugu-Ultra wins this benchmark.

  4. GPQA

    Knowledge
    Source ↗
    A 87.8%B 95.5%
    Winner: Sakana Fugu-UltraΔ 7.7
    GPQA: Qwen3.6-27B scored 87.8%; Sakana Fugu-Ultra scored 95.5%. Sakana Fugu-Ultra wins this benchmark.

Operational comparison

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

MetricQwen3.6-27BSakana Fugu-UltraComparison
Input / output priceUSD per 1M tokensQwen3.6-27B$0 input / $0 outputSakana Fugu-UltraNot availableA complete price comparison is not available.
Generation speedtokens per secondQwen3.6-27BNot availableSakana Fugu-UltraNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenQwen3.6-27BNot availableSakana Fugu-UltraNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensQwen3.6-27B262KSakana Fugu-Ultra1MSakana Fugu-Ultra lists the larger context window.

Benchmark Deep Dive

AgenticSakana Fugu-Ultra wins
BenchmarkQwen3.6-27BSakana Fugu-UltraResult
Terminal-Bench 2.0Source 59.3%82.1%Sakana Fugu-Ultra leads
Claw-EvalSource 72.4%—Not comparable
QwenClawBenchSource 53.4%—Not comparable
QwenWebBenchSource 1487—Not comparable
AndroidWorldSource 70.3%—Not comparable
AA Agentic IndexSource 27.0%—Not comparable
τ²-bench resultsSource 94.2%—Not comparable
GDPval-AASource 32.0%—Not comparable
GDPval-AASource 1140—Not comparable
Gert LabsSource 54.84%—Not comparable
CodingQwen3.6-27B wins
BenchmarkQwen3.6-27BSakana Fugu-UltraResult
SWE-bench VerifiedSource 77.2%—Not comparable
SWE MultilingualSource 71.3%—Not comparable
SWE-bench ProSource 53.5%73.7%Sakana Fugu-Ultra leads
Terminal-Bench 2.0Source 59.3%82.1%Sakana Fugu-Ultra leads
LiveCodeBenchSource 83.9%—Not comparable
NL2RepoSource 36.2%—Not comparable
AA Coding IndexSource 53.7%—Not comparable
AA-SciCodeSource 39.8%—Not comparable
LiveCodeBench v6Source —93.2%Not comparable
LiveCodeBench ProSource —90.8%Not comparable
SciCodeSource —58.7%Not comparable
Reasoning
BenchmarkQwen3.6-27BSakana Fugu-UltraResult
AA-LCRSource 68.7%—Not comparable
CritPtSource 1.1%—Not comparable
MRCRv2Source —93.6%Not comparable
KnowledgeSakana Fugu-Ultra wins
BenchmarkQwen3.6-27BSakana Fugu-UltraResult
MMLU-ProSource 86.2%—Not comparable
MMLU-ReduxSource 93.5%—Not comparable
SuperGPQASource 66%—Not comparable
C-EvalSource 91.4%—Not comparable
GPQASource 87.8%95.5%Sakana Fugu-Ultra leads
HLESource 24%—Not comparable
Artificial Analysis Intelligence IndexSource 37.0%—Not comparable
AA-GPQA DiamondSource 84.2%—Not comparable
AA-HLESource 21.6%—Not comparable
AA-Omniscience IndexSource -19.8%—Not comparable
AA-Omniscience AccuracySource 19.2%—Not comparable
AA-Omniscience Hallucination RateSource 48.3%—Not comparable
GPQA-DSource —95.5%Not comparable
HLE w/o toolsSource —50%Not comparable
Math
BenchmarkQwen3.6-27BSakana Fugu-UltraResult
HMMT Feb 2025Source 93.8%—Not comparable
HMMT Nov 2025Source 90.7%—Not comparable
HMMT Feb 2026Source 84.3%—Not comparable
MMAnswerBenchSource 80.8%—Not comparable
AIME26Source 94.1%—Not comparable
MultimodalSakana Fugu-Ultra wins
BenchmarkQwen3.6-27BSakana Fugu-UltraResult
MMMUSource 82.9%—Not comparable
MMMU-ProSource 75.8%—Not comparable
RealWorldQASource 84.1%—Not comparable
DynaMathSource 85.6%—Not comparable
MStarSource 81.4%—Not comparable
SimpleVQASource 56.1%—Not comparable
CharXivSource 78.4%86.6%Sakana Fugu-Ultra leads
CC-OCRSource 81.2%—Not comparable
CountBenchSource 97.8%—Not comparable
RefCOCO (avg)Source 92.5%—Not comparable
ERQASource 62.5%—Not comparable
Video-MME (with subtitle)Source 87.7%—Not comparable
VideoMMMUSource 84.4%—Not comparable
MLVU (M-Avg)Source 86.6%—Not comparable
V*Source 94.7%—Not comparable
AA-MMMU-ProSource 74.6%—Not comparable
Inst. Following
BenchmarkQwen3.6-27BSakana Fugu-UltraResult
AA-IFBenchSource 67.6%—Not comparable
Frequently Asked Questions (5)

Which is better, Qwen3.6-27B or Sakana Fugu-Ultra?

Qwen3.6-27B 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, Qwen3.6-27B or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 53.3. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3.6-27B or Sakana Fugu-Ultra?

Qwen3.6-27B has the edge for coding in this comparison, averaging 77.5 versus 64.5. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3.6-27B or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for agentic tasks in this comparison, averaging 82.1 versus 59.3. 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, Qwen3.6-27B or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for multimodal and grounded tasks in this comparison, averaging 86.6 versus 76.7. Inside this category, CharXiv is the benchmark that creates the most daylight between them.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Qwen3.6-27B
API / mo$0
Self-host / mo$429
Break-even—
Sakana Fugu-Ultra
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Model the full break-even

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.