Skip to main content
BenchLM
Advertise

Model comparison

Kimi K2.6 vs Sakana Fugu-Ultra

Data verified

Head-to-head evidence from 8 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Kimi K2.6
Moonshot AI
56.79/100
No comparison
N/A
0 category wins4 category wins

Public leaderboard positions: Kimi K2.6 #74 (Estimated); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Kimi K2.6 and Sakana Fugu-Ultra share 8 comparable benchmark results. 4 of 8 categories are comparable. 43 results are unique to Kimi K2.6; 3 to Sakana Fugu-Ultra.

Updated July 23, 2026
Shared results
8
Kimi K2.6 only
43
Sakana Fugu-Ultra only
3
Comparable categories
4 / 8

Treat this as a split decision. Kimi K2.6 makes more sense if its workflow fits your team better; 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 8 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

Kimi K2.6 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 256K for Kimi K2.6.

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 Kimi K2.6 and Sakana Fugu-Ultra
CategoryKimi K2.6ΔSakana Fugu-Ultra
KnowledgeKimi K2.642.2Margin→ 53.3Sakana Fugu-Ultra95.5
AgenticKimi K2.673.5Margin→ 8.6Sakana Fugu-Ultra82.1
MultimodalKimi K2.679.8Margin→ 6.8Sakana Fugu-Ultra86.6
CodingKimi K2.664.4Margin→ 0.1Sakana Fugu-Ultra64.5
ReasoningKimi K2.6Not measuredMarginNo overlapSakana Fugu-Ultra93.6
MathKimi K2.667.1MarginNo overlapSakana Fugu-UltraNot measured

Decisive benchmark drivers

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

More
A · Kimi K2.6B · Sakana Fugu-Ultra

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 66.7%B 82.1%
    Winner: Sakana Fugu-UltraΔ 15.4
    Terminal-Bench 2.0: Kimi K2.6 scored 66.7%; Sakana Fugu-Ultra scored 82.1%. Sakana Fugu-Ultra wins this benchmark.

  2. SWE-bench Pro

    Coding
    Source ↗
    A 58.6%B 73.7%
    Winner: Sakana Fugu-UltraΔ 15.1
    SWE-bench Pro: Kimi K2.6 scored 58.6%; Sakana Fugu-Ultra scored 73.7%. Sakana Fugu-Ultra wins this benchmark.

  3. SciCode

    Coding
    Source ↗
    A 52.2%B 58.7%
    Winner: Sakana Fugu-UltraΔ 6.5
    SciCode: Kimi K2.6 scored 52.2%; Sakana Fugu-Ultra scored 58.7%. Sakana Fugu-Ultra wins this benchmark.

  4. CharXiv

    Multimodal
    Source ↗
    A 80.4%B 86.6%
    Winner: Sakana Fugu-UltraΔ 6.2
    CharXiv: Kimi K2.6 scored 80.4%; Sakana Fugu-Ultra scored 86.6%. Sakana Fugu-Ultra wins this benchmark.

  5. GPQA

    Knowledge
    Source ↗
    A 90.5%B 95.5%
    Winner: Sakana Fugu-UltraΔ 5
    GPQA: Kimi K2.6 scored 90.5%; 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.

MetricKimi K2.6Sakana Fugu-UltraComparison
Input / output priceUSD per 1M tokensKimi K2.6$0.95 input / $4 outputSakana Fugu-UltraNot availableA complete price comparison is not available.
Generation speedtokens per secondKimi K2.6Not availableSakana Fugu-UltraNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenKimi K2.6Not availableSakana Fugu-UltraNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensKimi K2.6256KSakana Fugu-Ultra1MSakana Fugu-Ultra lists the larger context window.

Benchmark Deep Dive

AgenticSakana Fugu-Ultra wins
BenchmarkKimi K2.6Sakana Fugu-UltraResult
Terminal-Bench 2.0Source 66.7%82.1%Sakana Fugu-Ultra leads
BrowseCompSource 83.2%—Not comparable
OSWorld-VerifiedSource 73.1%—Not comparable
ToolathlonSource 50%—Not comparable
MCP AtlasSource 55.9%—Not comparable
Claw-EvalSource 62.3%—Not comparable
DeepSearchQASource 92.5%—Not comparable
WideResearchSource 80.8%—Not comparable
AA Agentic IndexSource 30.3%—Not comparable
τ²-bench resultsSource 95.9%—Not comparable
GDPval-AASource 34.5%—Not comparable
GDPval-AASource 1189—Not comparable
APEX-Agents-AASource 28.5%—Not comparable
Gert LabsSource 56.82%—Not comparable
ResearchClawBenchSource 18.0%—Not comparable
OSWorld 2.0Source 4.6%—Not comparable
terminalBenchHardSource 43.9%—Not comparable
CodingSakana Fugu-Ultra wins
BenchmarkKimi K2.6Sakana Fugu-UltraResult
SWE-bench VerifiedSource 80.2%—Not comparable
LiveCodeBench v6Source 89.6%93.2%Sakana Fugu-Ultra leads
SWE-bench ProSource 58.6%73.7%Sakana Fugu-Ultra leads
SWE MultilingualSource 76.7%—Not comparable
SciCodeSource 52.2%58.7%Sakana Fugu-Ultra leads
Terminal-Bench 2.0Source 66.7%82.1%Sakana Fugu-Ultra leads
Vibe Code BenchSource 37.89%—Not comparable
cursorBench31Source 47.6%—Not comparable
AA Coding IndexSource 61.8%—Not comparable
AA-SciCodeSource 53.5%—Not comparable
LiveCodeBench ProSource —90.8%Not comparable
Reasoning
BenchmarkKimi K2.6Sakana Fugu-UltraResult
AA-LCRSource 69.7%—Not comparable
CritPtSource 8.0%—Not comparable
MRCRv2Source —93.6%Not comparable
KnowledgeSakana Fugu-Ultra wins
BenchmarkKimi K2.6Sakana Fugu-UltraResult
GPQASource 90.5%95.5%Sakana Fugu-Ultra leads
GPQA-DSource 90.5%95.5%Sakana Fugu-Ultra leads
HLESource 34.7%—Not comparable
Artificial Analysis Intelligence IndexSource 44.2%—Not comparable
AA-GPQA DiamondSource 91.1%—Not comparable
AA-HLESource 35.9%—Not comparable
AA-Omniscience IndexSource 6.4%—Not comparable
AA-Omniscience AccuracySource 32.8%—Not comparable
AA-Omniscience Hallucination RateSource 39.3%—Not comparable
HLE w/o toolsSource —50%Not comparable
Math
BenchmarkKimi K2.6Sakana Fugu-UltraResult
AIME26Source 96.4%—Not comparable
HMMT Feb 2026Source 92.7%—Not comparable
MMAnswerBenchSource 86.0%—Not comparable
FrontierMath v2 (Tiers 1-3)Source 38.966%—Not comparable
FrontierMath v2 (Tier 4)Source 14.580%—Not comparable
MultimodalSakana Fugu-Ultra wins
BenchmarkKimi K2.6Sakana Fugu-UltraResult
MMMU-ProSource 79.4%—Not comparable
MMMU-Pro w/ PythonSource 80.1%—Not comparable
CharXivSource 80.4%86.6%Sakana Fugu-Ultra leads
MathVisionSource 87.4%—Not comparable
V*Source 96.9%—Not comparable
AA-MMMU-ProSource 79.4%—Not comparable
Design Arena WebsiteSource 1306—Not comparable
Inst. Following
BenchmarkKimi K2.6Sakana Fugu-UltraResult
AA-IFBenchSource 76.0%—Not comparable
Frequently Asked Questions (5)

Which is better, Kimi K2.6 or Sakana Fugu-Ultra?

Kimi K2.6 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, Kimi K2.6 or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 42.2. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for coding, Kimi K2.6 or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for coding in this comparison, averaging 64.5 versus 64.4. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Kimi K2.6 or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for agentic tasks in this comparison, averaging 82.1 versus 73.5. 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, Kimi K2.6 or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for multimodal and grounded tasks in this comparison, averaging 86.6 versus 79.8. 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.

Kimi K2.6
API / mo$3,713
Self-host / mo$18,221
Break-even326M/day
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

Moonshot AI 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.