Skip to main content
BenchLM
Advertise

Model comparison

Kimi K3 vs Sakana Fugu-Ultra

Data verified

Head-to-head evidence from 5 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Kimi K3
Moonshot AI
80.96/100
No comparison
N/A
1 category wins2 category wins

Public leaderboard positions: Kimi K3 #4 (Supported); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Kimi K3 and Sakana Fugu-Ultra share 5 comparable benchmark results. 3 of 8 categories are comparable. 52 results are unique to Kimi K3; 6 to Sakana Fugu-Ultra.

Updated July 23, 2026
Shared results
5
Kimi K3 only
52
Sakana Fugu-Ultra only
6
Comparable categories
3 / 8

Treat this as a split decision. Kimi K3 makes more sense if agentic is the priority or you need the larger 1.05M context window; Sakana Fugu-Ultra is the better fit if knowledge is the priority.

Confidence note. This is a partial-evidence comparison with 5 shared benchmark results across 3 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Kimi K3 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.

Kimi K3 gives you the larger context window at 1.05M, compared with 1M for Sakana Fugu-Ultra.

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 K3 and Sakana Fugu-Ultra
CategoryKimi K3ΔSakana Fugu-Ultra
KnowledgeKimi K361.0Margin→ 34.5Sakana Fugu-Ultra95.5
MultimodalKimi K378.5Margin→ 8.1Sakana Fugu-Ultra86.6
AgenticKimi K389.5Margin← 7.4Sakana Fugu-Ultra82.1
CodingKimi K3Not measuredMarginNo overlapSakana Fugu-Ultra64.5
ReasoningKimi K3Not measuredMarginNo overlapSakana Fugu-Ultra93.6

Decisive benchmark drivers

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

More
A · Kimi K3B · Sakana Fugu-Ultra

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 88.3%B 82.1%
    Winner: Kimi K3Δ 6.2
    Terminal-Bench 2.0: Kimi K3 scored 88.3%; Sakana Fugu-Ultra scored 82.1%. Kimi K3 wins this benchmark.

  2. CharXiv

    Multimodal
    Source ↗
    A 91.3%B 86.6%
    Winner: Kimi K3Δ 4.7
    CharXiv: Kimi K3 scored 91.3%; Sakana Fugu-Ultra scored 86.6%. Kimi K3 wins this benchmark.

  3. GPQA

    Knowledge
    Source ↗
    A 93.5%B 95.5%
    Winner: Sakana Fugu-UltraΔ 2
    GPQA: Kimi K3 scored 93.5%; 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 K3Sakana Fugu-UltraComparison
Input / output priceUSD per 1M tokensKimi K3$3 input / $15 outputSakana Fugu-UltraNot availableA complete price comparison is not available.
Generation speedtokens per secondKimi K3Not availableSakana Fugu-UltraNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenKimi K3Not availableSakana Fugu-UltraNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensKimi K31.05MSakana Fugu-Ultra1MKimi K3 lists the larger context window.

Benchmark Deep Dive

AgenticKimi K3 wins
BenchmarkKimi K3Sakana Fugu-UltraResult
Terminal-Bench 2.0Source 88.3%82.1%Kimi K3 leads
BrowseCompSource 91.2%—Not comparable
DeepSearchQASource 95.0%—Not comparable
Toolathlon-VerifiedSource 73.2%—Not comparable
MCP AtlasSource 84.2%—Not comparable
AutomationBenchSource 30.8%—Not comparable
JobBenchSource 52.9%—Not comparable
APEX-AgentsSource 37.6%—Not comparable
SpreadsheetBench 2Source 34.8%—Not comparable
DECK-BenchSource 73.5%—Not comparable
AA Agentic IndexSource 50.1%—Not comparable
GDPval-AASource 59.0%—Not comparable
GDPval-AASource 1679—Not comparable
AA BriefcaseSource 1543—Not comparable
AA AutomationBenchSource 52.7%—Not comparable
AA EnterpriseOps-GymSource 45.3%—Not comparable
AA Harvey LABSource 94.6%—Not comparable
AA Tau3 BankingSource 33.4%—Not comparable
aaTerminalBench21Source 85%—Not comparable
APEX-Agents-AASource 41.3%—Not comparable
AA ITBenchSource 47.7%—Not comparable
Coding
BenchmarkKimi K3Sakana Fugu-UltraResult
deepSweSource 67.5%—Not comparable
FrontierSWESource 81.2%—Not comparable
ProgramBenchSource 77.8%—Not comparable
Kimi Code Bench v2Source 72.9%—Not comparable
sweMarathonSource 42%—Not comparable
PostTrain BenchSource 36.6%—Not comparable
MLS-Bench LiteSource 48.3%—Not comparable
AA Coding IndexSource 76.2%—Not comparable
AA-SciCodeSource 58.7%—Not comparable
SWE-bench ProSource —73.7%Not comparable
Terminal-Bench 2.0Source —82.1%Not comparable
LiveCodeBench v6Source —93.2%Not comparable
LiveCodeBench ProSource —90.8%Not comparable
SciCodeSource —58.7%Not comparable
Reasoning
BenchmarkKimi K3Sakana Fugu-UltraResult
AA-LCRSource 74.7%—Not comparable
CritPtSource 23.4%—Not comparable
MRCRv2Source —93.6%Not comparable
KnowledgeSakana Fugu-Ultra wins
BenchmarkKimi K3Sakana Fugu-UltraResult
GPQASource 93.5%95.5%Sakana Fugu-Ultra leads
GPQA-DSource 93.5%95.5%Sakana Fugu-Ultra leads
HLESource 56%—Not comparable
HLE w/o toolsSource 43.5%50%Sakana Fugu-Ultra leads
Artificial Analysis Intelligence IndexSource 57.1%—Not comparable
AA-GPQA DiamondSource 93.5%—Not comparable
AA-HLESource 44.3%—Not comparable
AA-Omniscience IndexSource 18.4%—Not comparable
AA-Omniscience AccuracySource 46.0%—Not comparable
AA-Omniscience Hallucination RateSource 50.9%—Not comparable
MultimodalSakana Fugu-Ultra wins
BenchmarkKimi K3Sakana Fugu-UltraResult
OfficeQA ProSource 63.3%—Not comparable
MMMU-ProSource 81.6%—Not comparable
MMMU-Pro w/ PythonSource 83.4%—Not comparable
CharXiv w/o toolsSource 84.8%—Not comparable
CharXivSource 91.3%86.6%Kimi K3 leads
MathVisionSource 94.3%—Not comparable
MathVision w/ PythonSource 97.8%—Not comparable
BabyVision w/ PythonSource 85.7%—Not comparable
ZeroBenchSource 23.0%—Not comparable
ZeroBench w/ PythonSource 41.0%—Not comparable
WorldVQA ForceAnswerSource 51.0%—Not comparable
OmniDocBenchSource 91.1%—Not comparable
PerceptionBenchSource 58.5%—Not comparable
AA-MMMU-ProSource 80.5%—Not comparable
Design Arena WebsiteSource 1386—Not comparable
Frequently Asked Questions (4)

Which is better, Kimi K3 or Sakana Fugu-Ultra?

Kimi K3 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 K3 or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 61. Inside this category, HLE w/o tools is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Kimi K3 or Sakana Fugu-Ultra?

Kimi K3 has the edge for agentic tasks in this comparison, averaging 89.5 versus 82.1. 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 K3 or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for multimodal and grounded tasks in this comparison, averaging 86.6 versus 78.5. Inside this category, CharXiv is the benchmark that creates the most daylight between them.

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.