Skip to main content
BenchLM
Advertise

Model comparison

Inkling vs Sakana Fugu-Ultra

Data verified

Head-to-head evidence from 7 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Inkling
Thinking Machines Lab
67.54/100
No comparison
N/A
1 category wins3 category wins

Public leaderboard positions: Inkling #20 (Supported); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Inkling and Sakana Fugu-Ultra share 7 comparable benchmark results. 4 of 8 categories are comparable. 25 results are unique to Inkling; 4 to Sakana Fugu-Ultra.

Updated July 23, 2026
Shared results
7
Inkling only
25
Sakana Fugu-Ultra only
4
Comparable categories
4 / 8

Treat this as a split decision. Inkling 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 want the stronger reasoning-first profile.

Confidence note. This is a partial-evidence comparison with 7 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

Inkling 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 Inkling 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.

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 Inkling and Sakana Fugu-Ultra
CategoryInklingΔSakana Fugu-Ultra
KnowledgeInkling51.6Margin→ 43.9Sakana Fugu-Ultra95.5
AgenticInkling69.4Margin→ 12.7Sakana Fugu-Ultra82.1
MultimodalInkling76.5Margin→ 10.1Sakana Fugu-Ultra86.6
CodingInkling68.6Margin← 4.1Sakana Fugu-Ultra64.5
ReasoningInklingNot measuredMarginNo overlapSakana Fugu-Ultra93.6
MathInkling97.1MarginNo overlapSakana Fugu-UltraNot measured
Inst. FollowingInkling79.8MarginNo overlapSakana Fugu-UltraNot measured

Decisive benchmark drivers

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

More
A · InklingB · Sakana Fugu-Ultra

  1. SWE-bench Pro

    Coding
    Source ↗
    A 54.3%B 73.7%
    Winner: Sakana Fugu-UltraΔ 19.4
    SWE-bench Pro: Inkling scored 54.3%; Sakana Fugu-Ultra scored 73.7%. Sakana Fugu-Ultra wins this benchmark.

  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 63.8%B 82.1%
    Winner: Sakana Fugu-UltraΔ 18.3
    Terminal-Bench 2.0: Inkling scored 63.8%; Sakana Fugu-Ultra scored 82.1%. Sakana Fugu-Ultra wins this benchmark.

  3. GPQA

    Knowledge
    Source ↗
    A 87.9%B 95.5%
    Winner: Sakana Fugu-UltraΔ 7.6
    GPQA: Inkling scored 87.9%; Sakana Fugu-Ultra scored 95.5%. Sakana Fugu-Ultra wins this benchmark.

  4. CharXiv

    Multimodal
    Source ↗
    A 82%B 86.6%
    Winner: Sakana Fugu-UltraΔ 4.6
    CharXiv: Inkling scored 82%; 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.

MetricInklingSakana Fugu-UltraComparison
Input / output priceUSD per 1M tokensInkling$1.87 input / $4.68 outputSakana Fugu-UltraNot availableA complete price comparison is not available.
Generation speedtokens per secondInklingNot availableSakana Fugu-UltraNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenInklingNot availableSakana Fugu-UltraNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensInkling1MSakana Fugu-Ultra1MListed context windows are equal.

Benchmark Deep Dive

AgenticSakana Fugu-Ultra wins
BenchmarkInklingSakana Fugu-UltraResult
Terminal-Bench 2.0Source 63.8%82.1%Sakana Fugu-Ultra leads
BrowseCompSource 77.1%—Not comparable
MCP AtlasSource 74.1%—Not comparable
Design Arena Agentic Web DevSource 1257—Not comparable
AA Agentic IndexSource 32.3%—Not comparable
GDPval-AASource 36.9%—Not comparable
GDPval-AASource 1239—Not comparable
AA BriefcaseSource 836—Not comparable
AA Tau3 BankingSource 23.7%—Not comparable
CodingInkling wins
BenchmarkInklingSakana Fugu-UltraResult
SWE-bench VerifiedSource 77.6%—Not comparable
SWE-bench ProSource 54.3%73.7%Sakana Fugu-Ultra leads
Terminal-Bench 2.0Source 63.8%82.1%Sakana Fugu-Ultra leads
AA Coding IndexSource 52.1%—Not comparable
AA-SciCodeSource 46.1%—Not comparable
LiveCodeBench v6Source —93.2%Not comparable
LiveCodeBench ProSource —90.8%Not comparable
SciCodeSource —58.7%Not comparable
Reasoning
BenchmarkInklingSakana Fugu-UltraResult
AA-LCRSource 63.3%—Not comparable
CritPtSource 5.4%—Not comparable
MRCRv2Source —93.6%Not comparable
KnowledgeSakana Fugu-Ultra wins
BenchmarkInklingSakana Fugu-UltraResult
GPQASource 87.9%95.5%Sakana Fugu-Ultra leads
GPQA-DSource 87.9%95.5%Sakana Fugu-Ultra leads
HLESource 46%—Not comparable
HLE w/o toolsSource 30%50%Sakana Fugu-Ultra leads
Artificial Analysis Intelligence IndexSource 40.7%—Not comparable
AA-GPQA DiamondSource 87.2%—Not comparable
AA-HLESource 29.7%—Not comparable
AA-Omniscience IndexSource 2.1%—Not comparable
AA-Omniscience AccuracySource 40.0%—Not comparable
AA-Omniscience Hallucination RateSource 63.1%—Not comparable
Math
BenchmarkInklingSakana Fugu-UltraResult
AIME26Source 97.1%—Not comparable
MultimodalSakana Fugu-Ultra wins
BenchmarkInklingSakana Fugu-UltraResult
MMMU-ProSource 73.5%—Not comparable
CharXivSource 82%86.6%Sakana Fugu-Ultra leads
CharXiv w/o toolsSource 78.1%—Not comparable
AA-MMMU-ProSource 73.5%—Not comparable
Inst. Following
BenchmarkInklingSakana Fugu-UltraResult
IFBenchSource 79.8%—Not comparable
Frequently Asked Questions (5)

Which is better, Inkling or Sakana Fugu-Ultra?

Inkling 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, Inkling or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 51.6. Inside this category, HLE w/o tools is the benchmark that creates the most daylight between them.

Which is better for coding, Inkling or Sakana Fugu-Ultra?

Inkling has the edge for coding in this comparison, averaging 68.6 versus 64.5. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

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

Sakana Fugu-Ultra has the edge for agentic tasks in this comparison, averaging 82.1 versus 69.4. 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, Inkling or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for multimodal and grounded tasks in this comparison, averaging 86.6 versus 76.5. Inside this category, CharXiv is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Thinking Machines Lab 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.