Skip to main content

Model comparison

Claude Opus 4.6 vs Sakana Fugu-Ultra

Data verified

Head-to-head evidence from 6 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

68.59/100
No comparison
N/A
1 category wins3 category wins

Public leaderboard positions: Claude Opus 4.6 #16 (Supported); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Opus 4.6 and Sakana Fugu-Ultra share 6 comparable benchmark results. 4 of 8 categories are comparable. 40 results are unique to Claude Opus 4.6; 5 to Sakana Fugu-Ultra.

Updated July 23, 2026
Shared results
6
Claude Opus 4.6 only
40
Sakana Fugu-Ultra only
5
Comparable categories
4 / 8

Treat this as a split decision. Claude Opus 4.6 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 6 shared benchmark results across 3 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

Claude Opus 4.6 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 is the reasoning model in the pair, while Claude Opus 4.6 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 Claude Opus 4.6 and Sakana Fugu-Ultra
CategoryClaude Opus 4.6ΔSakana Fugu-Ultra
KnowledgeClaude Opus 4.669.1Margin 26.4Sakana Fugu-Ultra95.5
MultimodalClaude Opus 4.677.3Margin 9.3Sakana Fugu-Ultra86.6
AgenticClaude Opus 4.673.0Margin 9.1Sakana Fugu-Ultra82.1
CodingClaude Opus 4.668.1Margin 3.6Sakana Fugu-Ultra64.5
ReasoningClaude Opus 4.6Not measuredMarginNo overlapSakana Fugu-Ultra93.6
MathClaude Opus 4.636.3MarginNo overlapSakana Fugu-UltraNot measured

Decisive benchmark drivers

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

More
A · Claude Opus 4.6B · Sakana Fugu-Ultra
  1. SWE-bench Pro

    Coding
    Source ↗
    A 53.4%B 73.7%
    Winner: Sakana Fugu-UltraΔ 20.3
    SWE-bench Pro: Claude Opus 4.6 scored 53.4%; Sakana Fugu-Ultra scored 73.7%. Sakana Fugu-Ultra wins this benchmark.
  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 65.4%B 82.1%
    Winner: Sakana Fugu-UltraΔ 16.7
    Terminal-Bench 2.0: Claude Opus 4.6 scored 65.4%; Sakana Fugu-Ultra scored 82.1%. Sakana Fugu-Ultra wins this benchmark.
  3. GPQA

    Knowledge
    Source ↗
    A 91.3%B 95.5%
    Winner: Sakana Fugu-UltraΔ 4.2
    GPQA: Claude Opus 4.6 scored 91.3%; 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.

MetricClaude Opus 4.6Sakana Fugu-UltraComparison
Input / output priceUSD per 1M tokensClaude Opus 4.6$5 input / $25 outputSakana Fugu-UltraNot availableA complete price comparison is not available.
Generation speedtokens per secondClaude Opus 4.640 tok/sSakana Fugu-UltraNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Opus 4.61.78 sSakana Fugu-UltraNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Opus 4.61MSakana Fugu-Ultra1MListed context windows are equal.

Benchmark Deep Dive

AgenticSakana Fugu-Ultra wins
BenchmarkClaude Opus 4.6Sakana Fugu-UltraResult
Terminal-Bench 2.0Source 65.4%82.1%Sakana Fugu-Ultra leads
BrowseCompSource 83.7%Not comparable
OSWorld-VerifiedSource 72.7%Not comparable
τ²-bench resultsSource 84.8%Not comparable
Claw-EvalSource 70.4%Not comparable
DeepSearchQASource 73.7%Not comparable
CyberGymSource 66.6%Not comparable
Gert LabsSource 61.85%Not comparable
ResearchClawBenchSource 19.9%Not comparable
JobBenchSource 36.7%Not comparable
CodingClaude Opus 4.6 wins
BenchmarkClaude Opus 4.6Sakana Fugu-UltraResult
SWE-bench VerifiedSource 80.8%Not comparable
SWE-bench Verified*Source 75.6%Not comparable
LiveCodeBench ProSource 70.7%90.8%Sakana Fugu-Ultra leads
SWE-bench ProSource 53.4%73.7%Sakana Fugu-Ultra leads
SWE-RebenchSource 65.3%Not comparable
React Native EvalsSource 84.1%Not comparable
Vibe Code BenchSource 57.57%Not comparable
AA-SciCodeSource 45.7%Not comparable
FrontierCode 1.1 MainSource 26.9%Not comparable
Terminal-Bench 2.0Source 82.1%Not comparable
LiveCodeBench v6Source 93.2%Not comparable
SciCodeSource 58.7%Not comparable
Reasoning
BenchmarkClaude Opus 4.6Sakana Fugu-UltraResult
AA-LCRSource 58.3%Not comparable
CritPtSource 2.8%Not comparable
MRCRv2Source 93.6%Not comparable
KnowledgeSakana Fugu-Ultra wins
BenchmarkClaude Opus 4.6Sakana Fugu-UltraResult
GPQASource 91.3%95.5%Sakana Fugu-Ultra leads
GPQA-DSource 89.2%95.5%Sakana Fugu-Ultra leads
SuperGPQASource 95%Not comparable
MMLU-ProSource 82%Not comparable
MMLU-Pro (Arcee)Source 89.1%Not comparable
HLESource 53%Not comparable
HLE w/o toolsSource 40%50%Sakana Fugu-Ultra leads
HealthBench HardSource 14.8%Not comparable
MedXpertQA (Text)Source 52.1%Not comparable
Artificial Analysis Intelligence IndexSource 37.8%Not comparable
AA-GPQA DiamondSource 84.0%Not comparable
AA-HLESource 18.6%Not comparable
AA-Omniscience IndexSource 3.5%Not comparable
AA-Omniscience AccuracySource 45.2%Not comparable
AA-Omniscience Hallucination RateSource 76.0%Not comparable
Math
BenchmarkClaude Opus 4.6Sakana Fugu-UltraResult
AIME25 (Arcee)Source 99.8%Not comparable
FrontierMath v2 (Tiers 1-3)Source 40.700%Not comparable
FrontierMath v2 (Tier 4)Source 22.900%Not comparable
MultimodalSakana Fugu-Ultra wins
BenchmarkClaude Opus 4.6Sakana Fugu-UltraResult
MMMU-ProSource 77.3%Not comparable
ERQASource 51.6%Not comparable
ScreenSpot ProSource 83.1%Not comparable
MedXpertQA (MM)Source 64.8%Not comparable
AA-MMMU-ProSource 72.5%Not comparable
Design Arena WebsiteSource 1325Not comparable
CharXivSource 86.6%Not comparable
Inst. Following
BenchmarkClaude Opus 4.6Sakana Fugu-UltraResult
AA-IFBenchSource 44.6%Not comparable
Frequently Asked Questions (5)

Which is better, Claude Opus 4.6 or Sakana Fugu-Ultra?

Claude Opus 4.6 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, Claude Opus 4.6 or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 69.1. Inside this category, HLE w/o tools is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Opus 4.6 or Sakana Fugu-Ultra?

Claude Opus 4.6 has the edge for coding in this comparison, averaging 68.1 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, Claude Opus 4.6 or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for agentic tasks in this comparison, averaging 82.1 versus 73. 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, Claude Opus 4.6 or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for multimodal and grounded tasks in this comparison, averaging 86.6 versus 77.3. Claude Opus 4.6 stays close enough that the answer can still flip depending on your workload.

Related Comparisons

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.