Skip to main content

Model comparison

Command A+ vs Sakana Fugu-Ultra

Data verified

Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.

47.51/100
No comparison
N/A
0 category wins1 category wins

Public leaderboard positions: Command A+ #135 (Estimated); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Command A+ and Sakana Fugu-Ultra share 1 comparable benchmark result. 1 of 8 categories are comparable. 20 results are unique to Command A+; 10 to Sakana Fugu-Ultra.

Updated July 23, 2026
Shared results
1
Command A+ only
20
Sakana Fugu-Ultra only
10
Comparable categories
1 / 8

Treat this as a split decision. Command A+ makes more sense if its workflow fits your team better; Sakana Fugu-Ultra is the better fit if multimodal & grounded is the priority or you need the larger 1M context window.

Confidence note. This is a partial-evidence comparison with 1 shared benchmark result across 1 evidence category; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Command A+ 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 128K for Command A+.

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 Command A+ and Sakana Fugu-Ultra
CategoryCommand A+ΔSakana Fugu-Ultra
MultimodalCommand A+59.3Margin 27.3Sakana Fugu-Ultra86.6
AgenticCommand A+Not measuredMarginNo overlapSakana Fugu-Ultra82.1
CodingCommand A+Not measuredMarginNo overlapSakana Fugu-Ultra64.5
ReasoningCommand A+Not measuredMarginNo overlapSakana Fugu-Ultra93.6
KnowledgeCommand A+Not measuredMarginNo overlapSakana Fugu-Ultra95.5

Decisive benchmark drivers

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

More
A · Command A+B · Sakana Fugu-Ultra
  1. CharXiv

    Multimodal
    Source ↗
    A 52.7%B 86.6%
    Winner: Sakana Fugu-UltraΔ 33.9
    CharXiv: Command A+ scored 52.7%; 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.

MetricCommand A+Sakana Fugu-UltraComparison
Input / output priceUSD per 1M tokensCommand A+$2.5 input / $10 outputSakana Fugu-UltraNot availableA complete price comparison is not available.
Generation speedtokens per secondCommand A+272 tok/sSakana Fugu-UltraNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenCommand A+0.25 sSakana Fugu-UltraNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensCommand A+128KSakana Fugu-Ultra1MSakana Fugu-Ultra lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkCommand A+Sakana Fugu-UltraResult
τ²-bench resultsSource 80.7%Not comparable
AA Agentic IndexSource 9.2%Not comparable
GDPval-AASource 10.7%Not comparable
GDPval-AASource 714Not comparable
terminalBenchHardSource 25%Not comparable
Terminal-Bench 2.0Source 82.1%Not comparable
Coding
BenchmarkCommand A+Sakana Fugu-UltraResult
AA Coding IndexSource 27.9%Not comparable
AA-SciCodeSource 37.8%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
BenchmarkCommand A+Sakana Fugu-UltraResult
AA-LCRSource 46.0%Not comparable
CritPtSource 0.3%Not comparable
MRCRv2Source 93.6%Not comparable
Knowledge
BenchmarkCommand A+Sakana Fugu-UltraResult
Artificial Analysis Intelligence IndexSource 22.5%Not comparable
AA-GPQA DiamondSource 76.1%Not comparable
AA-HLESource 11.4%Not comparable
AA-Omniscience IndexSource -4.0%Not comparable
AA-Omniscience AccuracySource 8.9%Not comparable
AA-Omniscience Hallucination RateSource 14.1%Not comparable
AA Openness IndexSource 38.9%Not comparable
GPQASource 95.5%Not comparable
GPQA-DSource 95.5%Not comparable
HLE w/o toolsSource 50%Not comparable
MultimodalSakana Fugu-Ultra wins
BenchmarkCommand A+Sakana Fugu-UltraResult
MMMUSource 75.1%Not comparable
MMMU-ProSource 63%Not comparable
CharXivSource 52.7%86.6%Sakana Fugu-Ultra leads
AA-MMMU-ProSource 63.2%Not comparable
Inst. Following
BenchmarkCommand A+Sakana Fugu-UltraResult
AA-IFBenchSource 73.9%Not comparable
Frequently Asked Questions (2)

Which is better, Command A+ or Sakana Fugu-Ultra?

Command A+ 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 multimodal and grounded tasks, Command A+ or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for multimodal and grounded tasks in this comparison, averaging 86.6 versus 59.3. Inside this category, CharXiv is the benchmark that creates the most daylight between them.

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.