Skip to main content

Model comparison

GPT-5.3 Codex vs Sakana Fugu-Ultra

Data verified

Head-to-head evidence from 2 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

66.69/100
No comparison
N/A
1 category wins1 category wins

Public leaderboard positions: GPT-5.3 Codex #26 (Supported); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-5.3 Codex and Sakana Fugu-Ultra share 2 comparable benchmark results. 2 of 8 categories are comparable. 19 results are unique to GPT-5.3 Codex; 9 to Sakana Fugu-Ultra.

Updated July 23, 2026
Shared results
2
GPT-5.3 Codex only
19
Sakana Fugu-Ultra only
9
Comparable categories
2 / 8

Treat this as a split decision. GPT-5.3 Codex makes more sense if coding is the priority; Sakana Fugu-Ultra is the better fit if agentic is the priority or you need the larger 1M context window.

Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 2 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

GPT-5.3 Codex 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 400K for GPT-5.3 Codex.

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 GPT-5.3 Codex and Sakana Fugu-Ultra
CategoryGPT-5.3 CodexΔSakana Fugu-Ultra
AgenticGPT-5.3 Codex71.4Margin 10.7Sakana Fugu-Ultra82.1
CodingGPT-5.3 Codex67.2Margin 2.7Sakana Fugu-Ultra64.5
ReasoningGPT-5.3 CodexNot measuredMarginNo overlapSakana Fugu-Ultra93.6
KnowledgeGPT-5.3 CodexNot measuredMarginNo overlapSakana Fugu-Ultra95.5
MultimodalGPT-5.3 CodexNot measuredMarginNo overlapSakana Fugu-Ultra86.6

Decisive benchmark drivers

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

More
A · GPT-5.3 CodexB · Sakana Fugu-Ultra
  1. SWE-bench Pro

    Coding
    Source ↗
    A 56.8%B 73.7%
    Winner: Sakana Fugu-UltraΔ 16.9
    SWE-bench Pro: GPT-5.3 Codex scored 56.8%; Sakana Fugu-Ultra scored 73.7%. Sakana Fugu-Ultra wins this benchmark.
  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 77.3%B 82.1%
    Winner: Sakana Fugu-UltraΔ 4.8
    Terminal-Bench 2.0: GPT-5.3 Codex scored 77.3%; Sakana Fugu-Ultra scored 82.1%. Sakana Fugu-Ultra wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGPT-5.3 CodexSakana Fugu-UltraComparison
Input / output priceUSD per 1M tokensGPT-5.3 Codex$1.75 input / $14 outputSakana Fugu-UltraNot availableA complete price comparison is not available.
Generation speedtokens per secondGPT-5.3 Codex79 tok/sSakana Fugu-UltraNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGPT-5.3 Codex88.26 sSakana Fugu-UltraNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGPT-5.3 Codex400KSakana Fugu-Ultra1MSakana Fugu-Ultra lists the larger context window.

Benchmark Deep Dive

AgenticSakana Fugu-Ultra wins
BenchmarkGPT-5.3 CodexSakana Fugu-UltraResult
Terminal-Bench 2.0Source 77.3%82.1%Sakana Fugu-Ultra leads
OSWorld-VerifiedSource 64.7%Not comparable
τ²-bench resultsSource 86%Not comparable
Gert LabsSource 57.47%Not comparable
JobBenchSource 33.7%Not comparable
CodingGPT-5.3 Codex wins
BenchmarkGPT-5.3 CodexSakana Fugu-UltraResult
SWE-bench VerifiedSource 85%Not comparable
SWE-bench ProSource 56.8%73.7%Sakana Fugu-Ultra leads
SWE-RebenchSource 58.2%Not comparable
Vibe Code BenchSource 61.77%Not comparable
AA-SciCodeSource 53.2%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
BenchmarkGPT-5.3 CodexSakana Fugu-UltraResult
AA-LCRSource 74.0%Not comparable
CritPtSource 16.9%Not comparable
MRCRv2Source 93.6%Not comparable
Knowledge
BenchmarkGPT-5.3 CodexSakana Fugu-UltraResult
Artificial Analysis Intelligence IndexSource 44.3%Not comparable
AA-GPQA DiamondSource 91.5%Not comparable
AA-HLESource 39.9%Not comparable
AA-Omniscience IndexSource 9.9%Not comparable
AA-Omniscience AccuracySource 51.8%Not comparable
AA-Omniscience Hallucination RateSource 86.9%Not comparable
GPQASource 95.5%Not comparable
GPQA-DSource 95.5%Not comparable
HLE w/o toolsSource 50%Not comparable
Multimodal
BenchmarkGPT-5.3 CodexSakana Fugu-UltraResult
AA-MMMU-ProSource 78.5%Not comparable
Design Arena WebsiteSource 1193Not comparable
CharXivSource 86.6%Not comparable
Inst. Following
BenchmarkGPT-5.3 CodexSakana Fugu-UltraResult
AA-IFBenchSource 75.4%Not comparable
Frequently Asked Questions (3)

Which is better, GPT-5.3 Codex or Sakana Fugu-Ultra?

GPT-5.3 Codex 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 coding, GPT-5.3 Codex or Sakana Fugu-Ultra?

GPT-5.3 Codex has the edge for coding in this comparison, averaging 67.2 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, GPT-5.3 Codex or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for agentic tasks in this comparison, averaging 82.1 versus 71.4. Inside this category, Terminal-Bench 2.0 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.