GPT-5.5 vs Sakana Fugu

Updated September 27, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.

Decision reading

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. 4 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A

GPT-5.5

OpenAI

69.13/100

Supported · Public rank #16

90% interval 63.4–74.8

Model B

Sakana Fugu

Sakana AI

—

Evidence status unavailable

90% interval unavailable

Shared results: 4
GPT-5.5 only: 35
Sakana Fugu only: 7
Like-for-like categories: 0 / 8

Supported: GPT-5.5How the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

No workload recommendation clears the current evidence threshold.

Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.

Show secondary and unsupported calls

Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Sakana Fugu is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Sakana Fugu is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

Pick the job you would use them for

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

64.1GPT-5.5—Sakana Fugu

Not comparable · BenchAlign v5.7

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboard Shortlist models for this job

Same basis rules as the category table below

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

HLE w/o toolsKnowledge
Normalized gap 5.8
GPT-5.5:41.4%
Sakana Fugu:47.2%
GPT-5.5 source Sakana Fugu source
GPQAKnowledge
Normalized gap 1.9
GPT-5.5:93.6%
Sakana Fugu:95.5%
GPT-5.5 source Sakana Fugu source
SWE-bench ProCoding
Normalized gap 0.4
GPT-5.5:58.6%
Sakana Fugu:59%
GPT-5.5 source Sakana Fugu source

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.7 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Not comparable

GPT-5.5: 60.1; Supported · #15/105
Sakana Fugu: Not ranked
Basis: BenchAlign v5.7 lane · 14 vs 1 public rows
Reading: Not comparable

Coding

Not comparable

GPT-5.5: 64.1; Supported · #11/135
Sakana Fugu: Not ranked
Basis: BenchAlign v5.7 lane · 9 vs 5 public rows
Reading: Not comparable

Reasoning

Not comparable

GPT-5.5: 65.9; #10/19
Sakana Fugu: 70.6; Unranked · 1 rankable row
Basis: Provisional lane · 2 vs 1 weighted rows
Reading: Not comparable

Multimodal

Not comparable

GPT-5.5: 71.4; #20/50
Sakana Fugu: 68.6; Unranked · 1 rankable row
Basis: Provisional lane · 2 vs 1 weighted rows
Reading: Not comparable

Knowledge

Not comparable

GPT-5.5: 70.0; Supported · #12/158
Sakana Fugu: Not ranked
Basis: BenchAlign v5.7 lane · 6 vs 3 public rows
Reading: Not comparable

Multilingual

Not comparable

GPT-5.5: Not ranked
Sakana Fugu: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Instruction following

Not comparable

GPT-5.5: 91.9; #7/124
Sakana Fugu: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Math

Not comparable

GPT-5.5: 69.4; Unranked · 3 rankable rows
Sakana Fugu: Not ranked
Basis: Provisional lane · 2 vs 0 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for GPT-5.5 and Sakana Fugu
Category	GPT-5.5	Sakana Fugu	Basis	Reading
Agentic	60.1Supported · #15/105	Not ranked	Not comparableBenchAlign v5.7 lane · 14 vs 1 public rows	Not comparable
Coding	64.1Supported · #11/135	Not ranked	Not comparableBenchAlign v5.7 lane · 9 vs 5 public rows	Not comparable
Reasoning	65.9#10/19	70.6Unranked · 1 rankable row	Not comparableProvisional lane · 2 vs 1 weighted rows	Not comparable
Multimodal	71.4#20/50	68.6Unranked · 1 rankable row	Not comparableProvisional lane · 2 vs 1 weighted rows	Not comparable
Knowledge	70.0Supported · #12/158	Not ranked	Not comparableBenchAlign v5.7 lane · 6 vs 3 public rows	Not comparable
Multilingual	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Instruction following	91.9#7/124	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Math	69.4Unranked · 3 rankable rows	Not ranked	Not comparableProvisional lane · 2 vs 0 weighted rows	Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

GPT-5.5: $0.02; Fits in one request
Sakana Fugu: API rate not published; Fits in one request

Sakana Fugu has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

GPT-5.5: $0.34; Fits in one request
Sakana Fugu: API rate not published; Fits in one request

Sakana Fugu has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

GPT-5.5: $0.5; Fits in one request
Sakana Fugu: API rate not published; Fits in one request; Cached-input rate unavailable

Sakana Fugu has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

SpecificationGPT-5.5Sakana Fugu

Context window

Maximum documented context; output-token limits may be lower.

GPT-5.5

OpenAI pricing

Sakana Fugu

API model ID

GPT-5.5

gpt-5.5

OpenAI pricing

Sakana Fugu

Not sourced

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

GPT-5.5

$0.5 per 1M cached input tokens

OpenAI pricing

Sakana Fugu

No comparable hosted API rate

Documented inputs

GPT-5.5

Not sourced

Sakana Fugu

Not sourced

Documented outputs

GPT-5.5

Not sourced

Sakana Fugu

Not sourced

Provider availability

GPT-5.5

Not sourced

Sakana Fugu

Not sourced

Reasoning profile

GPT-5.5

Reasoning

Sakana Fugu

Reasoning

Weight access

GPT-5.5

Proprietary

Sakana Fugu

Proprietary

License

GPT-5.5

Proprietary

Sakana Fugu

Proprietary

Release date

GPT-5.5

2026-04-23

Sakana Fugu

2026-06-22

If you already use one of these models

Deployment change: The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal: At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
Workload cost: A complete comparable API-rate estimate is not available for both models.
Context tradeoff: Both models list 1M.

Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, GPT-5.5 or Sakana Fugu?

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, GPT-5.5 or Sakana Fugu?

Sakana Fugu is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, GPT-5.5 or Sakana Fugu?

Sakana Fugu is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, GPT-5.5 or Sakana Fugu?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, GPT-5.5 or Sakana Fugu?

Both models list the same context window, 1M.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence46 rows

Agentic

Terminal-Bench 2.0
GPT-5.582%
Source
Sakana Fugu—
Not directly comparable
CyberGym
GPT-5.581.8%
Source
Sakana Fugu—
Not directly comparable
BrowseComp
GPT-5.584.4%
Source
Sakana Fugu—
Not directly comparable
OSWorld-Verified
GPT-5.578.7%
Source
Sakana Fugu—
Not directly comparable
MCP Atlas
GPT-5.575.3%
Source
Sakana Fugu—
Not directly comparable
Toolathlon
GPT-5.555.6%
Source
Sakana Fugu—
Not directly comparable
τ²-bench results
GPT-5.598%
Source
Sakana Fugu—
Not directly comparable
Gert Labs
GPT-5.572.93%
Source
Sakana Fugu—
Not directly comparable
ResearchClawBench
GPT-5.517.0%
Source
Sakana Fugu—
Not directly comparable
OSWorld 2.0
GPT-5.513.0%
Source
Sakana Fugu—
Not directly comparable
JobBench
GPT-5.542.7%
Source
Sakana Fugu—
Not directly comparable
ExploitGym
GPT-5.513.4%
Source
Sakana Fugu—
Not directly comparable
Terminal-Bench 2.1 (Vals)
GPT-5.576.4%
Source
Sakana Fugu—
Not directly comparable
ApprenticeBench
GPT-5.520%
Source
Sakana Fugu—
Not directly comparable
Terminal-Bench 2.1
GPT-5.5—
Sakana Fugu80.2%
Source
Not directly comparable

Coding

SWE-bench Pro
GPT-5.558.6%
Source
Sakana Fugu59%
Source
Sakana Fugu leads this result
Terminal-Bench 2.0
GPT-5.582.0%
Source
Sakana Fugu—
Not directly comparable
Vibe Code Bench
GPT-5.569.85%
Source
Sakana Fugu—
Not directly comparable
React Native Evals
GPT-5.584.7%
Source
Sakana Fugu—
Not directly comparable
cursorBench31
GPT-5.559.2%
Source
Sakana Fugu—
Not directly comparable
cursorBench32
GPT-5.558.4%
Source
Sakana Fugu—
Not directly comparable
FrontierCode 1.1 Main
GPT-5.543.0%
Source
Sakana Fugu—
Not directly comparable
LiveCodeBench (Vals)
GPT-5.585.3%
Source
Sakana Fugu—
Not directly comparable
SWE-bench (Vals)
GPT-5.582.6%
Source
Sakana Fugu—
Not directly comparable
Terminal-Bench 2.1
GPT-5.5—
Sakana Fugu80.2%
Source
Not directly comparable
LiveCodeBench v6
GPT-5.5—
Sakana Fugu92.9%
Source
Not directly comparable
LiveCodeBench Pro
GPT-5.5—
Sakana Fugu87.8%
Source
Not directly comparable
SciCode
GPT-5.5—
Sakana Fugu60.1%
Source
Not directly comparable

Reasoning

MRCR v2 64K-128K
GPT-5.583.1%
Source
Sakana Fugu—
Not directly comparable
MRCR v2 128K-256K
GPT-5.587.5%
Source
Sakana Fugu—
Not directly comparable
ARC-AGI-2
GPT-5.585%
Source
Sakana Fugu—
Not directly comparable
ARC-AGI-3
GPT-5.50.4%
Source
Sakana Fugu—
Not directly comparable
MRCRv2
GPT-5.5—
Sakana Fugu86.6%
Source
Not directly comparable

Multimodal

MMMU-Pro
GPT-5.581.2%
Source
Sakana Fugu—
Not directly comparable
MMMU-Pro w/ Python
GPT-5.583.2%
Source
Sakana Fugu—
Not directly comparable
OfficeQA Pro
GPT-5.554.1%
Source
Sakana Fugu—
Not directly comparable
CharXiv
GPT-5.5—
Sakana Fugu85.1%
Source
Not directly comparable

Knowledge

GPQA
GPT-5.593.6%
Source
Sakana Fugu95.5%
Source
Sakana Fugu leads this result
GPQA-D
GPT-5.593.6%
Source
Sakana Fugu95.5%
Source
Sakana Fugu leads this result
HLE
GPT-5.552.2%
Source
Sakana Fugu—
Not directly comparable
HLE w/o tools
GPT-5.541.4%
Source
Sakana Fugu47.2%
Source
Sakana Fugu leads this result
GPQA Diamond (Vals)
GPT-5.593.2%
Source
Sakana Fugu—
Not directly comparable
MMLU-Pro (Vals)
GPT-5.588.1%
Source
Sakana Fugu—
Not directly comparable

Math

FrontierMath (legacy)
GPT-5.551.7%
Source
Sakana Fugu—
Not directly comparable
FrontierMath v2 (Tiers 1-3)
GPT-5.551.700%
Source
Sakana Fugu—
Not directly comparable
FrontierMath v2 (Tier 4)
GPT-5.535.400%
Source
Sakana Fugu—
Not directly comparable

46 public results · 4 shared

Related comparisons

Compare API pricing Read the methodology Open the model selector

Watch GPT-5.5 vs Sakana Fugu

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.

Last updated September 27, 2026

GPT-5.5 vs Sakana Fugu

Decision reading

Which one for your work

Coding work

Agentic work

Long documents

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

Which one for a specific job

What is actually comparable

Shape of the matched evidence

Category results, on a stated basis

Agentic

Coding

Reasoning

Multimodal

Knowledge

Multilingual

Instruction following

Math

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

If you already use one of these models

Questions

Which is better, GPT-5.5 or Sakana Fugu?

Which is better for coding, GPT-5.5 or Sakana Fugu?

Which is better for agentic tasks, GPT-5.5 or Sakana Fugu?

Which costs less, GPT-5.5 or Sakana Fugu?

Which has the larger context window, GPT-5.5 or Sakana Fugu?

Benchmark evidence

Agentic

Coding

Reasoning

Multimodal

Knowledge

Math

Related comparisons

Watch GPT-5.5 vs Sakana Fugu