Agentic
Directional only- GPT-5.4
- 77.2
- Sakana Fugu
- 80.2
- Weighted basis
- 3 vs 1 rows
- Reading
- Directional only
GPT-5.4 vs Sakana Fugu
Updated August 13, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
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.
7 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
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.
Long documents
Prompts that approach the documented context limit
GPT-5.4
GPT-5.4 has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
31 GPT-5.4 only
7 Shared
4 Sakana Fugu only
- Shared results
- 7
- GPT-5.4 only
- 31
- Sakana Fugu only
- 4
- Like-for-like categories
- 0 / 8
4 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Coding
Directional only- GPT-5.4
- 57.7
- Sakana Fugu
- 59.7
- Weighted basis
- 1 vs 2 rows
- Reading
- Directional only
Knowledge
Directional only- GPT-5.4
- 57.6
- Sakana Fugu
- 95.5
- Weighted basis
- 2 vs 1 rows
- Reading
- Directional only
Multimodal
Directional only- GPT-5.4
- 73.2
- Sakana Fugu
- 85.1
- Weighted basis
- 3 vs 1 rows
- Reading
- Directional only
Reasoning
Not comparable- GPT-5.4
- 74.0
- Sakana Fugu
- 86.6
- Weighted basis
- 1 vs 1 rows
- Reading
- Not comparable
Math
Not comparable- GPT-5.4
- 42.5
- Sakana Fugu
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- GPT-5.4
- Not measured
- Sakana Fugu
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- GPT-5.4
- Not measured
- Sakana Fugu
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | GPT-5.4 | Sakana Fugu | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 77.2 | 80.2 | Directional only3 vs 1 rows | Directional only |
| Coding | 57.7 | 59.7 | Directional only1 vs 2 rows | Directional only |
| Knowledge | 57.6 | 95.5 | Directional only2 vs 1 rows | Directional only |
| Multimodal | 73.2 | 85.1 | Directional only3 vs 1 rows | Directional only |
| Reasoning | 74.0 | 86.6 | Not comparable1 vs 1 rows | Not comparable |
| Math | 42.5 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
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.
Terminal-Bench 2.0
Agentic
GPQA
Knowledge
CharXiv
Multimodal
SWE-bench Pro
Coding
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-5.4
- $0.01
- 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-5.4
- $0.17
- 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-5.4
- $0.25
- 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.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGPT-5.4Sakana Fugu
Context window
Maximum documented context; output-token limits may be lower.
GPT-5.4
1.05M
OpenAI pricingSakana Fugu
1M
API model ID
GPT-5.4
gpt-5.4
OpenAI pricingSakana 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-5.4
$0.25 per 1M cached input tokens
OpenAI pricingSakana Fugu
No comparable hosted API rate
Documented inputs
GPT-5.4
Not sourced
Sakana Fugu
Not sourced
Documented outputs
GPT-5.4
Not sourced
Sakana Fugu
Not sourced
Provider availability
GPT-5.4
Not sourced
Sakana Fugu
Not sourced
Reasoning profile
GPT-5.4
Reasoning
Sakana Fugu
Reasoning
Weight access
GPT-5.4
Proprietary
Sakana Fugu
Proprietary
License
GPT-5.4
Proprietary
Sakana Fugu
Proprietary
Release date
GPT-5.4
2026-03-05
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
- GPT-5.4 has the larger documented window (1.05M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence42 rows
Agentic
Terminal-Bench 2.0
GPT-5.475.1%SourceSakana Fugu80.2%SourceSakana Fugu leads this result
CyberGym
GPT-5.479.0%SourceSakana Fugu—Not directly comparable
BrowseComp
GPT-5.482.7%SourceSakana Fugu—Not directly comparable
OSWorld-Verified
GPT-5.475%SourceSakana Fugu—Not directly comparable
MCP Atlas
GPT-5.470.6%SourceSakana Fugu—Not directly comparable
Toolathlon
GPT-5.454.6%SourceSakana Fugu—Not directly comparable
τ²-bench results
GPT-5.498.9%SourceSakana Fugu—Not directly comparable
Claw-Eval
GPT-5.460.3%SourceSakana Fugu—Not directly comparable
DeepSearchQA
GPT-5.473.6%SourceSakana Fugu—Not directly comparable
Gert Labs
GPT-5.464.89%SourceSakana Fugu—Not directly comparable
ResearchClawBench
GPT-5.415.3%SourceSakana Fugu—Not directly comparable
JobBench
GPT-5.438.9%SourceSakana Fugu—Not directly comparable
ExploitGym
GPT-5.46.0%SourceSakana Fugu—Not directly comparable
Coding
LiveCodeBench Pro
GPT-5.487.5%SourceSakana Fugu87.8%SourceSakana Fugu leads this result
SWE-bench Pro
GPT-5.457.7%SourceSakana Fugu59%SourceSakana Fugu leads this result
React Native Evals
GPT-5.485.3%SourceSakana Fugu—Not directly comparable
Vibe Code Bench
GPT-5.467.42%SourceSakana Fugu—Not directly comparable
EEBench
GPT-5.438.5%SourceSakana Fugu—Not directly comparable
Terminal-Bench 2.0
GPT-5.4—Sakana Fugu80.2%SourceNot directly comparable
LiveCodeBench v6
GPT-5.4—Sakana Fugu92.9%SourceNot directly comparable
SciCode
GPT-5.4—Sakana Fugu60.1%SourceNot directly comparable
Reasoning
Knowledge
GPQA
GPT-5.492.8%SourceSakana Fugu95.5%SourceSakana Fugu leads this result
HLE
GPT-5.452.1%SourceSakana Fugu—Not directly comparable
HLE w/o tools
GPT-5.439.8%SourceSakana Fugu47.2%SourceSakana Fugu leads this result
GPQA-D
GPT-5.492.8%SourceSakana Fugu95.5%SourceSakana Fugu leads this result
HealthBench Hard
GPT-5.440.1%SourceSakana Fugu—Not directly comparable
MedXpertQA (Text)
GPT-5.459.6%SourceSakana Fugu—Not directly comparable
HealthBench Professional
GPT-5.448.1%SourceSakana Fugu—Not directly comparable
Math
Multimodal
MMMU-Pro
GPT-5.481.2%SourceSakana Fugu—Not directly comparable
OfficeQA Pro
GPT-5.453.2%SourceSakana Fugu—Not directly comparable
MMMU-Pro w/ Python
GPT-5.482.1%SourceSakana Fugu—Not directly comparable
CharXiv
GPT-5.482.8%SourceSakana Fugu85.1%SourceSakana Fugu leads this result
ERQA
GPT-5.465.4%SourceSakana Fugu—Not directly comparable
SimpleVQA
GPT-5.461.1%SourceSakana Fugu—Not directly comparable
ScreenSpot Pro
GPT-5.485.4%SourceSakana Fugu—Not directly comparable
ZeroBench
GPT-5.441.0%SourceSakana Fugu—Not directly comparable
MedXpertQA (MM)
GPT-5.477.1%SourceSakana Fugu—Not directly comparable
Frequently asked questions
Which is better, GPT-5.4 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-5.4 or Sakana Fugu?
The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, GPT-5.4 or Sakana Fugu?
The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which costs less, GPT-5.4 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-5.4 or Sakana Fugu?
GPT-5.4 has the larger documented context window: 1.05M, compared with 1M.
Related comparisons
Last updated August 13, 2026
Watch GPT-5.4 vs Sakana Fugu
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.