Agentic
Not comparable- Fugu Cyber
- Not ranked
- Sakana Fugu-Ultra
- Not ranked
- Basis
- BenchAlign lane · 2 vs 1 public rows
- Reading
- Not comparable
Fugu Cyber vs Sakana Fugu-Ultra
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload. This is a same-family comparison, so migration details appear when the source data supports them.
Decision reading
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.
0 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
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
Fugu Cyber and Sakana Fugu-Ultra are 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
Fugu Cyber and Sakana Fugu-Ultra are 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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
2 Fugu Cyber only
11 Sakana Fugu-Ultra only
- Shared results
- 0
- Fugu Cyber only
- 2
- Sakana Fugu-Ultra only
- 11
- Like-for-like categories
- 0 / 8
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign 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.
Coding
Not comparable- Fugu Cyber
- Not ranked
- Sakana Fugu-Ultra
- Not ranked
- Basis
- BenchAlign lane · 0 vs 5 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Fugu Cyber
- Not ranked
- Sakana Fugu-Ultra
- 77.9
- Unranked · 1 rankable row
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- Fugu Cyber
- Not ranked
- Sakana Fugu-Ultra
- Not ranked
- Basis
- BenchAlign lane · 0 vs 3 public rows
- Reading
- Not comparable
Math
Not comparable- Fugu Cyber
- Not ranked
- Sakana Fugu-Ultra
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Fugu Cyber
- Not ranked
- Sakana Fugu-Ultra
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Fugu Cyber
- Not ranked
- Sakana Fugu-Ultra
- 72.5
- Unranked · 1 rankable row
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Fugu Cyber
- Not ranked
- Sakana Fugu-Ultra
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Fugu Cyber | Sakana Fugu-Ultra | Basis | Reading |
|---|---|---|---|---|
| Agentic | Not ranked | Not ranked | Not comparableBenchAlign lane · 2 vs 1 public rows | Not comparable |
| Coding | Not ranked | Not ranked | Not comparableBenchAlign lane · 0 vs 5 public rows | Not comparable |
| Reasoning | Not ranked | 77.9Unranked · 1 rankable row | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Knowledge | Not ranked | Not ranked | Not comparableBenchAlign lane · 0 vs 3 public rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | 72.5Unranked · 1 rankable row | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
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
- Fugu Cyber
- $0.024
- Fits in one request
- Sakana Fugu-Ultra
- API rate not published
- Fits in one request
Sakana Fugu-Ultra has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Fugu Cyber
- $0.408
- Fits in one request
- Sakana Fugu-Ultra
- API rate not published
- Fits in one request
Sakana Fugu-Ultra has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Fugu Cyber
- $0.6
- Fits in one request
- Sakana Fugu-Ultra
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Sakana Fugu-Ultra 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.
SpecificationFugu CyberSakana Fugu-Ultra
Context window
Maximum documented context; output-token limits may be lower.
Fugu Cyber
1M
Sakana Fugu-Ultra
1M
API model ID
Fugu Cyber
Not sourced
Sakana Fugu-Ultra
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Fugu Cyber
$0.6 per 1M cached input tokens
Sakana Fugu-Ultra
No comparable hosted API rate
Documented inputs
Fugu Cyber
Not sourced
Sakana Fugu-Ultra
Not sourced
Documented outputs
Fugu Cyber
Not sourced
Sakana Fugu-Ultra
Not sourced
Provider availability
Fugu Cyber
Not sourced
Sakana Fugu-Ultra
Not sourced
Reasoning profile
Fugu Cyber
Reasoning
Sakana Fugu-Ultra
Reasoning
Weight access
Fugu Cyber
Proprietary
Sakana Fugu-Ultra
Proprietary
License
Fugu Cyber
Proprietary
Sakana Fugu-Ultra
Proprietary
Release date
Fugu Cyber
2026-07-21
Sakana Fugu-Ultra
2026-06-22
If you are choosing between sibling variants
- Deployment change
- Both entries list Sakana AI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
- 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.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence13 rows
Agentic
Coding
SWE-bench Pro
Fugu Cyber—Sakana Fugu-Ultra73.7%SourceNot directly comparable
Terminal-Bench 2.0
Fugu Cyber—Sakana Fugu-Ultra82.1%SourceNot directly comparable
LiveCodeBench v6
Fugu Cyber—Sakana Fugu-Ultra93.2%SourceNot directly comparable
LiveCodeBench Pro
Fugu Cyber—Sakana Fugu-Ultra90.8%SourceNot directly comparable
SciCode
Fugu Cyber—Sakana Fugu-Ultra58.7%SourceNot directly comparable
Reasoning
MRCRv2
Fugu Cyber—Sakana Fugu-Ultra93.6%SourceNot directly comparable
Knowledge
Multimodal
CharXiv
Fugu Cyber—Sakana Fugu-Ultra86.6%SourceNot directly comparable
Frequently asked questions
Which is better, Fugu Cyber or Sakana Fugu-Ultra?
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Fugu Cyber or Sakana Fugu-Ultra?
Fugu Cyber and Sakana Fugu-Ultra are not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Fugu Cyber or Sakana Fugu-Ultra?
Fugu Cyber and Sakana Fugu-Ultra are not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Fugu Cyber or Sakana Fugu-Ultra?
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, Fugu Cyber or Sakana Fugu-Ultra?
Both models list the same context window, 1M.
Related comparisons
Last updated September 4, 2026
Watch Fugu Cyber vs Sakana Fugu-Ultra
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.