Agentic
Like-for-like- Sakana Fugu
- 80.2
- Sakana Fugu-Ultra
- 82.1
- Weighted basis
- 1 vs 1 rows
- Reading
- Sakana Fugu-Ultra leads
Sakana Fugu vs Sakana Fugu-Ultra
Updated August 13, 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
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
11 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.
Coding work
Code generation, repair, and software-engineering tasks
Sakana Fugu-Ultra
Sakana Fugu-Ultra leads on the same 2 weighted benchmark rows.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Sakana Fugu-Ultra
Sakana Fugu-Ultra leads on the same 1 weighted benchmark row.
Confidence: limited
Show secondary and unsupported calls
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.
11 Shared
- Shared results
- 11
- Sakana Fugu only
- 0
- Sakana Fugu-Ultra only
- 0
- Like-for-like categories
- 5 / 8
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
Like-for-like- Sakana Fugu
- 59.7
- Sakana Fugu-Ultra
- 64.5
- Weighted basis
- 2 vs 2 rows
- Reading
- Sakana Fugu-Ultra leads
Reasoning
Like-for-like- Sakana Fugu
- 86.6
- Sakana Fugu-Ultra
- 93.6
- Weighted basis
- 1 vs 1 rows
- Reading
- Sakana Fugu-Ultra leads
Knowledge
Like-for-like- Sakana Fugu
- 95.5
- Sakana Fugu-Ultra
- 95.5
- Weighted basis
- 1 vs 1 rows
- Reading
- Tie
Multimodal
Like-for-like- Sakana Fugu
- 85.1
- Sakana Fugu-Ultra
- 86.6
- Weighted basis
- 1 vs 1 rows
- Reading
- Sakana Fugu-Ultra leads
Math
Not comparable- Sakana Fugu
- Not measured
- Sakana Fugu-Ultra
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Sakana Fugu
- Not measured
- Sakana Fugu-Ultra
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Sakana Fugu
- Not measured
- Sakana Fugu-Ultra
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Sakana Fugu | Sakana Fugu-Ultra | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 80.2 | 82.1 | Like-for-like1 vs 1 rows | Sakana Fugu-Ultra leads |
| Coding | 59.7 | 64.5 | Like-for-like2 vs 2 rows | Sakana Fugu-Ultra leads |
| Reasoning | 86.6 | 93.6 | Like-for-like1 vs 1 rows | Sakana Fugu-Ultra leads |
| Knowledge | 95.5 | 95.5 | Like-for-like1 vs 1 rows | Tie |
| Multimodal | 85.1 | 86.6 | Like-for-like1 vs 1 rows | Sakana Fugu-Ultra leads |
| Math | Not measured | Not measured | Not comparable0 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.
SWE-bench Pro
Coding
MRCRv2
Reasoning
Terminal-Bench 2.0
Agentic
CharXiv
Multimodal
SciCode
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
- Sakana Fugu
- API rate not published
- Fits in one request
- Sakana Fugu-Ultra
- API rate not published
- Fits in one request
Sakana Fugu has no comparable published API token rate. Sakana Fugu-Ultra has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Sakana Fugu
- API rate not published
- Fits in one request
- Sakana Fugu-Ultra
- API rate not published
- Fits in one request
Sakana Fugu has no comparable published API token rate. Sakana Fugu-Ultra has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Sakana Fugu
- API rate not published
- Fits in one request
- Cached-input rate unavailable
- Sakana Fugu-Ultra
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Sakana Fugu has no comparable published API token rate. 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.
SpecificationSakana FuguSakana Fugu-Ultra
Context window
Maximum documented context; output-token limits may be lower.
Sakana Fugu
1M
Sakana Fugu-Ultra
1M
API model ID
Sakana Fugu
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.
Sakana Fugu
No comparable hosted API rate
Sakana Fugu-Ultra
No comparable hosted API rate
Documented inputs
Sakana Fugu
Not sourced
Sakana Fugu-Ultra
Not sourced
Documented outputs
Sakana Fugu
Not sourced
Sakana Fugu-Ultra
Not sourced
Provider availability
Sakana Fugu
Not sourced
Sakana Fugu-Ultra
Not sourced
Reasoning profile
Sakana Fugu
Reasoning
Sakana Fugu-Ultra
Reasoning
Weight access
Sakana Fugu
Proprietary
Sakana Fugu-Ultra
Proprietary
License
Sakana Fugu
Proprietary
Sakana Fugu-Ultra
Proprietary
Release date
Sakana Fugu
2026-06-22
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
- 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.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence11 rows
Agentic
Terminal-Bench 2.0
Shared sourceSakana Fugu80.2%Sakana Fugu-Ultra82.1%Sakana Fugu-Ultra leads this result
Coding
SWE-bench Pro
Shared sourceSakana Fugu59%Sakana Fugu-Ultra73.7%Sakana Fugu-Ultra leads this result
Terminal-Bench 2.0
Shared sourceSakana Fugu80.2%Sakana Fugu-Ultra82.1%Sakana Fugu-Ultra leads this result
LiveCodeBench v6
Shared sourceSakana Fugu92.9%Sakana Fugu-Ultra93.2%Sakana Fugu-Ultra leads this result
LiveCodeBench Pro
Shared sourceSakana Fugu87.8%Sakana Fugu-Ultra90.8%Sakana Fugu-Ultra leads this result
SciCode
Shared sourceSakana Fugu60.1%Sakana Fugu-Ultra58.7%Sakana Fugu leads this result
Reasoning
MRCRv2
Shared sourceSakana Fugu86.6%Sakana Fugu-Ultra93.6%Sakana Fugu-Ultra leads this result
Knowledge
GPQA
Shared sourceSakana Fugu95.5%Sakana Fugu-Ultra95.5%Tie
GPQA-D
Shared sourceSakana Fugu95.5%Sakana Fugu-Ultra95.5%Tie
HLE w/o tools
Shared sourceSakana Fugu47.2%Sakana Fugu-Ultra50%Sakana Fugu-Ultra leads this result
Multimodal
CharXiv
Shared sourceSakana Fugu85.1%Sakana Fugu-Ultra86.6%Sakana Fugu-Ultra leads this result
Frequently asked questions
Which is better, Sakana Fugu or Sakana Fugu-Ultra?
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, Sakana Fugu or Sakana Fugu-Ultra?
Sakana Fugu-Ultra leads the like-for-like coding comparison across 2 shared weighted benchmark rows.
Which is better for agentic tasks, Sakana Fugu or Sakana Fugu-Ultra?
Sakana Fugu-Ultra leads the like-for-like agentic tasks comparison across 1 shared weighted benchmark row.
Which costs less, Sakana Fugu 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, Sakana Fugu or Sakana Fugu-Ultra?
Both models list the same context window, 1M.
Related comparisons
Last updated August 13, 2026
Watch Sakana Fugu 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.