Capability
Unranked
field median 57.7
Not eligible for a public rank
Superseded.Sakana AI has newer models in this line:Sakana Fugu-Ultra v1.1
Sakana Fugu-Ultra
Released Jun 22, 2026 — see all recent releases
Decision reading
Sakana Fugu-Ultra is tracked, but not publicly ranked yet. The profile exposes 11 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Data as of August 13, 2026 · How the score is built
Strongest published evidence
Published rows are visible, but no category has enough eligible evidence for a comparative rank.
Validate before choosing
11 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Price
API rate not published
input median $1
No comparable first-party hosted token rate
Speed
Not measured
field median 93 tok/s
Time to first token not measured
Context
1Mtokens
field median 200,000
Reported for this model; direct source link not stored
How much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic1/1 verified
- Coding5/5 verified
- Reasoning1/1 verified
- Knowledge3/3 verified
- MathNot measured
- MultilingualNot measured
- Multimodal1/1 verified
- Inst. FollowingNot measured
Verified sourceProvisionalNot measured
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 1M
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Superseded
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank Not rankedWeight 22%1 benchmarkVerified | 83.0 | Not ranked | Not available | 22% | 1 benchmark | Verified |
| CodingRank Not rankedWeight 20%5 benchmarksVerified | 76.4 | Not ranked | Not available | 20% | 5 benchmarks | Verified |
| ReasoningRank Not rankedWeight 17%1 benchmarkVerified | 91.2 | Not ranked | Not available | 17% | 1 benchmark | Verified |
| KnowledgeRank Not rankedWeight 12%3 benchmarksVerified | 83.6 | Not ranked | Not available | 12% | 3 benchmarks | Verified |
| MathWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | Not ranked | Not available | 7% | 0 benchmarks | Not measured |
| MultimodalRank Not rankedWeight 12%1 benchmarkVerified | 72.8 | Not ranked | Not available | 12% | 1 benchmark | Verified |
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SciCodeScientific Code Benchmark | Score58.7% | Versus best verified row Best verified: Sakana Fugu · 60.1% | Gap1.4 behind | WeightWeighted 16% | Provider exact |
| SWE-bench Pro | Score73.7% | Versus best verified row Best verified: Claude Mythos 5 · 80.3% | Gap6.6 behind | WeightWeighted 10% | Provider exact |
| Terminal-Bench 2.0 | Score82.1% | Versus best verified row Best verified: GPT-5.6 Sol · 91.9% | Gap9.8 behind | WeightDisplay only | Provider exact |
| LiveCodeBench v6 | Score93.2% | Versus best verified row Best verified: Sakana Fugu-Ultra · 93.2% | GapBest verified | WeightDisplay only | Provider exact |
| LiveCodeBench Pro | Score90.8% | Versus best verified row Best verified: Sakana Fugu-Ultra · 90.8% | GapBest verified | WeightDisplay only | Provider exact |
Agentic1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Score82.1% | Versus best verified row Best verified: GPT-5.6 Sol · 91.9% | Gap9.8 behind | WeightWeighted 38% | Provider exact |
Reasoning1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MRCRv2 | Score93.6% | Versus best verified row Best verified: Sakana Fugu-Ultra · 93.6% | GapBest verified | WeightWeighted 31% | Provider exact |
Knowledge3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| GPQAGraduate-Level Google-Proof Q&A | Score95.5% | Versus best verified row Best verified: Sakana Fugu-Ultra · 95.5% | GapBest verified | WeightWeighted 7% | Provider exact |
| GPQA-DGPQA Diamond | Score95.5% | Versus best verified row Best verified: Sakana Fugu-Ultra · 95.5% | GapBest verified | WeightDisplay only | Provider exact |
| HLE w/o toolsHumanity's Last Exam without tools | Score50% | Versus best verified row Best verified: Claude Mythos 5 · 59% | Gap9 behind | WeightDisplay only | Provider exact |
Multimodal1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| CharXivCharXiv Reasoning | Score86.6% | Versus best verified row Best verified: Claude Mythos 5 · 93.5% | Gap6.9 behind | WeightWeighted 25% | Provider exact |
Lineage
The sequence follows explicit supersedes links. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Jun 22, 2026 · you are here
Sakana Fugu-UltraNot publicly ranked · Price not listed
Jul 24, 2026
Sakana Fugu-Ultra v1.1Not publicly ranked · $5 / $30
ultra · Ultra
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Sakana Fugu-Ultra, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Sakana Fugu-Ultra is a proprietary model with a 1M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Official exact-value snapshot from Sakana AI's Fugu technical report. BenchLM maps only table rows with existing keys: SWE-Bench Pro, Terminal-Bench 2.1, LiveCodeBench v6, LiveCodeBench Pro, HLE no-tools, GPQA Diamond, SciCode, LCR, MRCRv2, and CharXiv Reasoning. Banking, AutoResearch, CAD, and bespoke qualitative tasks remain out of schema.
Sakana Fugu-Ultra sits in the Sakana Fugu family with Sakana Fugu, Fugu Cyber, Sakana Fugu-Ultra v1.1. 11 of 431 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Radar
Full release historySakana Fugu-Ultra release history
Sakana Fugu released
Sakana AI · Model release
Source confirmed
Frequently asked questions
How does Sakana Fugu-Ultra perform overall in AI benchmarks?
Sakana Fugu-Ultra has 11 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.
Is Sakana Fugu-Ultra good for knowledge and understanding?
Sakana Fugu-Ultra has source-displayable benchmark coverage for knowledge and understanding, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Sakana Fugu-Ultra good for coding and programming?
Sakana Fugu-Ultra has source-displayable benchmark coverage for coding and programming, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Sakana Fugu-Ultra good for reasoning and logic?
Sakana Fugu-Ultra has source-displayable benchmark coverage for reasoning and logic, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Sakana Fugu-Ultra good for agentic tool use and computer tasks?
Sakana Fugu-Ultra has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Sakana Fugu-Ultra good for multimodal and grounded tasks?
Sakana Fugu-Ultra has source-displayable benchmark coverage for multimodal and grounded tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Which sibling models are related to Sakana Fugu-Ultra?
Sakana Fugu-Ultra belongs to the Sakana Fugu family. Related tracked variants include Sakana Fugu, Fugu Cyber, Sakana Fugu-Ultra v1.1. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Sakana Fugu-Ultra have full benchmark coverage on BenchLM?
No. Sakana Fugu-Ultra currently has 11 source-displayable rows across 431 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Sakana Fugu-Ultra?
Sakana Fugu-Ultra has a reported context window of 1M in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.
Last updated August 13, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch Sakana Fugu-Ultra in the weekly brief
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.