Skip to main content

Model profile

Fugu Cyber

Sakana AICurrentReleased Jul 21, 2026
Data verified
Overall Score
Unranked
Arena Elo
Not listed
Eligible category ranks
0of 8
Price (1M tokens)
$6 in / $36 out
API pricing
Speed
Not listed
Context
1M

Evidence coverage

2 of 323 tracked benchmarks are published. 2 are verified and 0 provisional. 1 of 8 categories are measured.

Updated July 21, 2026Methodology
Published / tracked
2 / 323
Verified
2
Provisional
0
Categories with evidence
1 / 8

Evidence by category

  • Agentic2 benchmarks
    Verified
  • Coding0 benchmarks
    Not measured
  • Reasoning0 benchmarks
    Not measured
  • Knowledge0 benchmarks
    Not measured
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal0 benchmarks
    Not measured
  • Inst. Following0 benchmarks
    Not measured
ProprietaryReasoning
Confidence:
Low
cyber

BenchLM is tracking Fugu Cyber, but this profile is currently excluded from the public leaderboard because it still lacks enough non-generated benchmark coverage to rank safely. Only non-generated public benchmark rows appear below.

Fugu Cyber is a proprietary model with a 1M token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

Available through Sakana AI's OpenAI-compatible API as fugu-cyber-v1.0. Access is limited to the Token Plan and requires an approved use-case application.

Fugu Cyber sits inside the Sakana Fugu family alongside Sakana Fugu, Sakana Fugu-Ultra. This profile currently has 2 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 77.4483.93

  1. Claude Mythos 5
    Anthropic
    #183.93
    Claude Mythos 5 is #1 with a score of 83.93.
    Compare
  2. Claude Fable 5
    Anthropic
    #283.68
    Claude Fable 5 is #2 with a score of 83.68.
    Compare
  3. GPT-5.6 Sol
    OpenAI
    #381.96
    GPT-5.6 Sol is #3 with a score of 81.96.
    Compare
  4. Kimi K3
    Moonshot AI
    #480.96
    Kimi K3 is #4 with a score of 80.96.
    Compare
  5. Claude Opus 4.8
    Anthropic
    #578.34
    Claude Opus 4.8 is #5 with a score of 78.34.
    Compare
  6. Muse Spark 1.1
    Meta
    #677.44
    Muse Spark 1.1 is #6 with a score of 77.44.
    Compare
  7. Fugu CyberCurrent model
    Sakana AI
    UnrankedNot measured
    Fugu Cyber is Unranked with a score of Not measured.

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

No eligible category percentile is available from the published evidence yet.

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticWeight 22%2 benchmarksVerifiedScore pending
CodingWeight 20%0 benchmarksNot measuredNot measured
ReasoningWeight 17%0 benchmarksNot measuredNot measured
KnowledgeWeight 12%0 benchmarksNot measuredNot measured
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalWeight 12%0 benchmarksNot measuredNot measured
Inst. FollowingWeight 5%0 benchmarksNot measuredNot measured

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic2 benchmarks
CyberGymProvider exact
86.9%Display only
Source: Sakana AI: Introducing Fugu-CyberProvenance: Sakana AI reports Fugu Cyber at 86.9% success rate on CyberGym.
CTI-REALMProvider exact
72.1%Display only
Source: Sakana AI: Introducing Fugu-CyberProvenance: Sakana AI reports Fugu Cyber at 72.1% success rate on CTI-REALM.

Sakana Fugu Family

cyber · Cyber

Canonical Entry

Sakana Fugu-Ultra

Frequently Asked Questions

How does Fugu Cyber perform overall in AI benchmarks?

Fugu Cyber has 2 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is Fugu Cyber good for agentic tool use and computer tasks?

Fugu Cyber has visible benchmark coverage in agentic tool use and computer tasks, but BenchLM does not currently assign it a global category rank there.

Which sibling models are related to Fugu Cyber?

Fugu Cyber belongs to the Sakana Fugu family. Related variants on BenchLM include Sakana Fugu, Sakana Fugu-Ultra.

Does Fugu Cyber have full benchmark coverage on BenchLM?

Not yet. Fugu Cyber currently has 2 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Fugu Cyber?

Fugu Cyber has a published context window of 1M, which determines how much text it can process in a single interaction.

Last updated: July 21, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.