Agentic
Not comparable- Claude Opus 5
- 77.4
- Supported · #2/151
- Sakana Fugu-Ultra
- Not ranked
- Basis
- BenchAlign lane · 19 vs 1 public rows
- Reading
- Not comparable
Claude Opus 5 vs Sakana Fugu-Ultra
Updated September 4, 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.
2 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
Sakana Fugu-Ultra is 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
Sakana Fugu-Ultra is 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.
71 Claude Opus 5 only
2 Shared
9 Sakana Fugu-Ultra only
- Shared results
- 2
- Claude Opus 5 only
- 71
- Sakana Fugu-Ultra only
- 9
- 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- Claude Opus 5
- 75.6
- Supported · #3/183
- Sakana Fugu-Ultra
- Not ranked
- Basis
- BenchAlign lane · 16 vs 5 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Claude Opus 5
- 75.6
- #13/22
- Sakana Fugu-Ultra
- 77.9
- Unranked · 1 rankable row
- Basis
- Provisional lane · 2 vs 1 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude Opus 5
- 82.1
- Supported · #3/181
- Sakana Fugu-Ultra
- Not ranked
- Basis
- BenchAlign lane · 19 vs 3 public rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 5
- Not ranked
- Sakana Fugu-Ultra
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 5
- Not ranked
- Sakana Fugu-Ultra
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Opus 5
- 88.7
- #2/48
- Sakana Fugu-Ultra
- 72.8
- Unranked · 1 rankable row
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 5
- Not ranked
- Sakana Fugu-Ultra
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Opus 5 | Sakana Fugu-Ultra | Basis | Reading |
|---|---|---|---|---|
| Agentic | 77.4Supported · #2/151 | Not ranked | Not comparableBenchAlign lane · 19 vs 1 public rows | Not comparable |
| Coding | 75.6Supported · #3/183 | Not ranked | Not comparableBenchAlign lane · 16 vs 5 public rows | Not comparable |
| Reasoning | 75.6#13/22 | 77.9Unranked · 1 rankable row | Not comparableProvisional lane · 2 vs 1 weighted rows | Not comparable |
| Knowledge | 82.1Supported · #3/181 | Not ranked | Not comparableBenchAlign lane · 19 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 | 88.7#2/48 | 72.8Unranked · 1 rankable row | Not comparableProvisional lane · 1 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.
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.
HLE w/o tools
Knowledge
Claude Opus 5: 56.3%Sakana Fugu-Ultra: 50%Normalized gap 6.3Claude Opus 5 source Sakana Fugu-Ultra sourceSWE-bench Pro
Coding
Claude Opus 5: 79.2%Sakana Fugu-Ultra: 73.7%Normalized gap 5.5Claude Opus 5 source Sakana Fugu-Ultra source
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
- Claude Opus 5
- $0.0175
- 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
- Claude Opus 5
- $0.325
- 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
- Claude Opus 5
- $0.45
- 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.
SpecificationClaude Opus 5Sakana Fugu-Ultra
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 5
Sakana Fugu-Ultra
1M
API model ID
Claude Opus 5
claude-opus-5
Anthropic model overviewSakana 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.
Claude Opus 5
$0.5 per 1M cached input tokens
Claude API pricingSakana Fugu-Ultra
No comparable hosted API rate
Documented inputs
Claude Opus 5
text, image
Anthropic model overviewSakana Fugu-Ultra
Not sourced
Documented outputs
Claude Opus 5
Sakana Fugu-Ultra
Not sourced
Provider availability
Claude Opus 5
Generally Available · Claude API
Anthropic model overviewSakana Fugu-Ultra
Not sourced
Reasoning profile
Claude Opus 5
Reasoning
Sakana Fugu-Ultra
Reasoning
Weight access
Claude Opus 5
Proprietary
Sakana Fugu-Ultra
Proprietary
License
Claude Opus 5
Proprietary
Sakana Fugu-Ultra
Proprietary
Release date
Claude Opus 5
2026-07-24
Sakana Fugu-Ultra
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
- 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 evidence82 rows
Agentic
Terminal-Bench 3.0
Claude Opus 542.7%SourceSakana Fugu-Ultra—Not directly comparable
BrowseComp
Claude Opus 590.8%SourceSakana Fugu-Ultra—Not directly comparable
HLE w/ tools
Claude Opus 564.7%SourceSakana Fugu-Ultra—Not directly comparable
DeepSearchQA
Claude Opus 595.0%SourceSakana Fugu-Ultra—Not directly comparable
DRACO
Claude Opus 588.6%SourceSakana Fugu-Ultra—Not directly comparable
BrowseComp (10-agent, prerelease)
Claude Opus 593.6%SourceSakana Fugu-Ultra—Not directly comparable
OSWorld 2.0
Claude Opus 570.6%SourceSakana Fugu-Ultra—Not directly comparable
MCP Atlas
Claude Opus 585.8%SourceSakana Fugu-Ultra—Not directly comparable
MCP-Atlas claim coverage
Claude Opus 589.1%SourceSakana Fugu-Ultra—Not directly comparable
LAB all-pass (Anthropic harness)
Claude Opus 523.58%SourceSakana Fugu-Ultra—Not directly comparable
LAB criterion-pass (Anthropic harness)
Claude Opus 593.74%SourceSakana Fugu-Ultra—Not directly comparable
LAB all-pass (Harvey held-out)
Claude Opus 511.7%SourceSakana Fugu-Ultra—Not directly comparable
LAB criterion-pass (Harvey held-out)
Claude Opus 594.1%SourceSakana Fugu-Ultra—Not directly comparable
Toolathlon-Verified
Claude Opus 580.6%SourceSakana Fugu-Ultra—Not directly comparable
Toolathlon Verified Pass@3
Claude Opus 587.0%SourceSakana Fugu-Ultra—Not directly comparable
Toolathlon Verified Pass³
Claude Opus 573.1%SourceSakana Fugu-Ultra—Not directly comparable
Toolathlon Verified avg. turns
Claude Opus 523.5 turnsSourceSakana Fugu-Ultra—Not directly comparable
AutomationBench
Claude Opus 526.0%SourceSakana Fugu-Ultra—Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Opus 584.6%SourceSakana Fugu-Ultra—Not directly comparable
Terminal-Bench 2.0
Claude Opus 5—Sakana Fugu-Ultra82.1%SourceNot directly comparable
Coding
Bug Hunt Bench
Claude Opus 527 fixesSourceSakana Fugu-Ultra—Not directly comparable
SWE-bench Verified
Claude Opus 596%SourceSakana Fugu-Ultra—Not directly comparable
SWE-bench Pro
Claude Opus 579.2%SourceSakana Fugu-Ultra73.7%SourceClaude Opus 5 leads this result
SWE Multilingual
Claude Opus 589.5%SourceSakana Fugu-Ultra—Not directly comparable
SWE Multimodal
Claude Opus 559.4%SourceSakana Fugu-Ultra—Not directly comparable
deepSwe
Claude Opus 568.8%SourceSakana Fugu-Ultra—Not directly comparable
FrontierCode 1.1 Main
Claude Opus 553.4%SourceSakana Fugu-Ultra—Not directly comparable
FrontierCode 1.1 Extended
Claude Opus 563.6%SourceSakana Fugu-Ultra—Not directly comparable
FrontierSWE v2
Claude Opus 552.0%SourceSakana Fugu-Ultra—Not directly comparable
ProgramBench (episode 1)
Claude Opus 583.0%SourceSakana Fugu-Ultra—Not directly comparable
ProgramBench
Claude Opus 593.0%SourceSakana Fugu-Ultra—Not directly comparable
cursorBench32
Claude Opus 570.0%SourceSakana Fugu-Ultra—Not directly comparable
VulcanBench v3
Claude Opus 587.0%SourceSakana Fugu-Ultra—Not directly comparable
VulcanBench CII v1
Claude Opus 596.4%SourceSakana Fugu-Ultra—Not directly comparable
LiveCodeBench (Vals)
Claude Opus 589.0%SourceSakana Fugu-Ultra—Not directly comparable
SWE-bench (Vals)
Claude Opus 597.0%SourceSakana Fugu-Ultra—Not directly comparable
Terminal-Bench 2.0
Claude Opus 5—Sakana Fugu-Ultra82.1%SourceNot directly comparable
LiveCodeBench v6
Claude Opus 5—Sakana Fugu-Ultra93.2%SourceNot directly comparable
LiveCodeBench Pro
Claude Opus 5—Sakana Fugu-Ultra90.8%SourceNot directly comparable
SciCode
Claude Opus 5—Sakana Fugu-Ultra58.7%SourceNot directly comparable
Reasoning
Knowledge
HLE
Claude Opus 564.7%SourceSakana Fugu-Ultra—Not directly comparable
HLE w/o tools
Claude Opus 556.3%SourceSakana Fugu-Ultra50%SourceClaude Opus 5 leads this result
HLE-Verified
Claude Opus 554.4%SourceSakana Fugu-Ultra—Not directly comparable
LABBench2
Claude Opus 584.2%SourceSakana Fugu-Ultra—Not directly comparable
HealthBench (raw)
Claude Opus 567.1%SourceSakana Fugu-Ultra—Not directly comparable
HealthBench (length-adjusted)
Claude Opus 557.8%SourceSakana Fugu-Ultra—Not directly comparable
HealthBench Professional
Claude Opus 559.8%SourceSakana Fugu-Ultra—Not directly comparable
HealthBench Professional (raw)
Claude Opus 573.4%SourceSakana Fugu-Ultra—Not directly comparable
BioMysteryBench (human-solvable)
Claude Opus 590.1%SourceSakana Fugu-Ultra—Not directly comparable
BioMysteryBench (human-difficult)
Claude Opus 549.4%SourceSakana Fugu-Ultra—Not directly comparable
SpatialBench Verified
Claude Opus 572.5%SourceSakana Fugu-Ultra—Not directly comparable
SingleCellBench
Claude Opus 560.6%SourceSakana Fugu-Ultra—Not directly comparable
ProteinGym Hard
Claude Opus 547.7%SourceSakana Fugu-Ultra—Not directly comparable
Protein Design
Claude Opus 542.5%SourceSakana Fugu-Ultra—Not directly comparable
Organic chemistry V2
Claude Opus 561.6%SourceSakana Fugu-Ultra—Not directly comparable
Protocols (troubleshooting)
Claude Opus 561.1%SourceSakana Fugu-Ultra—Not directly comparable
Protocols (understanding)
Claude Opus 578.4%SourceSakana Fugu-Ultra—Not directly comparable
GPQA Diamond (Vals)
Claude Opus 593.4%SourceSakana Fugu-Ultra—Not directly comparable
MMLU-Pro (Vals)
Claude Opus 591.6%SourceSakana Fugu-Ultra—Not directly comparable
GPQA
Claude Opus 5—Sakana Fugu-Ultra95.5%SourceNot directly comparable
GPQA-D
Claude Opus 5—Sakana Fugu-Ultra95.5%SourceNot directly comparable
Math
IMO 2026
Claude Opus 542/42SourceSakana Fugu-Ultra—Not directly comparable
RiemannBench (no tools)
Claude Opus 560.0%SourceSakana Fugu-Ultra—Not directly comparable
RiemannBench (tools)
Claude Opus 579.0%SourceSakana Fugu-Ultra—Not directly comparable
ArXivMath Jun. 2026 (no tools)
Claude Opus 590.8%SourceSakana Fugu-Ultra—Not directly comparable
ArXivMath Jun. 2026 (tools)
Claude Opus 591.3%SourceSakana Fugu-Ultra—Not directly comparable
Multilingual
Multimodal
Chartography (no tools)
Claude Opus 529.6%SourceSakana Fugu-Ultra—Not directly comparable
Chartography (tools)
Claude Opus 583.0%SourceSakana Fugu-Ultra—Not directly comparable
BenchCAD Vision2Code (no tools)
Claude Opus 50.366SourceSakana Fugu-Ultra—Not directly comparable
BenchCAD Vision2Code (tools)
Claude Opus 50.821SourceSakana Fugu-Ultra—Not directly comparable
GDP.pdf (no tools)
Claude Opus 583.4%SourceSakana Fugu-Ultra—Not directly comparable
GDP.pdf (tools)
Claude Opus 585.5%SourceSakana Fugu-Ultra—Not directly comparable
OfficeQA
Claude Opus 578.1%SourceSakana Fugu-Ultra—Not directly comparable
OfficeQA Pro
Claude Opus 566.9%SourceSakana Fugu-Ultra—Not directly comparable
CharXiv
Claude Opus 5—Sakana Fugu-Ultra86.6%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Opus 5 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, Claude Opus 5 or Sakana Fugu-Ultra?
Sakana Fugu-Ultra is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Claude Opus 5 or Sakana Fugu-Ultra?
Sakana Fugu-Ultra is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Claude Opus 5 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, Claude Opus 5 or Sakana Fugu-Ultra?
Both models list the same context window, 1M.
Related comparisons
Last updated September 4, 2026
Watch Claude Opus 5 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.