Reasoning
Like-for-like- Pokee-Isaac 28B
- 60.7
- Sakana Fugu
- 86.6
- Weighted basis
- 1 vs 1 rows
- Reading
- Sakana Fugu leads
Model comparison
Pokee-Isaac 28B vs Sakana Fugu
Updated August 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
1 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.
Long documents
Prompts that approach the documented context limit
Pokee-Isaac 28B
Pokee-Isaac 28B has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
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: rate-fallback
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.
6 Pokee-Isaac 28B only
1 Shared
10 Sakana Fugu only
- Shared results
- 1
- Pokee-Isaac 28B only
- 6
- Sakana Fugu only
- 10
- Like-for-like categories
- 1 / 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.
Agentic
Not comparable- Pokee-Isaac 28B
- Not measured
- Sakana Fugu
- 80.2
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Coding
Not comparable- Pokee-Isaac 28B
- Not measured
- Sakana Fugu
- 59.7
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Knowledge
Not comparable- Pokee-Isaac 28B
- Not measured
- Sakana Fugu
- 95.5
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Math
Not comparable- Pokee-Isaac 28B
- Not measured
- Sakana Fugu
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Pokee-Isaac 28B
- Not measured
- Sakana Fugu
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Pokee-Isaac 28B
- Not measured
- Sakana Fugu
- 85.1
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Instruction following
Not comparable- Pokee-Isaac 28B
- Not measured
- Sakana Fugu
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Pokee-Isaac 28B | Sakana Fugu | Weighted basis | Reading |
|---|---|---|---|---|
| Reasoning | 60.7 | 86.6 | Like-for-like1 vs 1 rows | Sakana Fugu leads |
| Agentic | Not measured | 80.2 | Not comparable0 vs 1 rows | Not comparable |
| Coding | Not measured | 59.7 | Not comparable0 vs 2 rows | Not comparable |
| Knowledge | Not measured | 95.5 | Not comparable0 vs 1 rows | Not comparable |
| Math | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | 85.1 | Not comparable0 vs 1 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.
MRCRv2
Reasoning
Pokee-Isaac 28B: 60.7%Sakana Fugu: 86.6%Normalized gap 25.9Pokee-Isaac 28B source Sakana Fugu 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
- Pokee-Isaac 28B
- $0.00065
- Fits in one request
- Sakana Fugu
- API rate not published
- Fits in one request
Sakana Fugu has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Pokee-Isaac 28B
- $0.0105
- Fits in one request
- Sakana Fugu
- API rate not published
- Fits in one request
Sakana Fugu has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Pokee-Isaac 28B
- $0.043
- Fits in one request
- Cached input priced at the published list-input rate
- Sakana Fugu
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Pokee-Isaac 28B has no published cached-input rate, so cached tokens use its listed input rate. Sakana Fugu 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.
SpecificationPokee-Isaac 28BSakana Fugu
Context window
Maximum documented context; output-token limits may be lower.
Pokee-Isaac 28B
Sakana Fugu
1M
API model ID
Pokee-Isaac 28B
pokee-isaac
Pokee-Isaac 28B model pageSakana Fugu
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Pokee-Isaac 28B
Not published
Pokee-Isaac 28B model pageSakana Fugu
No comparable hosted API rate
Documented inputs
Pokee-Isaac 28B
Not sourced
Sakana Fugu
Not sourced
Documented outputs
Pokee-Isaac 28B
Not sourced
Sakana Fugu
Not sourced
Provider availability
Pokee-Isaac 28B
Not sourced
Sakana Fugu
Not sourced
Reasoning profile
Pokee-Isaac 28B
Reasoning
Sakana Fugu
Reasoning
Weight access
Pokee-Isaac 28B
Proprietary
Sakana Fugu
Proprietary
License
Pokee-Isaac 28B
Proprietary
Sakana Fugu
Proprietary
Release date
Pokee-Isaac 28B
2026-08-03
Sakana Fugu
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
- Pokee-Isaac 28B has the larger documented window (10M).
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 evidence17 rows
Agentic
Terminal-Bench 2.1
Pokee-Isaac 28B65.1%SourceSakana Fugu—Not directly comparable
BFCL v4
Pokee-Isaac 28B70.9%SourceSakana Fugu—Not directly comparable
τ³-bench results
Pokee-Isaac 28B66.2%SourceSakana Fugu—Not directly comparable
MCP-Atlas claim coverage
Pokee-Isaac 28B74.6%SourceSakana Fugu—Not directly comparable
PinchBench
Pokee-Isaac 28B95.7%SourceSakana Fugu—Not directly comparable
Terminal-Bench 2.0
Pokee-Isaac 28B—Sakana Fugu80.2%SourceNot directly comparable
Coding
Terminal-Bench 2.1
Pokee-Isaac 28B65.1%SourceSakana Fugu—Not directly comparable
SWE-bench Pro
Pokee-Isaac 28B—Sakana Fugu59%SourceNot directly comparable
Terminal-Bench 2.0
Pokee-Isaac 28B—Sakana Fugu80.2%SourceNot directly comparable
LiveCodeBench v6
Pokee-Isaac 28B—Sakana Fugu92.9%SourceNot directly comparable
LiveCodeBench Pro
Pokee-Isaac 28B—Sakana Fugu87.8%SourceNot directly comparable
SciCode
Pokee-Isaac 28B—Sakana Fugu60.1%SourceNot directly comparable
Reasoning
Knowledge
Multimodal
CharXiv
Pokee-Isaac 28B—Sakana Fugu85.1%SourceNot directly comparable
Frequently asked questions
Which is better, Pokee-Isaac 28B or Sakana Fugu?
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, Pokee-Isaac 28B or Sakana Fugu?
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
Which is better for agentic tasks, Pokee-Isaac 28B or Sakana Fugu?
The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.
Which costs less, Pokee-Isaac 28B or Sakana Fugu?
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, Pokee-Isaac 28B or Sakana Fugu?
Pokee-Isaac 28B has the larger documented context window: 10M, compared with 1M.
Related comparisons
Last updated August 4, 2026
Watch Pokee-Isaac 28B vs Sakana Fugu
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.