Agentic
Directional only- Claude Opus 4.5
- 43.2
- Estimated · #102/154
- Pokee-Isaac 28B
- 49.6
- Estimated · #62/154
- Basis
- BenchAlign lane · 15 vs 5 public rows
- Reading
- Directional only
Claude Opus 4.5 vs Pokee-Isaac 28B
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.
1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Updated September 18, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
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.
Long documents
Prompts that approach the documented context limit
Pokee-Isaac 28B
Pokee-Isaac 28B has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Pokee-Isaac 28B
Pokee-Isaac 28B has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Pokee-Isaac 28B
Pokee-Isaac 28B has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Pokee-Isaac 28B 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
Claude Opus 4.5 and Pokee-Isaac 28B are scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Claude Opus 4.5 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate. Pokee-Isaac 28B has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Which one for a specific job
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
56.7Claude Opus 4.5—Pokee-Isaac 28B
Not comparable · BenchAlign
The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
44 Claude Opus 4.5 only
1 Shared
6 Pokee-Isaac 28B only
- Shared results
- 1
- Claude Opus 4.5 only
- 44
- Pokee-Isaac 28B only
- 6
- Like-for-like categories
- 0 / 8
1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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 4.5
- 56.7
- Estimated · #36/154
- Pokee-Isaac 28B
- Not ranked
- Basis
- BenchAlign lane · 5 vs 1 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Claude Opus 4.5
- 72.1
- Unranked · 4 rankable rows
- Pokee-Isaac 28B
- 38.6
- Unranked · 1 rankable row
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude Opus 4.5
- 54.0
- Estimated · #60/184
- Pokee-Isaac 28B
- Not ranked
- Basis
- BenchAlign lane · 6 vs 0 public rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 4.5
- 57.9
- #6/7
- Pokee-Isaac 28B
- Not ranked
- Basis
- Provisional lane · 4 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 4.5
- 82.9
- #2/12
- Pokee-Isaac 28B
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Opus 4.5
- 23.5
- #46/48
- Pokee-Isaac 28B
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 4.5
- 30.6
- #114/124
- Pokee-Isaac 28B
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Opus 4.5 | Pokee-Isaac 28B | Basis | Reading |
|---|---|---|---|---|
| Agentic | 43.2Estimated · #102/154 | 49.6Estimated · #62/154 | Directional onlyBenchAlign lane · 15 vs 5 public rows | Directional only |
| Coding | 56.7Estimated · #36/154 | Not ranked | Not comparableBenchAlign lane · 5 vs 1 public rows | Not comparable |
| Reasoning | 72.1Unranked · 4 rankable rows | 38.6Unranked · 1 rankable row | Not comparableProvisional lane · 1 vs 1 weighted rows | Not comparable |
| Knowledge | 54.0Estimated · #60/184 | Not ranked | Not comparableBenchAlign lane · 6 vs 0 public rows | Not comparable |
| Math | 57.9#6/7 | Not ranked | Not comparableProvisional lane · 4 vs 0 weighted rows | Not comparable |
| Multilingual | 82.9#2/12 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multimodal | 23.5#46/48 | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Instruction following | 30.6#114/124 | Not ranked | Not comparableProvisional lane · 1 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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
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 4.5
- $0.0175
- Fits in one request
- Pokee-Isaac 28B
- $0.00065
- Fits in one request
Pokee-Isaac 28B has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 4.5
- $0.325
- Fits in one request
- Pokee-Isaac 28B
- $0.0105
- Fits in one request
Pokee-Isaac 28B has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Opus 4.5
- $1.35
- Does not fit in one request
- Cached input priced at the published list-input rate
- Pokee-Isaac 28B
- $0.043
- Fits in one request
- Cached input priced at the published list-input rate
Claude Opus 4.5 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate. Pokee-Isaac 28B has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Opus 4.5Pokee-Isaac 28B
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 4.5
200K
Pokee-Isaac 28B
API model ID
Claude Opus 4.5
Not sourced
Pokee-Isaac 28B
pokee-isaac
Pokee-Isaac 28B model pageCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 4.5
Not published
Pokee-Isaac 28B
Not published
Pokee-Isaac 28B model pageDocumented inputs
Claude Opus 4.5
Not sourced
Pokee-Isaac 28B
Not sourced
Documented outputs
Claude Opus 4.5
Not sourced
Pokee-Isaac 28B
Not sourced
Provider availability
Claude Opus 4.5
Not sourced
Pokee-Isaac 28B
Not sourced
Reasoning profile
Claude Opus 4.5
Non-Reasoning
Pokee-Isaac 28B
Reasoning
Weight access
Claude Opus 4.5
Proprietary
Pokee-Isaac 28B
Proprietary
License
Claude Opus 4.5
Proprietary
Pokee-Isaac 28B
Proprietary
Release date
Claude Opus 4.5
2025-11-01
Pokee-Isaac 28B
2026-08-03
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
- Repository review: $0.325 vs $0.0105. Cache-heavy agent loop: $1.35 vs $0.043.
- 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 evidence51 rows
Agentic
Terminal-Bench 2.0
Claude Opus 4.559.3%SourcePokee-Isaac 28B—Not directly comparable
OSWorld-Verified
Claude Opus 4.566.3%SourcePokee-Isaac 28B—Not directly comparable
OSWorld
Claude Opus 4.566.3%SourcePokee-Isaac 28B—Not directly comparable
Claw-Eval
Claude Opus 4.559.6%SourcePokee-Isaac 28B—Not directly comparable
QwenClawBench
Claude Opus 4.552.3%SourcePokee-Isaac 28B—Not directly comparable
τ³-bench results
Claude Opus 4.570.2%SourcePokee-Isaac 28B66.2%SourceClaude Opus 4.5 leads this result
VITA-Bench
Claude Opus 4.523.3%SourcePokee-Isaac 28B—Not directly comparable
DeepPlanning
Claude Opus 4.526.4%SourcePokee-Isaac 28B—Not directly comparable
Toolathlon
Claude Opus 4.543.5%SourcePokee-Isaac 28B—Not directly comparable
MCP Atlas
Claude Opus 4.542.3%SourcePokee-Isaac 28B—Not directly comparable
MCP-Tasks
Claude Opus 4.571.8%SourcePokee-Isaac 28B—Not directly comparable
WideResearch
Claude Opus 4.576.4%SourcePokee-Isaac 28B—Not directly comparable
CyberGym
Claude Opus 4.550.6%SourcePokee-Isaac 28B—Not directly comparable
Gert Labs
Claude Opus 4.564.23%SourcePokee-Isaac 28B—Not directly comparable
JobBench
Claude Opus 4.532.3%SourcePokee-Isaac 28B—Not directly comparable
Terminal-Bench 2.1
Claude Opus 4.5—Pokee-Isaac 28B65.1%SourceNot directly comparable
BFCL v4
Claude Opus 4.5—Pokee-Isaac 28B70.9%SourceNot directly comparable
MCP-Atlas claim coverage
Claude Opus 4.5—Pokee-Isaac 28B74.6%SourceNot directly comparable
PinchBench
Claude Opus 4.5—Pokee-Isaac 28B95.7%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Opus 4.580.9%SourcePokee-Isaac 28B—Not directly comparable
LiveCodeBench v6
Claude Opus 4.584.8%SourcePokee-Isaac 28B—Not directly comparable
SWE-bench Pro
Claude Opus 4.557.1%SourcePokee-Isaac 28B—Not directly comparable
SWE Multilingual
Claude Opus 4.577.5%SourcePokee-Isaac 28B—Not directly comparable
NL2Repo
Claude Opus 4.543.2%SourcePokee-Isaac 28B—Not directly comparable
Terminal-Bench 2.1
Claude Opus 4.5—Pokee-Isaac 28B65.1%SourceNot directly comparable
Reasoning
Knowledge
GPQA
Claude Opus 4.587%SourcePokee-Isaac 28B—Not directly comparable
SuperGPQA
Claude Opus 4.570.6%SourcePokee-Isaac 28B—Not directly comparable
MMLU-Pro
Claude Opus 4.589.5%SourcePokee-Isaac 28B—Not directly comparable
MMLU-Redux
Claude Opus 4.596.6%SourcePokee-Isaac 28B—Not directly comparable
C-Eval
Claude Opus 4.592.2%SourcePokee-Isaac 28B—Not directly comparable
HLE
Claude Opus 4.530.8%SourcePokee-Isaac 28B—Not directly comparable
Math
AIME26
Claude Opus 4.595.1%SourcePokee-Isaac 28B—Not directly comparable
HMMT Feb 2025
Claude Opus 4.592.9%SourcePokee-Isaac 28B—Not directly comparable
HMMT Nov 2025
Claude Opus 4.593.3%SourcePokee-Isaac 28B—Not directly comparable
HMMT Feb 2026
Claude Opus 4.585.3%SourcePokee-Isaac 28B—Not directly comparable
MMAnswerBench
Claude Opus 4.584.0%SourcePokee-Isaac 28B—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Claude Opus 4.520.690%SourcePokee-Isaac 28B—Not directly comparable
FrontierMath v2 (Tier 4)
Claude Opus 4.54.167%SourcePokee-Isaac 28B—Not directly comparable
Multilingual
Multimodal
MMMU-Pro
Claude Opus 4.570.6%SourcePokee-Isaac 28B—Not directly comparable
MathVision
Claude Opus 4.574.3%SourcePokee-Isaac 28B—Not directly comparable
CharXiv
Claude Opus 4.568.5%SourcePokee-Isaac 28B—Not directly comparable
VideoMMMU
Claude Opus 4.584.4%SourcePokee-Isaac 28B—Not directly comparable
ScreenSpot Pro
Claude Opus 4.545.7%SourcePokee-Isaac 28B—Not directly comparable
V*
Claude Opus 4.567.0%SourcePokee-Isaac 28B—Not directly comparable
Instruction following
Questions
Which is better, Claude Opus 4.5 or Pokee-Isaac 28B?
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 4.5 or Pokee-Isaac 28B?
Pokee-Isaac 28B is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Claude Opus 4.5 or Pokee-Isaac 28B?
Pokee-Isaac 28B scores higher for agentic tasks on the public lane, 49.6 to 43.2. Claude Opus 4.5 and Pokee-Isaac 28B are scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Claude Opus 4.5 or Pokee-Isaac 28B?
For the stated presets, chat costs $0.0175 on Claude Opus 4.5 and $0.00065 on Pokee-Isaac 28B; repository review costs $0.325 and $0.0105; the cache-heavy agent loop costs $1.35 and $0.043. Claude Opus 4.5 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate. Pokee-Isaac 28B has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Opus 4.5 or Pokee-Isaac 28B?
Pokee-Isaac 28B has the larger documented context window: 10M, compared with 200K.
Related comparisons
Last updated September 18, 2026
Watch Claude Opus 4.5 vs Pokee-Isaac 28B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.