Agentic
Not comparable- Step 5 Preview
- Not ranked
- Ternary Bonsai 2 27B
- 50.1
- Estimated · #59/154
- Basis
- BenchAlign lane · 11 vs 3 public rows
- Reading
- Not comparable
Step 5 Preview vs Ternary Bonsai 2 27B
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.
3 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Updated September 21, 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
Step 5 Preview
Step 5 Preview 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
Step 5 Preview 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
Step 5 Preview is not ranked on the public lane for agentic, so no winner is named for agentic.
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: 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
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.
—Step 5 Preview50.1Ternary Bonsai 2 27B
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.
19 Step 5 Preview only
3 Shared
18 Ternary Bonsai 2 27B only
- Shared results
- 3
- Step 5 Preview only
- 19
- Ternary Bonsai 2 27B only
- 18
- 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- Step 5 Preview
- Not ranked
- Ternary Bonsai 2 27B
- 50.1
- Estimated · #66/156
- Basis
- BenchAlign lane · 6 vs 4 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Step 5 Preview
- 78.5
- Unranked · 2 rankable rows
- Ternary Bonsai 2 27B
- 73.9
- Unranked · 1 rankable row
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Step 5 Preview
- 61.2
- #28/49
- Ternary Bonsai 2 27B
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- Step 5 Preview
- Not ranked
- Ternary Bonsai 2 27B
- 50.7
- Estimated · #82/186
- Basis
- BenchAlign lane · 2 vs 3 public rows
- Reading
- Not comparable
Multilingual
Not comparable- Step 5 Preview
- Not ranked
- Ternary Bonsai 2 27B
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Step 5 Preview
- Not ranked
- Ternary Bonsai 2 27B
- 71.0
- #64/124
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Math
Not comparable- Step 5 Preview
- Not ranked
- Ternary Bonsai 2 27B
- 76.8
- Unranked · 4 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
| Category | Step 5 Preview | Ternary Bonsai 2 27B | Basis | Reading |
|---|---|---|---|---|
| Agentic | Not ranked | 50.1Estimated · #59/154 | Not comparableBenchAlign lane · 11 vs 3 public rows | Not comparable |
| Coding | Not ranked | 50.1Estimated · #66/156 | Not comparableBenchAlign lane · 6 vs 4 public rows | Not comparable |
| Reasoning | 78.5Unranked · 2 rankable rows | 73.9Unranked · 1 rankable row | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 61.2#28/49 | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Knowledge | Not ranked | 50.7Estimated · #82/186 | Not comparableBenchAlign lane · 2 vs 3 public rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 71.0#64/124 | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Math | Not ranked | 76.8Unranked · 4 rankable rows | Not comparableProvisional lane · 0 vs 1 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
- Step 5 Preview
- $0.00235
- Fits in one request
- Ternary Bonsai 2 27B
- Self-hosted; infrastructure cost varies
- Fits in one request
Ternary Bonsai 2 27B has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Step 5 Preview
- $0.0581
- Fits in one request
- Ternary Bonsai 2 27B
- Self-hosted; infrastructure cost varies
- Fits in one request
Ternary Bonsai 2 27B has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Step 5 Preview
- $0.057
- Fits in one request
- Ternary Bonsai 2 27B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
Ternary Bonsai 2 27B 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.
SpecificationStep 5 PreviewTernary Bonsai 2 27B
Context window
Maximum documented context; output-token limits may be lower.
Step 5 Preview
Ternary Bonsai 2 27B
API model ID
Step 5 Preview
step-5-preview
StepFun Step 5 Preview model documentationTernary Bonsai 2 27B
prism-ml/Ternary-Bonsai-2-27B-gguf
PrismML Bonsai 2 collectionCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Step 5 Preview
$0.05 per 1M cached input tokens
StepFun pricing and rate limitsTernary Bonsai 2 27B
No comparable hosted API rate
PrismML Bonsai 2 collectionDocumented inputs
Step 5 Preview
text, image, video
StepFun Step 5 Preview model documentationTernary Bonsai 2 27B
Not sourced
Documented outputs
Step 5 Preview
Ternary Bonsai 2 27B
Not sourced
Provider availability
Step 5 Preview
Preview · StepFun Open Platform API
StepFun Step 5 Preview model documentationTernary Bonsai 2 27B
Not sourced
Reasoning profile
Step 5 Preview
Reasoning
Ternary Bonsai 2 27B
Reasoning
Weight access
Step 5 Preview
Pending
Ternary Bonsai 2 27B
Open Weight
License
Step 5 Preview
Pending
Ternary Bonsai 2 27B
Open Weight
Release date
Step 5 Preview
2026-09-20
Ternary Bonsai 2 27B
2026-09-17
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
- Step 5 Preview has the larger documented window (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 evidence40 rows
Agentic
Terminal-Bench 2.1
Step 5 Preview85.0%SourceTernary Bonsai 2 27B52.8%SourceStep 5 Preview leads this result
Terminal-Bench 4.0
Step 5 Preview33.30%SourceTernary Bonsai 2 27B—Not directly comparable
CyberGym
Step 5 Preview84.7%SourceTernary Bonsai 2 27B—Not directly comparable
AutomationBench
Step 5 Preview44.0%SourceTernary Bonsai 2 27B—Not directly comparable
Toolathlon-Verified
Step 5 Preview74.1%SourceTernary Bonsai 2 27B—Not directly comparable
MCP Atlas
Step 5 Preview85.6%SourceTernary Bonsai 2 27B—Not directly comparable
JobBench
Step 5 Preview59.0%SourceTernary Bonsai 2 27B—Not directly comparable
APEX-Agents
Step 5 Preview37.8%SourceTernary Bonsai 2 27B—Not directly comparable
DRACO
Step 5 Preview83.3%SourceTernary Bonsai 2 27B—Not directly comparable
BrowseComp
Step 5 Preview88.7%SourceTernary Bonsai 2 27B—Not directly comparable
Agents' Last Exam
Step 5 Preview29.5%SourceTernary Bonsai 2 27B—Not directly comparable
τ²-bench results
Step 5 Preview—Ternary Bonsai 2 27B80.2%SourceNot directly comparable
BFCL v3
Step 5 Preview—Ternary Bonsai 2 27B74.9%SourceNot directly comparable
Coding
DeepSWE
Step 5 Preview67.7%SourceTernary Bonsai 2 27B—Not directly comparable
Terminal-Bench 2.1
Step 5 Preview85.0%SourceTernary Bonsai 2 27B52.8%SourceStep 5 Preview leads this result
SciCode
Step 5 Preview58.9%SourceTernary Bonsai 2 27B—Not directly comparable
ProgramBench
Step 5 Preview80.5%SourceTernary Bonsai 2 27B—Not directly comparable
sweMarathon
Step 5 Preview72.7%SourceTernary Bonsai 2 27B—Not directly comparable
MLS-Bench Lite
Step 5 Preview40.5%SourceTernary Bonsai 2 27B—Not directly comparable
LiveCodeBench v6
Step 5 Preview—Ternary Bonsai 2 27B90.1%SourceNot directly comparable
BigCodeBench
Step 5 Preview—Ternary Bonsai 2 27B58.1%SourceNot directly comparable
SWE-bench Verified
Step 5 Preview—Ternary Bonsai 2 27B60.8%SourceNot directly comparable
Reasoning
CritPt
Step 5 Preview20.9%SourceTernary Bonsai 2 27B—Not directly comparable
Multimodal
OfficeQA Pro
Step 5 Preview60.3%SourceTernary Bonsai 2 27B—Not directly comparable
MMMU-Pro
Step 5 Preview76%SourceTernary Bonsai 2 27B—Not directly comparable
CharXiv (overall)
Step 5 Preview—Ternary Bonsai 2 27B80.0%SourceNot directly comparable
A-OKVQA
Step 5 Preview—Ternary Bonsai 2 27B86.8%SourceNot directly comparable
OmniDocBench 1.6
Step 5 Preview—Ternary Bonsai 2 27B89.1%SourceNot directly comparable
RealWorldQA
Step 5 Preview—Ternary Bonsai 2 27B80.1%SourceNot directly comparable
OCRBench V2
Step 5 Preview—Ternary Bonsai 2 27B56.9%SourceNot directly comparable
Knowledge
GPQA-D
Step 5 Preview93.5%SourceTernary Bonsai 2 27B85.8%SourceStep 5 Preview leads this result
HLE
Step 5 Preview46.5%SourceTernary Bonsai 2 27B—Not directly comparable
MMLU-Redux
Step 5 Preview—Ternary Bonsai 2 27B89.1%SourceNot directly comparable
GPQA
Step 5 Preview—Ternary Bonsai 2 27B85.8%SourceNot directly comparable
Instruction following
Math
GSM8K
Step 5 Preview—Ternary Bonsai 2 27B96.7%SourceNot directly comparable
MATH-500
Step 5 Preview—Ternary Bonsai 2 27B98.8%SourceNot directly comparable
AIME 2025
Step 5 Preview—Ternary Bonsai 2 27B95%SourceNot directly comparable
AIME26
Step 5 Preview—Ternary Bonsai 2 27B95.8%SourceNot directly comparable
Questions
Which is better, Step 5 Preview or Ternary Bonsai 2 27B?
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, Step 5 Preview or Ternary Bonsai 2 27B?
Step 5 Preview is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Step 5 Preview or Ternary Bonsai 2 27B?
Step 5 Preview is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Step 5 Preview or Ternary Bonsai 2 27B?
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, Step 5 Preview or Ternary Bonsai 2 27B?
Step 5 Preview has the larger documented context window: 1M, compared with 262K.
Related comparisons
Last updated September 21, 2026
Watch Step 5 Preview vs Ternary Bonsai 2 27B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.