Chat turn cost
1K fresh input + 500 output tokens
Step 5 Preview
Step 5 Preview has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Muse Wonder vs Step 5 Preview
Updated October 12, 2026. Rank says Muse Wonder is ahead. Price, access, and your workload can each overturn that. 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
Decision reading
Muse Wonder has the higher public point estimate, 70.44 versus 68.81. Their conditional score ranges overlap. These ranges do not establish rank confidence. 4 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 4
- Muse Wonder only
- 2
- Step 5 Preview only
- 18
- Like-for-like categories
- 1 / 8
Estimated: Muse Wonder and Step 5 Preview. Conditional ranges do not establish rank confidence.How the comparison works
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.
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Step 5 Preview
Step 5 Preview 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
Step 5 Preview
Step 5 Preview has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCoding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Step 5 Preview is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Muse Wonder is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limitedLong documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
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.
69.8Muse Wonder60.8Step 5 Preview
Directional only · BenchAlign v5.8
Muse Wonder has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
2 Muse Wonder only
4 Shared
18 Step 5 Preview only
1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.8 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.
Knowledge
Like-for-like- Muse Wonder
- 74.0
- Supported · #12/180
- Step 5 Preview
- 68.3
- Supported · #21/180
- Basis
- BenchAlign v5.8 lane · 1 vs 2 public rows
- Reading
- Muse Wonder leads · intervals overlap
Coding
Directional only- Muse Wonder
- 69.8
- Supported · #10/148
- Step 5 Preview
- 60.8
- Estimated · #19/148
- Basis
- BenchAlign v5.8 lane · 3 vs 6 public rows
- Reading
- Directional only
Agentic
Not comparable- Muse Wonder
- Not ranked
- Step 5 Preview
- 63.9
- Estimated · #17/123
- Basis
- BenchAlign v5.8 lane · 2 vs 11 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Muse Wonder
- 81.3
- Unranked · 2 rankable rows
- Step 5 Preview
- 83.4
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Muse Wonder
- Not ranked
- Step 5 Preview
- 74.6
- #24/54
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Muse Wonder
- Not ranked
- Step 5 Preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Muse Wonder
- Not ranked
- Step 5 Preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Muse Wonder
- Not ranked
- Step 5 Preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Muse Wonder | Step 5 Preview | Basis | Reading |
|---|---|---|---|---|
| Knowledge | 74.0Supported · #12/180 | 68.3Supported · #21/180 | Like-for-likeBenchAlign v5.8 lane · 1 vs 2 public rows | Muse Wonder leads · intervals overlap |
| Coding | 69.8Supported · #10/148 | 60.8Estimated · #19/148 | Directional onlyBenchAlign v5.8 lane · 3 vs 6 public rows | Directional only |
| Agentic | Not ranked | 63.9Estimated · #17/123 | Not comparableBenchAlign v5.8 lane · 2 vs 11 public rows | Not comparable |
| Reasoning | 81.3Unranked · 2 rankable rows | 83.4Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | 74.6#24/54 | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 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 v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Supported evidence per lane · bars run 0–100Methodology
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
- Muse Wonder
- $0.014
- Fits in one request
- Step 5 Preview
- $0.00235
- Fits in one request
Step 5 Preview has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Muse Wonder
- $0.26
- Fits in one request
- Step 5 Preview
- $0.0581
- Fits in one request
Step 5 Preview has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Muse Wonder
- $0.32
- Fits in one request
- Step 5 Preview
- $0.057
- Fits in one request
Step 5 Preview has the lower modeled cost
Costs use the listed standard API rates.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationMuse WonderStep 5 Preview
Context window
Maximum documented context; output-token limits may be lower.
Muse Wonder
Step 5 Preview
API model ID
Muse Wonder
muse-wonder-1.0
Meta: Muse Wonder models and pricingStep 5 Preview
step-5-preview
StepFun Step 5 Preview model documentationCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Muse Wonder
$0.2 per 1M cached input tokens
Meta: Muse Wonder models and pricingStep 5 Preview
$0.05 per 1M cached input tokens
StepFun pricing and rate limitsDocumented inputs
Muse Wonder
Not sourced
Step 5 Preview
text, image, video
StepFun Step 5 Preview model documentationDocumented outputs
Muse Wonder
Not sourced
Step 5 Preview
Provider availability
Muse Wonder
Not sourced
Step 5 Preview
Preview · StepFun Open Platform API
StepFun Step 5 Preview model documentationReasoning profile
Muse Wonder
Reasoning
Step 5 Preview
Reasoning
Weight access
Muse Wonder
Proprietary
Step 5 Preview
Pending
License
Muse Wonder
Proprietary
Step 5 Preview
Pending
Release date
Muse Wonder
2026-10-12
Step 5 Preview
2026-09-20
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
- Muse Wonder has the higher public point estimate, 70.44 versus 68.81. Their conditional score ranges overlap. These ranges do not establish rank confidence.
- Workload cost
- Repository review: $0.26 vs $0.0581. Cache-heavy agent loop: $0.32 vs $0.057.
- Context tradeoff
- Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Muse Wonder or Step 5 Preview?
Muse Wonder has the higher public point estimate, 70.44 versus 68.81. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Muse Wonder or Step 5 Preview?
Muse Wonder scores higher for coding on the public lane, 69.8 to 60.8. Step 5 Preview is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Muse Wonder or Step 5 Preview?
Muse Wonder is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Muse Wonder or Step 5 Preview?
For the stated presets, chat costs $0.014 on Muse Wonder and $0.00235 on Step 5 Preview; repository review costs $0.26 and $0.0581; the cache-heavy agent loop costs $0.32 and $0.057. Costs use the listed standard API rates.
Which has the larger context window, Muse Wonder or Step 5 Preview?
Both models list the same context window, 1M.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence24 rows
Agentic
JobBench
Muse Wonder70.5%SourceStep 5 Preview59.0%SourceMuse Wonder leads this result
Finance Agent v2
Muse Wonder56.6%SourceStep 5 Preview—Not directly comparable
Terminal-Bench 2.1
Muse Wonder—Step 5 Preview85.0%SourceNot directly comparable
Terminal-Bench 4.0
Muse Wonder—Step 5 Preview33.30%SourceNot directly comparable
CyberGym
Muse Wonder—Step 5 Preview84.7%SourceNot directly comparable
AutomationBench
Muse Wonder—Step 5 Preview44.0%SourceNot directly comparable
Toolathlon-Verified
Muse Wonder—Step 5 Preview74.1%SourceNot directly comparable
MCP Atlas
Muse Wonder—Step 5 Preview85.6%SourceNot directly comparable
APEX-Agents
Muse Wonder—Step 5 Preview37.8%SourceNot directly comparable
DRACO
Muse Wonder—Step 5 Preview83.3%SourceNot directly comparable
BrowseComp
Muse Wonder—Step 5 Preview88.7%SourceNot directly comparable
Agents' Last Exam
Muse Wonder—Step 5 Preview29.5%SourceNot directly comparable
Coding
DeepSWE
Muse Wonder78.8%SourceStep 5 Preview67.7%SourceMuse Wonder leads this result
ProgramBench
Muse Wonder50.0%SourceStep 5 Preview80.5%SourceStep 5 Preview leads this result
sweMarathon
Muse Wonder53.1%SourceStep 5 Preview72.7%SourceStep 5 Preview leads this result
Terminal-Bench 2.1
Muse Wonder—Step 5 Preview85.0%SourceNot directly comparable
SciCode
Muse Wonder—Step 5 Preview58.9%SourceNot directly comparable
MLS-Bench Lite
Muse Wonder—Step 5 Preview40.5%SourceNot directly comparable
Reasoning
CritPt
Muse Wonder—Step 5 Preview20.9%SourceNot directly comparable
Multimodal
Knowledge
24 public results · 4 shared
Watch Muse Wonder vs Step 5 Preview
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,500+ readers.
Last updated October 12, 2026