Agentic
Like-for-like- Inkling-Small
- 36.9
- Supported · #128/152
- Muse Spark 1.1
- 59.4
- Supported · #23/152
- Basis
- BenchAlign lane · 5 vs 14 public rows
- Reading
- Muse Spark 1.1 leads
Inkling-Small vs Muse Spark 1.1
Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Muse Spark 1.1 has the higher public score estimate, 70.41 versus 59.25, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
12 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.
Coding work
Code generation, repair, and software-engineering tasks
Muse Spark 1.1
Muse Spark 1.1 leads on the public coding lane, 59.7 to 43.8, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Muse Spark 1.1
Muse Spark 1.1 leads on the public agentic lane, 59.4 to 36.9, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: stronger
Show secondary and unsupported calls
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.
13 Inkling-Small only
12 Shared
14 Muse Spark 1.1 only
- Shared results
- 12
- Inkling-Small only
- 13
- Muse Spark 1.1 only
- 14
- Like-for-like categories
- 3 / 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
Like-for-like- Inkling-Small
- 43.8
- Supported · #97/151
- Muse Spark 1.1
- 59.7
- Supported · #23/151
- Basis
- BenchAlign lane · 6 vs 4 public rows
- Reading
- Muse Spark 1.1 leads · intervals overlap
Knowledge
Like-for-like- Inkling-Small
- 56.5
- Supported · #46/183
- Muse Spark 1.1
- 70.7
- Supported · #11/183
- Basis
- BenchAlign lane · 6 vs 5 public rows
- Reading
- Muse Spark 1.1 leads · intervals overlap
Reasoning
Not comparable- Inkling-Small
- 42.7
- Unranked · 3 rankable rows
- Muse Spark 1.1
- 74.4
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Inkling-Small
- 76.9
- Unranked · 2 rankable rows
- Muse Spark 1.1
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Inkling-Small
- Not ranked
- Muse Spark 1.1
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Inkling-Small
- 48.8
- #39/48
- Muse Spark 1.1
- 77.5
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 2 vs 1 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Inkling-Small
- 89.6
- #25/123
- Muse Spark 1.1
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
| Category | Inkling-Small | Muse Spark 1.1 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 36.9Supported · #128/152 | 59.4Supported · #23/152 | Like-for-likeBenchAlign lane · 5 vs 14 public rows | Muse Spark 1.1 leads |
| Coding | 43.8Supported · #97/151 | 59.7Supported · #23/151 | Like-for-likeBenchAlign lane · 6 vs 4 public rows | Muse Spark 1.1 leads · intervals overlap |
| Knowledge | 56.5Supported · #46/183 | 70.7Supported · #11/183 | Like-for-likeBenchAlign lane · 6 vs 5 public rows | Muse Spark 1.1 leads · intervals overlap |
| Reasoning | 42.7Unranked · 3 rankable rows | 74.4Unranked · 3 rankable rows | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Math | 76.9Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 48.8#39/48 | 77.5Unranked · 2 rankable rows | Not comparableProvisional lane · 2 vs 1 weighted rows | Not comparable |
| Instruction following | 89.6#25/123 | 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.
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
Inkling-Small: 31.6%Muse Spark 1.1: 52.2%Normalized gap 20.6Inkling-Small source Muse Spark 1.1 sourceTerminal-Bench 2.0
Agentic
Inkling-Small: 64.7%Muse Spark 1.1: 80%Normalized gap 15.3Inkling-Small source Muse Spark 1.1 sourceHLE
Knowledge
Inkling-Small: 47.8%Muse Spark 1.1: 62.1%Normalized gap 14.3Inkling-Small source Muse Spark 1.1 sourceCharXiv
Multimodal
Inkling-Small: 81.3%Muse Spark 1.1: 88.4%Normalized gap 7.1Inkling-Small source Muse Spark 1.1 sourceSWE-bench Pro
Coding
Inkling-Small: 55.9%Muse Spark 1.1: 61.5%Normalized gap 5.6Inkling-Small source Muse Spark 1.1 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
- Inkling-Small
- $0.0013
- Fits in one request
- Muse Spark 1.1
- API rate not published
- Fits in one request
Muse Spark 1.1 has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Inkling-Small
- $0.03332
- Fits in one request
- Muse Spark 1.1
- API rate not published
- Fits in one request
Muse Spark 1.1 has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Inkling-Small
- $0.0492
- Fits in one request
- Muse Spark 1.1
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Muse Spark 1.1 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.
SpecificationInkling-SmallMuse Spark 1.1
Context window
Maximum documented context; output-token limits may be lower.
Inkling-Small
1M
Muse Spark 1.1
1M
API model ID
Inkling-Small
Not sourced
Muse Spark 1.1
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Inkling-Small
$0.116 per 1M cached input tokens
Muse Spark 1.1
No comparable hosted API rate
Documented inputs
Inkling-Small
Not sourced
Muse Spark 1.1
Not sourced
Documented outputs
Inkling-Small
Not sourced
Muse Spark 1.1
Not sourced
Provider availability
Inkling-Small
Not sourced
Muse Spark 1.1
Not sourced
Reasoning profile
Inkling-Small
Hybrid
Muse Spark 1.1
Reasoning
Weight access
Inkling-Small
Open Weight
Muse Spark 1.1
Proprietary
License
Inkling-Small
Open Weight
Muse Spark 1.1
Proprietary
Release date
Inkling-Small
2026-07-30
Muse Spark 1.1
2026-07-09
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 Spark 1.1 has the higher public score estimate, 70.41 versus 59.25, but the 90% score intervals overlap.
- 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 evidence39 rows
Agentic
Terminal-Bench 2.0
Inkling-Small64.7%SourceMuse Spark 1.180%SourceMuse Spark 1.1 leads this result
BrowseComp
Inkling-Small77.4%SourceMuse Spark 1.1—Not directly comparable
MCP Atlas
Inkling-Small79.6%SourceMuse Spark 1.188.1%SourceMuse Spark 1.1 leads this result
Toolathlon-Verified
Inkling-Small54.4%SourceMuse Spark 1.1—Not directly comparable
Terminal-Bench 2.1 (Vals)
Inkling-Small55.1%SourceMuse Spark 1.169.3%SourceMuse Spark 1.1 leads this result
Toolathlon
Inkling-Small—Muse Spark 1.175.6%SourceNot directly comparable
OSWorld-Verified
Inkling-Small—Muse Spark 1.180.8%SourceNot directly comparable
WebArena-Verified
Inkling-Small—Muse Spark 1.169%SourceNot directly comparable
DeepSearchQA
Inkling-Small—Muse Spark 1.184.9%SourceNot directly comparable
CyberGym
Inkling-Small—Muse Spark 1.159.0%SourceNot directly comparable
Finance Agent v2
Inkling-Small—Muse Spark 1.157.2%SourceNot directly comparable
deepSwe
Inkling-Small—Muse Spark 1.153.3%SourceNot directly comparable
OSWorld 2.0
Inkling-Small—Muse Spark 1.114.2%SourceNot directly comparable
JobBench
Inkling-Small—Muse Spark 1.154.7%SourceNot directly comparable
Cybench
Inkling-Small—Muse Spark 1.192.9%SourceNot directly comparable
ExploitGym
Inkling-Small—Muse Spark 1.10.8%SourceNot directly comparable
Coding
SWE-bench Verified
Inkling-Small80.2%SourceMuse Spark 1.1—Not directly comparable
SWE-bench Pro
Inkling-Small55.9%SourceMuse Spark 1.161.5%SourceMuse Spark 1.1 leads this result
Terminal-Bench 2.0
Inkling-Small64.7%SourceMuse Spark 1.180.0%SourceMuse Spark 1.1 leads this result
SciCode
Inkling-Small48.7%SourceMuse Spark 1.1—Not directly comparable
LiveCodeBench (Vals)
Inkling-Small85.9%SourceMuse Spark 1.185.9%SourceTie
SWE-bench (Vals)
Inkling-Small82.2%SourceMuse Spark 1.182.0%SourceInkling-Small leads this result
Reasoning
Knowledge
GPQA
Inkling-Small89.5%SourceMuse Spark 1.1—Not directly comparable
GPQA-D
Inkling-Small89.5%SourceMuse Spark 1.1—Not directly comparable
HLE
Inkling-Small47.8%SourceMuse Spark 1.162.1%SourceMuse Spark 1.1 leads this result
HLE w/o tools
Inkling-Small31.6%SourceMuse Spark 1.152.2%SourceMuse Spark 1.1 leads this result
GPQA Diamond (Vals)
Inkling-Small83.6%SourceMuse Spark 1.191.2%SourceMuse Spark 1.1 leads this result
MMLU-Pro (Vals)
Inkling-Small85.6%SourceMuse Spark 1.188.7%SourceMuse Spark 1.1 leads this result
HealthBench Professional
Inkling-Small—Muse Spark 1.159.3%SourceNot directly comparable
Math
Multimodal
MMMU-Pro
Inkling-Small74%SourceMuse Spark 1.1—Not directly comparable
CharXiv
Inkling-Small81.3%SourceMuse Spark 1.188.4%SourceMuse Spark 1.1 leads this result
CharXiv w/o tools
Inkling-Small77.4%SourceMuse Spark 1.1—Not directly comparable
BabyVision
Inkling-Small—Muse Spark 1.176.3%SourceNot directly comparable
Instruction following
IFBench
Inkling-Small82.2%SourceMuse Spark 1.1—Not directly comparable
Frequently asked questions
Which is better, Inkling-Small or Muse Spark 1.1?
Muse Spark 1.1 has the higher public score estimate, 70.41 versus 59.25, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Inkling-Small or Muse Spark 1.1?
Muse Spark 1.1 leads the public coding lane, 59.7 to 43.8, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, Inkling-Small or Muse Spark 1.1?
Muse Spark 1.1 leads the public agentic tasks lane, 59.4 to 36.9, with Supported evidence for both models and non-overlapping 90% intervals.
Which costs less, Inkling-Small or Muse Spark 1.1?
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, Inkling-Small or Muse Spark 1.1?
Both models list the same context window, 1M.
Related comparisons
Last updated September 10, 2026
Watch Inkling-Small vs Muse Spark 1.1
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.