Coding
Like-for-like- Muse Spark
- 67.8
- Ornith-1.5-35B-A3B
- 71.5
- Weighted basis
- 2 vs 2 rows
- Reading
- Ornith-1.5-35B-A3B leads
Muse Spark vs Ornith-1.5-35B-A3B
Updated August 19, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Muse Spark has the higher public score, 70.84 versus 49.27, and the 90% score intervals do not overlap.
6 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.
Coding work
Code generation, repair, and software-engineering tasks
Ornith-1.5-35B-A3B
Ornith-1.5-35B-A3B leads on the same 2 weighted benchmark rows.
Confidence: limited
Show secondary and unsupported calls
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
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.
18 Muse Spark only
6 Shared
12 Ornith-1.5-35B-A3B only
- Shared results
- 6
- Muse Spark only
- 18
- Ornith-1.5-35B-A3B only
- 12
- Like-for-like categories
- 1 / 8
1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
Knowledge
Directional only- Muse Spark
- 50.4
- Ornith-1.5-35B-A3B
- 34.2
- Weighted basis
- 1 vs 2 rows
- Reading
- Directional only
Agentic
Not comparable- Muse Spark
- 59.0
- Ornith-1.5-35B-A3B
- 67.6
- Weighted basis
- 1 vs 1 rows
- Reading
- Not comparable
Reasoning
Not comparable- Muse Spark
- 42.5
- Ornith-1.5-35B-A3B
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- Muse Spark
- 32.9
- Ornith-1.5-35B-A3B
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Muse Spark
- Not measured
- Ornith-1.5-35B-A3B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Muse Spark
- 82.5
- Ornith-1.5-35B-A3B
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Muse Spark
- Not measured
- Ornith-1.5-35B-A3B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Muse Spark | Ornith-1.5-35B-A3B | Weighted basis | Reading |
|---|---|---|---|---|
| Coding | 67.8 | 71.5 | Like-for-like2 vs 2 rows | Ornith-1.5-35B-A3B leads |
| Knowledge | 50.4 | 34.2 | Directional only1 vs 2 rows | Directional only |
| Agentic | 59.0 | 67.6 | Not comparable1 vs 1 rows | Not comparable |
| Reasoning | 42.5 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Math | 32.9 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | 82.5 | Not measured | Not comparable2 vs 0 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.
HLE
Knowledge
Muse Spark: 50.4%Ornith-1.5-35B-A3B: 25.6%Normalized gap 24.8Muse Spark source Ornith-1.5-35B-A3B sourceSWE-bench Pro
Coding
Muse Spark: 52.4%Ornith-1.5-35B-A3B: 59.6%Normalized gap 7.2Muse Spark source Ornith-1.5-35B-A3B sourceSWE-bench Verified
Coding
Muse Spark: 77.4%Ornith-1.5-35B-A3B: 79%Normalized gap 1.6Muse Spark source Ornith-1.5-35B-A3B 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
- Muse Spark
- API rate not published
- Fits in one request
- Ornith-1.5-35B-A3B
- Self-hosted; infrastructure cost varies
- Fits in one request
Muse Spark has no comparable published API token rate. Ornith-1.5-35B-A3B has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Muse Spark
- API rate not published
- Fits in one request
- Ornith-1.5-35B-A3B
- Self-hosted; infrastructure cost varies
- Fits in one request
Muse Spark has no comparable published API token rate. Ornith-1.5-35B-A3B has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Muse Spark
- API rate not published
- Fits in one request
- Cached-input rate unavailable
- Ornith-1.5-35B-A3B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
Muse Spark has no comparable published API token rate. Ornith-1.5-35B-A3B 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.
SpecificationMuse SparkOrnith-1.5-35B-A3B
Context window
Maximum documented context; output-token limits may be lower.
Muse Spark
262K
Ornith-1.5-35B-A3B
API model ID
Muse Spark
Not sourced
Ornith-1.5-35B-A3B
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Muse Spark
No comparable hosted API rate
Ornith-1.5-35B-A3B
No comparable hosted API rate
Ornith-1.5-35B-A3B model cardDocumented inputs
Muse Spark
Not sourced
Ornith-1.5-35B-A3B
Not sourced
Documented outputs
Muse Spark
Not sourced
Ornith-1.5-35B-A3B
Not sourced
Provider availability
Muse Spark
Not sourced
Ornith-1.5-35B-A3B
Not sourced
Reasoning profile
Muse Spark
Reasoning
Ornith-1.5-35B-A3B
Reasoning
Weight access
Muse Spark
Proprietary
Ornith-1.5-35B-A3B
Open Weight
License
Muse Spark
Proprietary
Ornith-1.5-35B-A3B
Open Weight
Release date
Muse Spark
2026-04-08
Ornith-1.5-35B-A3B
2026-08-18
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 has the higher public score, 70.84 versus 49.27, and the 90% score intervals do not overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Both models list 262K.
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 evidence36 rows
Agentic
Terminal-Bench 2.0
Muse Spark59%SourceOrnith-1.5-35B-A3B—Not directly comparable
τ²-bench results
Muse Spark91.5%SourceOrnith-1.5-35B-A3B—Not directly comparable
DeepSearchQA
Muse Spark74.8%SourceOrnith-1.5-35B-A3B—Not directly comparable
CyberGym
Muse Spark43.5%SourceOrnith-1.5-35B-A3B—Not directly comparable
Claw-Eval
Muse Spark63.8%SourceOrnith-1.5-35B-A3B72.5%SourceOrnith-1.5-35B-A3B leads this result
Terminal-Bench 2.1
Muse Spark—Ornith-1.5-35B-A3B67.8%SourceNot directly comparable
HLE w/ tools
Muse Spark—Ornith-1.5-35B-A3B33.4%SourceNot directly comparable
MCP Atlas
Muse Spark—Ornith-1.5-35B-A3B70.2%SourceNot directly comparable
Toolathlon-Verified
Muse Spark—Ornith-1.5-35B-A3B48.7%SourceNot directly comparable
WideResearch
Muse Spark—Ornith-1.5-35B-A3B67.8%SourceNot directly comparable
BrowseComp
Muse Spark—Ornith-1.5-35B-A3B67.6%SourceNot directly comparable
Coding
SWE-bench Verified
Muse Spark77.4%SourceOrnith-1.5-35B-A3B79%SourceOrnith-1.5-35B-A3B leads this result
SWE-bench Pro
Muse Spark52.4%SourceOrnith-1.5-35B-A3B59.6%SourceOrnith-1.5-35B-A3B leads this result
LiveCodeBench Pro
Muse Spark80.0%SourceOrnith-1.5-35B-A3B—Not directly comparable
Vibe Code Bench
Muse Spark19.67%SourceOrnith-1.5-35B-A3B—Not directly comparable
Terminal-Bench 2.1
Muse Spark—Ornith-1.5-35B-A3B67.8%SourceNot directly comparable
SWE Multilingual
Muse Spark—Ornith-1.5-35B-A3B71.4%SourceNot directly comparable
deepSwe
Muse Spark—Ornith-1.5-35B-A3B22%SourceNot directly comparable
frontierBench
Muse Spark—Ornith-1.5-35B-A3B5.1%SourceNot directly comparable
NL2Repo
Muse Spark—Ornith-1.5-35B-A3B46.2%SourceNot directly comparable
Reasoning
ARC-AGI-2
Muse Spark42.5%SourceOrnith-1.5-35B-A3B—Not directly comparable
Knowledge
GPQA-D
Muse Spark89.5%SourceOrnith-1.5-35B-A3B89.2%SourceMuse Spark leads this result
HLE
Muse Spark50.4%SourceOrnith-1.5-35B-A3B25.6%SourceMuse Spark leads this result
HLE w/o tools
Muse Spark42.8%SourceOrnith-1.5-35B-A3B25.6%SourceMuse Spark leads this result
HealthBench Hard
Muse Spark42.8%SourceOrnith-1.5-35B-A3B—Not directly comparable
MedXpertQA (Text)
Muse Spark52.6%SourceOrnith-1.5-35B-A3B—Not directly comparable
GPQA
Muse Spark—Ornith-1.5-35B-A3B89.2%SourceNot directly comparable
Math
Multimodal
CharXiv
Muse Spark86.4%SourceOrnith-1.5-35B-A3B—Not directly comparable
MMMU-Pro
Muse Spark80.4%SourceOrnith-1.5-35B-A3B—Not directly comparable
ERQA
Muse Spark64.7%SourceOrnith-1.5-35B-A3B—Not directly comparable
SimpleVQA
Muse Spark71.3%SourceOrnith-1.5-35B-A3B—Not directly comparable
ScreenSpot Pro
Muse Spark84.1%SourceOrnith-1.5-35B-A3B—Not directly comparable
ZeroBench
Muse Spark33.0%SourceOrnith-1.5-35B-A3B—Not directly comparable
MedXpertQA (MM)
Muse Spark78.4%SourceOrnith-1.5-35B-A3B—Not directly comparable
Frequently asked questions
Which is better, Muse Spark or Ornith-1.5-35B-A3B?
Muse Spark has the higher public score, 70.84 versus 49.27, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, Muse Spark or Ornith-1.5-35B-A3B?
Ornith-1.5-35B-A3B leads the like-for-like coding comparison across 2 shared weighted benchmark rows.
Which is better for agentic tasks, Muse Spark or Ornith-1.5-35B-A3B?
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, Muse Spark or Ornith-1.5-35B-A3B?
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, Muse Spark or Ornith-1.5-35B-A3B?
Both models list the same context window, 262K.
Related comparisons
Last updated August 19, 2026
Watch Muse Spark vs Ornith-1.5-35B-A3B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.