Updated October 10, 2026. Rank says Muse Spark 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
Muse Spark has the higher public point estimate, 60 versus 58.74. Their conditional score ranges overlap. These ranges do not establish rank confidence. 15 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
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.
Code generation, repair, and software-engineering tasks
Muse Spark
Muse Spark has the higher public coding point estimate, 50.4 to 43.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Tool use, computer use, and multi-step task completion
Muse Spark
Muse Spark has the higher public agentic point estimate, 50.2 to 43.7, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
Muse Spark
Muse Spark has the larger documented context window.
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
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.
Like-for-like · BenchAlign v5.8
Muse Spark 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.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
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.
HLEKnowledge
Normalized gap 15.7Terminal-Bench 2.0Agentic
Normalized gap 7.7SWE-bench ProCoding
Normalized gap 6.2CharXivMultimodal
Normalized gap 6.0SWE-bench VerifiedCoding
Normalized gap 2.8Each 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.
| Category | Kimi K2.6 | Muse Spark | Basis | Reading |
|---|---|---|---|---|
| Agentic | 43.7Supported · #57/123 | 50.2Supported · #44/123 | Like-for-likeBenchAlign v5.8 lane · 12 vs 5 public rows | Muse Spark leads · intervals overlap |
| Coding | 43.9Supported · #54/146 | 50.4Supported · #40/146 | Like-for-likeBenchAlign v5.8 lane · 10 vs 5 public rows | Muse Spark leads · intervals overlap |
| Multimodal | 73.8#27/54 | 84.4#12/54 | Like-for-likeProvisional lane · 2 vs 2 weighted rows | Muse Spark leads |
| Knowledge | 59.8Supported · #45/177 | 61.8Supported · #41/177 | Like-for-likeBenchAlign v5.8 lane · 5 vs 7 public rows | Muse Spark leads · intervals overlap |
| Reasoning | Not ranked | 57.2Unranked · 3 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 93.3#10/127 | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 72.2#1/7 | 55.6Unranked · 2 rankable rows | Not comparableProvisional lane · 4 vs 2 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.
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.
1K fresh input + 500 output tokens
Muse Spark has no comparable published API token rate.
50K fresh input + 3K output tokens
Muse Spark has no comparable published API token rate.
200K cached + 20K fresh input + 10K output tokens
Muse Spark has no comparable published API token rate.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
Kimi K2.6
256K
Muse Spark
262K
Kimi K2.6
Not sourced
Muse Spark
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Kimi K2.6
$0.16 per 1M cached input tokens
Muse Spark
No comparable hosted API rate
Kimi K2.6
Not sourced
Muse Spark
Not sourced
Kimi K2.6
Not sourced
Muse Spark
Not sourced
Kimi K2.6
Not sourced
Muse Spark
Not sourced
Kimi K2.6
Reasoning
Muse Spark
Reasoning
Kimi K2.6
Open Weight
Muse Spark
Proprietary
Kimi K2.6
Open Weight
Muse Spark
Proprietary
Kimi K2.6
2026-04-20
Muse Spark
2026-04-08
Muse Spark has the higher public point estimate, 60 versus 58.74. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Muse Spark has the higher public coding point estimate, 50.4 to 43.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Muse Spark has the higher public agentic tasks point estimate, 50.2 to 43.7, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Muse Spark has the larger documented context window: 262K, compared with 256K.
Estimates at 50,000 req/day · 1000 tokens/req average.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 2.0
Kimi K2.6 leads this result
BrowseComp
Not directly comparable
OSWorld-Verified
Not directly comparable
Toolathlon
Not directly comparable
MCP Atlas
Not directly comparable
Claw-Eval
Shared sourceMuse Spark leads this result
DeepSearchQA
Kimi K2.6 leads this result
WideResearch
Not directly comparable
Gert Labs
Not directly comparable
ResearchClawBench
Not directly comparable
OSWorld 2.0
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
τ²-bench results
Not directly comparable
CyberGym
Not directly comparable
SWE-bench Verified
Kimi K2.6 leads this result
LiveCodeBench v6
Not directly comparable
SWE-bench Pro
Kimi K2.6 leads this result
SWE Multilingual
Not directly comparable
SciCode
Not directly comparable
Terminal-Bench 2.0
Not directly comparable
Vibe Code Bench
Shared sourceKimi K2.6 leads this result
cursorBench31
Not directly comparable
LiveCodeBench (Vals)
Not directly comparable
SWE-bench (Vals)
Kimi K2.6 leads this result
LiveCodeBench Pro
Not directly comparable
ARC-AGI-2
Not directly comparable
MMMU-Pro
Muse Spark leads this result
MMMU-Pro w/ Python
Not directly comparable
CharXiv
Muse Spark leads this result
MathVision
Not directly comparable
V*
Not directly comparable
ERQA
Not directly comparable
SimpleVQA
Not directly comparable
ScreenSpot Pro
Not directly comparable
ZeroBench
Not directly comparable
MedXpertQA (MM)
Not directly comparable
GPQA
Not directly comparable
GPQA-D
Kimi K2.6 leads this result
HLE
Muse Spark leads this result
GPQA Diamond (Vals)
Muse Spark leads this result
MMLU-Pro (Vals)
Kimi K2.6 leads this result
HLE w/o tools
Not directly comparable
HealthBench Hard
Not directly comparable
MedXpertQA (Text)
Not directly comparable
AIME26
Not directly comparable
HMMT Feb 2026
Not directly comparable
MMAnswerBench
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared sourceMuse Spark leads this result
FrontierMath v2 (Tier 4)
Shared sourceMuse Spark leads this result
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 10, 2026
