Agentic
Directional only- Kimi K3
- 89.5
- Muse Spark 1.1
- 80.4
- Weighted basis
- 2 vs 2 rows
- Reading
- Directional only
Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.
Start free briefUpdated August 19, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Kimi K3 has the higher public score estimate, 80.53 versus 76.91, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
7 results are shared. Category rows based on 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.
Prompts that approach the documented context limit
Kimi K3
Kimi K3 has the larger documented context window.
Confidence: documented
Code generation, repair, and software-engineering tasks
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Tool use, computer use, and multi-step task completion
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
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
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
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
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
3 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
| Category | Kimi K3 | Muse Spark 1.1 | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 89.5 | 80.4 | Directional only2 vs 2 rows | Directional only |
| Knowledge | 61.0 | 62.1 | Directional only2 vs 1 rows | Directional only |
| Multimodal | 78.5 | 88.4 | Directional only3 vs 1 rows | Directional only |
| Coding | Not measured | 61.5 | Not comparable0 vs 1 rows | Not comparable |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Math | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
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.
Terminal-Bench 2.0
Agentic
HLE
Knowledge
CharXiv
Multimodal
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 1.1 has no comparable published API token rate.
50K fresh input + 3K output tokens
Muse Spark 1.1 has no comparable published API token rate.
200K cached + 20K fresh input + 10K output tokens
Muse Spark 1.1 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 K3
1.05M
Muse Spark 1.1
1M
Kimi K3
Not sourced
Muse Spark 1.1
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Kimi K3
$0.3 per 1M cached input tokens
Muse Spark 1.1
No comparable hosted API rate
Kimi K3
Not sourced
Muse Spark 1.1
Not sourced
Kimi K3
Not sourced
Muse Spark 1.1
Not sourced
Kimi K3
Not sourced
Muse Spark 1.1
Not sourced
Kimi K3
Reasoning
Muse Spark 1.1
Reasoning
Kimi K3
Pending
Muse Spark 1.1
Proprietary
Kimi K3
Pending
Muse Spark 1.1
Proprietary
Kimi K3
2026-07-16
Muse Spark 1.1
2026-07-09
Run the same representative tasks against both endpoints before changing production traffic.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 2.0
Kimi K3 leads this result
BrowseComp
Not directly comparable
DeepSearchQA
Kimi K3 leads this result
Toolathlon-Verified
Not directly comparable
MCP Atlas
Muse Spark 1.1 leads this result
AutomationBench
Not directly comparable
JobBench
Muse Spark 1.1 leads this result
APEX-Agents
Not directly comparable
SpreadsheetBench 2
Not directly comparable
DECK-Bench
Not directly comparable
Toolathlon
Not directly comparable
OSWorld-Verified
Not directly comparable
WebArena-Verified
Not directly comparable
CyberGym
Not directly comparable
Finance Agent v2
Not directly comparable
deepSwe
Not directly comparable
OSWorld 2.0
Not directly comparable
Cybench
Not directly comparable
ExploitGym
Not directly comparable
deepSwe
Not directly comparable
cursorBench32
Not directly comparable
FrontierSWE
Not directly comparable
ProgramBench
Not directly comparable
Kimi Code Bench v2
Not directly comparable
sweMarathon
Not directly comparable
PostTrain Bench
Not directly comparable
MLS-Bench Lite
Not directly comparable
VulcanBench v3
Not directly comparable
APEX-SWE
Not directly comparable
EEBench
Not directly comparable
InferenceEval
Not directly comparable
KernelBench Internal
Not directly comparable
Terminal-Bench 2.0
Not directly comparable
SWE-bench Pro
Not directly comparable
MRCR 1M
Not directly comparable
GPQA
Not directly comparable
GPQA-D
Not directly comparable
HLE
Muse Spark 1.1 leads this result
HLE w/o tools
Muse Spark 1.1 leads this result
HealthBench Professional
Not directly comparable
OfficeQA Pro
Not directly comparable
MMMU-Pro
Not directly comparable
MMMU-Pro w/ Python
Not directly comparable
CharXiv w/o tools
Not directly comparable
CharXiv
Kimi K3 leads this result
MathVision
Not directly comparable
MathVision w/ Python
Not directly comparable
BabyVision w/ Python
Not directly comparable
ZeroBench
Not directly comparable
ZeroBench w/ Python
Not directly comparable
WorldVQA ForceAnswer
Not directly comparable
OmniDocBench
Not directly comparable
PerceptionBench
Not directly comparable
BabyVision
Not directly comparable
Kimi K3 has the higher public score estimate, 80.53 versus 76.91, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Kimi K3 has the larger documented context window: 1.05M, compared with 1M.
Last updated August 19, 2026
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.