Agentic
Like-for-like- MAI-Thinking-1
- 46.0
- Muse Spark
- 59.0
- Weighted basis
- 1 vs 1 rows
- Reading
- Muse Spark leads
Model comparison
MAI-Thinking-1 vs Muse Spark
Updated August 7, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Muse Spark has the higher public score, 70.48 versus 51.03, and the 90% score intervals do not overlap.
4 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
Muse Spark
Muse Spark leads on the same 2 weighted benchmark rows.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Muse Spark
Muse Spark leads on the same 1 weighted benchmark row.
Confidence: limited
Long documents
Prompts that approach the documented context limit
Muse Spark
Muse Spark has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
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.
10 MAI-Thinking-1 only
4 Shared
20 Muse Spark only
- Shared results
- 4
- MAI-Thinking-1 only
- 10
- Muse Spark only
- 20
- Like-for-like categories
- 2 / 8
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.
Coding
Like-for-like- MAI-Thinking-1
- 65.5
- Muse Spark
- 67.8
- Weighted basis
- 2 vs 2 rows
- Reading
- Muse Spark leads
Reasoning
Not comparable- MAI-Thinking-1
- Not measured
- Muse Spark
- 42.5
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Knowledge
Not comparable- MAI-Thinking-1
- 72.5
- Muse Spark
- 50.4
- Weighted basis
- 3 vs 1 rows
- Reading
- Not comparable
Math
Not comparable- MAI-Thinking-1
- 89.7
- Muse Spark
- 32.9
- Weighted basis
- 2 vs 2 rows
- Reading
- Not comparable
Multilingual
Not comparable- MAI-Thinking-1
- Not measured
- Muse Spark
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- MAI-Thinking-1
- Not measured
- Muse Spark
- 82.5
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Instruction following
Not comparable- MAI-Thinking-1
- 85.0
- Muse Spark
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
| Category | MAI-Thinking-1 | Muse Spark | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 46.0 | 59.0 | Like-for-like1 vs 1 rows | Muse Spark leads |
| Coding | 65.5 | 67.8 | Like-for-like2 vs 2 rows | Muse Spark leads |
| Reasoning | Not measured | 42.5 | Not comparable0 vs 1 rows | Not comparable |
| Knowledge | 72.5 | 50.4 | Not comparable3 vs 1 rows | Not comparable |
| Math | 89.7 | 32.9 | Not comparable2 vs 2 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | 82.5 | Not comparable0 vs 2 rows | Not comparable |
| Instruction following | 85.0 | Not measured | Not comparable1 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.
Terminal-Bench 2.0
Agentic
SWE-bench Verified
Coding
SWE-bench Pro
Coding
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
- MAI-Thinking-1
- API rate not published
- Fits in one request
- Muse Spark
- API rate not published
- Fits in one request
MAI-Thinking-1 has no comparable published API token rate. Muse Spark has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- MAI-Thinking-1
- API rate not published
- Fits in one request
- Muse Spark
- API rate not published
- Fits in one request
MAI-Thinking-1 has no comparable published API token rate. Muse Spark has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- MAI-Thinking-1
- API rate not published
- Fits in one request
- Cached-input rate unavailable
- Muse Spark
- API rate not published
- Fits in one request
- Cached-input rate unavailable
MAI-Thinking-1 has no comparable published API token rate. Muse Spark 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.
SpecificationMAI-Thinking-1Muse Spark
Context window
Maximum documented context; output-token limits may be lower.
MAI-Thinking-1
256K
Muse Spark
262K
API model ID
MAI-Thinking-1
Not sourced
Muse Spark
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
MAI-Thinking-1
No comparable hosted API rate
Muse Spark
No comparable hosted API rate
Documented inputs
MAI-Thinking-1
Not sourced
Muse Spark
Not sourced
Documented outputs
MAI-Thinking-1
Not sourced
Muse Spark
Not sourced
Provider availability
MAI-Thinking-1
Not sourced
Muse Spark
Not sourced
Reasoning profile
MAI-Thinking-1
Reasoning
Muse Spark
Reasoning
Weight access
MAI-Thinking-1
Proprietary
Muse Spark
Proprietary
License
MAI-Thinking-1
Proprietary
Muse Spark
Proprietary
Release date
MAI-Thinking-1
2026-06-02
Muse Spark
2026-04-08
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, 70.48 versus 51.03, and the 90% score intervals do not overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Muse Spark has the larger documented window (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 evidence34 rows
Agentic
Terminal-Bench 2.0
MAI-Thinking-146%SourceMuse Spark59%SourceMuse Spark leads this result
τ²-bench results
MAI-Thinking-1—Muse Spark91.5%SourceNot directly comparable
DeepSearchQA
MAI-Thinking-1—Muse Spark74.8%SourceNot directly comparable
CyberGym
MAI-Thinking-1—Muse Spark43.5%SourceNot directly comparable
Claw-Eval
MAI-Thinking-1—Muse Spark63.8%SourceNot directly comparable
Coding
LiveCodeBench v6
MAI-Thinking-187.7%SourceMuse Spark—Not directly comparable
SWE-bench Verified
MAI-Thinking-173.5%SourceMuse Spark77.4%SourceMuse Spark leads this result
SWE-bench Pro
MAI-Thinking-152.8%SourceMuse Spark52.4%SourceMAI-Thinking-1 leads this result
Terminal-Bench 2.0
MAI-Thinking-146.0%SourceMuse Spark—Not directly comparable
LiveCodeBench Pro
MAI-Thinking-1—Muse Spark80.0%SourceNot directly comparable
Vibe Code Bench
MAI-Thinking-1—Muse Spark19.67%SourceNot directly comparable
Reasoning
Knowledge
GPQA
MAI-Thinking-184.2%SourceMuse Spark—Not directly comparable
GPQA-D
MAI-Thinking-184.2%SourceMuse Spark89.5%SourceMuse Spark leads this result
MMLU-Pro
MAI-Thinking-185%SourceMuse Spark—Not directly comparable
SimpleQA
MAI-Thinking-131%SourceMuse Spark—Not directly comparable
HLE
MAI-Thinking-1—Muse Spark50.4%SourceNot directly comparable
HLE w/o tools
MAI-Thinking-1—Muse Spark42.8%SourceNot directly comparable
HealthBench Hard
MAI-Thinking-1—Muse Spark42.8%SourceNot directly comparable
MedXpertQA (Text)
MAI-Thinking-1—Muse Spark52.6%SourceNot directly comparable
Math
AIME 2025
MAI-Thinking-197%SourceMuse Spark—Not directly comparable
AIME26
MAI-Thinking-194.5%SourceMuse Spark—Not directly comparable
HMMT Feb 2026
MAI-Thinking-184.9%SourceMuse Spark—Not directly comparable
FrontierMath v2 (Tiers 1-3)
MAI-Thinking-1—Muse Spark39.000%SourceNot directly comparable
FrontierMath v2 (Tier 4)
MAI-Thinking-1—Muse Spark14.600%SourceNot directly comparable
Multimodal
CharXiv
MAI-Thinking-1—Muse Spark86.4%SourceNot directly comparable
MMMU-Pro
MAI-Thinking-1—Muse Spark80.4%SourceNot directly comparable
ERQA
MAI-Thinking-1—Muse Spark64.7%SourceNot directly comparable
SimpleVQA
MAI-Thinking-1—Muse Spark71.3%SourceNot directly comparable
ScreenSpot Pro
MAI-Thinking-1—Muse Spark84.1%SourceNot directly comparable
ZeroBench
MAI-Thinking-1—Muse Spark33.0%SourceNot directly comparable
MedXpertQA (MM)
MAI-Thinking-1—Muse Spark78.4%SourceNot directly comparable
Instruction following
IFBench
MAI-Thinking-185%SourceMuse Spark—Not directly comparable
Frequently asked questions
Which is better, MAI-Thinking-1 or Muse Spark?
Muse Spark has the higher public score, 70.48 versus 51.03, 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, MAI-Thinking-1 or Muse Spark?
Muse Spark leads the like-for-like coding comparison across 2 shared weighted benchmark rows.
Which is better for agentic tasks, MAI-Thinking-1 or Muse Spark?
Muse Spark leads the like-for-like agentic tasks comparison across 1 shared weighted benchmark row.
Which costs less, MAI-Thinking-1 or Muse Spark?
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, MAI-Thinking-1 or Muse Spark?
Muse Spark has the larger documented context window: 262K, compared with 256K.
Related comparisons
Last updated August 7, 2026
Watch MAI-Thinking-1 vs Muse Spark
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.