Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

See the free Radar Brief
BenchLM
Microsoft logo
Model A
MAI-Thinking-1

Microsoft

52.27/100

Estimated · Public rank #123

90% interval 42.4–62.1

MAI-Thinking-1 vs Muse Spark

Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Meta logo
Model B
Muse Spark

Meta

68.39/100

Supported · Public rank #30

90% interval 60.0–76.8

Decision reading

Muse Spark has the higher public score estimate, 68.39 versus 52.27, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

4 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

Share on XLinkedInSocial cardCSVJSON

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.

  • 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

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    MAI-Thinking-1 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    MAI-Thinking-1 is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    Confidence: limited

  • 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.

Shared results
4
MAI-Thinking-1 only
10
Muse Spark only
20
Like-for-like categories
0 / 8

4 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

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.

Agentic

Directional only
MAI-Thinking-1
51.7
Estimated · #53/151
Muse Spark
58.8
Supported · #31/151
Basis
BenchAlign lane · 1 vs 5 public rows
Reading
Directional only

Coding

Directional only
MAI-Thinking-1
51.8
Estimated · #60/183
Muse Spark
59.2
Supported · #28/183
Basis
BenchAlign lane · 4 vs 4 public rows
Reading
Directional only

Knowledge

Directional only
MAI-Thinking-1
53.3
Estimated · #68/181
Muse Spark
65.7
Supported · #23/181
Basis
BenchAlign lane · 4 vs 5 public rows
Reading
Directional only

Instruction following

Directional only
MAI-Thinking-1
94.7
#1/120
Muse Spark
92.9
#8/120
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Directional only

Reasoning

Not comparable
MAI-Thinking-1
Not ranked
Muse Spark
45.9
Unranked · 3 rankable rows
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Math

Not comparable
MAI-Thinking-1
73.4
Unranked · 3 rankable rows
Muse Spark
55.3
Unranked · 2 rankable rows
Basis
Provisional lane · 2 vs 2 weighted rows
Reading
Not comparable

Multilingual

Not comparable
MAI-Thinking-1
Not ranked
Muse Spark
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
MAI-Thinking-1
Not ranked
Muse Spark
77.5
#14/48
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
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.

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.

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 estimate, 68.39 versus 52.27, but the 90% score intervals 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%
    Source
    Muse Spark59%
    Source

    Muse Spark leads this result

  • τ²-bench results

    MAI-Thinking-1—
    Muse Spark91.5%
    Source

    Not directly comparable

  • DeepSearchQA

    MAI-Thinking-1—
    Muse Spark74.8%
    Source

    Not directly comparable

  • CyberGym

    MAI-Thinking-1—
    Muse Spark43.5%
    Source

    Not directly comparable

  • Claw-Eval

    MAI-Thinking-1—
    Muse Spark63.8%
    Source

    Not directly comparable

Coding

  • LiveCodeBench v6

    MAI-Thinking-187.7%
    Source
    Muse Spark—

    Not directly comparable

  • SWE-bench Verified

    MAI-Thinking-173.5%
    Source
    Muse Spark77.4%
    Source

    Muse Spark leads this result

  • SWE-bench Pro

    MAI-Thinking-152.8%
    Source
    Muse Spark52.4%
    Source

    MAI-Thinking-1 leads this result

  • Terminal-Bench 2.0

    MAI-Thinking-146.0%
    Source
    Muse Spark—

    Not directly comparable

  • LiveCodeBench Pro

    MAI-Thinking-1—
    Muse Spark80.0%
    Source

    Not directly comparable

  • Vibe Code Bench

    MAI-Thinking-1—
    Muse Spark19.67%
    Source

    Not directly comparable

Reasoning

  • Graphwalks BFS 128K

    MAI-Thinking-190%
    Source
    Muse Spark—

    Not directly comparable

  • ARC-AGI-2

    MAI-Thinking-1—
    Muse Spark42.5%
    Source

    Not directly comparable

Knowledge

  • GPQA

    MAI-Thinking-184.2%
    Source
    Muse Spark—

    Not directly comparable

  • GPQA-D

    MAI-Thinking-184.2%
    Source
    Muse Spark89.5%
    Source

    Muse Spark leads this result

  • MMLU-Pro

    MAI-Thinking-185%
    Source
    Muse Spark—

    Not directly comparable

  • SimpleQA

    MAI-Thinking-131%
    Source
    Muse Spark—

    Not directly comparable

  • HLE

    MAI-Thinking-1—
    Muse Spark50.4%
    Source

    Not directly comparable

  • HLE w/o tools

    MAI-Thinking-1—
    Muse Spark42.8%
    Source

    Not directly comparable

  • HealthBench Hard

    MAI-Thinking-1—
    Muse Spark42.8%
    Source

    Not directly comparable

  • MedXpertQA (Text)

    MAI-Thinking-1—
    Muse Spark52.6%
    Source

    Not directly comparable

Math

  • AIME 2025

    MAI-Thinking-197%
    Source
    Muse Spark—

    Not directly comparable

  • AIME26

    MAI-Thinking-194.5%
    Source
    Muse Spark—

    Not directly comparable

  • HMMT Feb 2026

    MAI-Thinking-184.9%
    Source
    Muse Spark—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    MAI-Thinking-1—
    Muse Spark39.000%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    MAI-Thinking-1—
    Muse Spark14.600%
    Source

    Not directly comparable

Multimodal

  • CharXiv

    MAI-Thinking-1—
    Muse Spark86.4%
    Source

    Not directly comparable

  • MMMU-Pro

    MAI-Thinking-1—
    Muse Spark80.4%
    Source

    Not directly comparable

  • ERQA

    MAI-Thinking-1—
    Muse Spark64.7%
    Source

    Not directly comparable

  • SimpleVQA

    MAI-Thinking-1—
    Muse Spark71.3%
    Source

    Not directly comparable

  • ScreenSpot Pro

    MAI-Thinking-1—
    Muse Spark84.1%
    Source

    Not directly comparable

  • ZeroBench

    MAI-Thinking-1—
    Muse Spark33.0%
    Source

    Not directly comparable

  • MedXpertQA (MM)

    MAI-Thinking-1—
    Muse Spark78.4%
    Source

    Not directly comparable

Instruction following

  • IFBench

    MAI-Thinking-185%
    Source
    Muse Spark—

    Not directly comparable

Frequently asked questions

Which is better, MAI-Thinking-1 or Muse Spark?

Muse Spark has the higher public score estimate, 68.39 versus 52.27, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, MAI-Thinking-1 or Muse Spark?

Muse Spark scores higher for coding on the public lane, 59.2 to 51.8. MAI-Thinking-1 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, MAI-Thinking-1 or Muse Spark?

Muse Spark scores higher for agentic tasks on the public lane, 58.8 to 51.7. MAI-Thinking-1 is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

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

Compare API pricing Read the methodology Open the model selector

Last updated September 4, 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 issue

Join 2,000+ readers.