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.

Start free brief
BenchLM
Model A
MAI-Thinking-1

Microsoft

50.6/100

Estimated · Public rank #126

90% interval 40.7–60.5

MAI-Thinking-1 vs Muse Spark 1.1

Updated August 22, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
Muse Spark 1.1

Meta

76.7/100

Supported · Public rank #7

90% interval 72.6–80.9

Decision reading

Muse Spark 1.1 has the higher public score, 76.74 versus 50.59, and the 90% score intervals do not overlap.

3 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.

  • Long documents

    Prompts that approach the documented context limit

    Muse Spark 1.1

    Muse Spark 1.1 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

    The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.

    Confidence: limited

  • Agentic work

    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

  • 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
3
MAI-Thinking-1 only
11
Muse Spark 1.1 only
18
Like-for-like categories
0 / 8

2 categories use 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.

Agentic

Directional only
MAI-Thinking-1
46.0
Muse Spark 1.1
80.4
Weighted basis
1 vs 2 rows
Reading
Directional only

Coding

Directional only
MAI-Thinking-1
65.5
Muse Spark 1.1
61.5
Weighted basis
2 vs 1 rows
Reading
Directional only

Reasoning

Not comparable
MAI-Thinking-1
Not measured
Muse Spark 1.1
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
MAI-Thinking-1
72.5
Muse Spark 1.1
62.1
Weighted basis
3 vs 1 rows
Reading
Not comparable

Math

Not comparable
MAI-Thinking-1
89.7
Muse Spark 1.1
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
MAI-Thinking-1
Not measured
Muse Spark 1.1
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
MAI-Thinking-1
Not measured
Muse Spark 1.1
88.4
Weighted basis
0 vs 1 rows
Reading
Not comparable

Instruction following

Not comparable
MAI-Thinking-1
85.0
Muse Spark 1.1
Not measured
Weighted basis
1 vs 0 rows
Reading
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.

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 1.1
API rate not published
Fits in one request

MAI-Thinking-1 has no comparable published API token rate. Muse Spark 1.1 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 1.1
API rate not published
Fits in one request

MAI-Thinking-1 has no comparable published API token rate. Muse Spark 1.1 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 1.1
API rate not published
Fits in one request
Cached-input rate unavailable

MAI-Thinking-1 has no comparable published API token rate. Muse Spark 1.1 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 1.1

1M

API model ID

MAI-Thinking-1

Not sourced

Muse Spark 1.1

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 1.1

No comparable hosted API rate

Documented inputs

MAI-Thinking-1

Not sourced

Muse Spark 1.1

Not sourced

Documented outputs

MAI-Thinking-1

Not sourced

Muse Spark 1.1

Not sourced

Provider availability

MAI-Thinking-1

Not sourced

Muse Spark 1.1

Not sourced

Reasoning profile

MAI-Thinking-1

Reasoning

Muse Spark 1.1

Reasoning

Weight access

MAI-Thinking-1

Proprietary

Muse Spark 1.1

Proprietary

License

MAI-Thinking-1

Proprietary

Muse Spark 1.1

Proprietary

Release date

MAI-Thinking-1

2026-06-02

Muse Spark 1.1

2026-07-09

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 1.1 has the higher public score, 76.74 versus 50.59, 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 1.1 has the larger documented window (1M).

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 evidence32 rows

Agentic

  • Terminal-Bench 2.0

    MAI-Thinking-146%
    Source
    Muse Spark 1.180%
    Source

    Muse Spark 1.1 leads this result

  • MCP Atlas

    MAI-Thinking-1—
    Muse Spark 1.188.1%
    Source

    Not directly comparable

  • Toolathlon

    MAI-Thinking-1—
    Muse Spark 1.175.6%
    Source

    Not directly comparable

  • OSWorld-Verified

    MAI-Thinking-1—
    Muse Spark 1.180.8%
    Source

    Not directly comparable

  • WebArena-Verified

    MAI-Thinking-1—
    Muse Spark 1.169%
    Source

    Not directly comparable

  • DeepSearchQA

    MAI-Thinking-1—
    Muse Spark 1.184.9%
    Source

    Not directly comparable

  • CyberGym

    MAI-Thinking-1—
    Muse Spark 1.159.0%
    Source

    Not directly comparable

  • Finance Agent v2

    MAI-Thinking-1—
    Muse Spark 1.157.2%
    Source

    Not directly comparable

  • deepSwe

    MAI-Thinking-1—
    Muse Spark 1.153.3%
    Source

    Not directly comparable

  • OSWorld 2.0

    MAI-Thinking-1—
    Muse Spark 1.114.2%
    Source

    Not directly comparable

  • JobBench

    MAI-Thinking-1—
    Muse Spark 1.154.7%
    Source

    Not directly comparable

  • Cybench

    MAI-Thinking-1—
    Muse Spark 1.192.9%
    Source

    Not directly comparable

  • ExploitGym

    MAI-Thinking-1—
    Muse Spark 1.10.8%
    Source

    Not directly comparable

Coding

  • LiveCodeBench v6

    MAI-Thinking-187.7%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • SWE-bench Verified

    MAI-Thinking-173.5%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • SWE-bench Pro

    MAI-Thinking-152.8%
    Source
    Muse Spark 1.161.5%
    Source

    Muse Spark 1.1 leads this result

  • Terminal-Bench 2.0

    MAI-Thinking-146.0%
    Source
    Muse Spark 1.180.0%
    Source

    Muse Spark 1.1 leads this result

Reasoning

  • Graphwalks BFS 128K

    MAI-Thinking-190%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • MRCR 1M

    MAI-Thinking-1—
    Muse Spark 1.154.1%
    Source

    Not directly comparable

Knowledge

  • GPQA

    MAI-Thinking-184.2%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • GPQA-D

    MAI-Thinking-184.2%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • MMLU-Pro

    MAI-Thinking-185%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • SimpleQA

    MAI-Thinking-131%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • HLE

    MAI-Thinking-1—
    Muse Spark 1.162.1%
    Source

    Not directly comparable

  • HLE w/o tools

    MAI-Thinking-1—
    Muse Spark 1.152.2%
    Source

    Not directly comparable

  • HealthBench Professional

    MAI-Thinking-1—
    Muse Spark 1.159.3%
    Source

    Not directly comparable

Math

  • AIME 2025

    MAI-Thinking-197%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • AIME26

    MAI-Thinking-194.5%
    Source
    Muse Spark 1.1—

    Not directly comparable

  • HMMT Feb 2026

    MAI-Thinking-184.9%
    Source
    Muse Spark 1.1—

    Not directly comparable

Multimodal

  • CharXiv

    MAI-Thinking-1—
    Muse Spark 1.188.4%
    Source

    Not directly comparable

  • BabyVision

    MAI-Thinking-1—
    Muse Spark 1.176.3%
    Source

    Not directly comparable

Instruction following

  • IFBench

    MAI-Thinking-185%
    Source
    Muse Spark 1.1—

    Not directly comparable

Frequently asked questions

Which is better, MAI-Thinking-1 or Muse Spark 1.1?

Muse Spark 1.1 has the higher public score, 76.74 versus 50.59, 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 1.1?

The current coding 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.

Which is better for agentic tasks, MAI-Thinking-1 or Muse Spark 1.1?

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.

Which costs less, MAI-Thinking-1 or Muse Spark 1.1?

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 1.1?

Muse Spark 1.1 has the larger documented context window: 1M, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 22, 2026

Watch MAI-Thinking-1 vs Muse Spark 1.1

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.