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
Thinking Machines Lab logo
Model A
Inkling

Thinking Machines Lab

66.66/100

Supported · Public rank #38

90% interval 59.174.3

Inkling vs Quasar 438B

Updated September 2, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
Quasar 438B

Multiverse Computing

Evidence status unavailable

90% interval unavailable

Decision reading

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.

0 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.

  • Chat turn cost

    1K fresh input + 500 output tokens

    Quasar 438B

    Quasar 438B has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Quasar 438B

    Quasar 438B has the lower estimated token cost for this stated workload. Quasar 438B has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

Show secondary and unsupported calls
  • Repository review cost

    50K fresh input + 3K output tokens

    Quasar 438B

    Quasar 438B has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

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
0
Inkling only
15
Quasar 438B only
2
Like-for-like categories
0 / 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.

Agentic

Not comparable
Inkling
69.4
Quasar 438B
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Coding

Not comparable
Inkling
68.6
Quasar 438B
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Reasoning

Not comparable
Inkling
Not measured
Quasar 438B
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Inkling
51.6
Quasar 438B
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Math

Not comparable
Inkling
97.1
Quasar 438B
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Inkling
Not measured
Quasar 438B
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Inkling
76.5
Quasar 438B
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Inkling
79.8
Quasar 438B
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.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

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

Inkling
$0.00421
Fits in one request
Quasar 438B
$0.0015
Fits in one request

Quasar 438B has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Inkling
$0.10754
Fits in one request
Quasar 438B
$0.0354
Fits in one request

Quasar 438B has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Inkling
$0.159
Fits in one request
Quasar 438B
$0.15
Fits in one request
Cached input priced at the published list-input rate

Quasar 438B has the lower modeled cost

Quasar 438B has no published cached-input rate, so cached tokens use its listed input 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.

Inkling

1M

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Inkling

$0.374 per 1M cached input tokens

Quasar 438B

Documented inputs

Inkling

Not sourced

Quasar 438B

Not sourced

Documented outputs

Inkling

Not sourced

Quasar 438B

Not sourced

Reasoning profile

Inkling

Hybrid

Quasar 438B

Reasoning

Weight access

Inkling

Open Weight

Quasar 438B

Proprietary

License

Inkling

Open Weight

Quasar 438B

Proprietary

Release date

Inkling

2026-07-15

Quasar 438B

2026-09-02

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
Repository review: $0.10754 vs $0.0354. Cache-heavy agent loop: $0.159 vs $0.15.
Context tradeoff
Both models list 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 evidence17 rows

Agentic

  • Terminal-Bench 2.0

    Inkling63.8%
    Source
    Quasar 438B

    Not directly comparable

  • BrowseComp

    Inkling77.1%
    Source
    Quasar 438B

    Not directly comparable

  • MCP Atlas

    Inkling74.1%
    Source
    Quasar 438B

    Not directly comparable

  • Terminal-Bench 2.1

    Inkling
    Quasar 438B69.3%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Inkling77.6%
    Source
    Quasar 438B

    Not directly comparable

  • SWE-bench Pro

    Inkling54.3%
    Source
    Quasar 438B

    Not directly comparable

  • Terminal-Bench 2.0

    Inkling63.8%
    Source
    Quasar 438B

    Not directly comparable

  • Terminal-Bench 2.1

    Inkling
    Quasar 438B69.3%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Inkling87.9%
    Source
    Quasar 438B

    Not directly comparable

  • GPQA-D

    Inkling87.9%
    Source
    Quasar 438B

    Not directly comparable

  • HLE

    Inkling46%
    Source
    Quasar 438B

    Not directly comparable

  • HLE w/o tools

    Inkling30%
    Source
    Quasar 438B

    Not directly comparable

Math

  • AIME26

    Inkling97.1%
    Source
    Quasar 438B

    Not directly comparable

Multimodal

  • MMMU-Pro

    Inkling73.5%
    Source
    Quasar 438B

    Not directly comparable

  • CharXiv

    Inkling82%
    Source
    Quasar 438B

    Not directly comparable

  • CharXiv w/o tools

    Inkling78.1%
    Source
    Quasar 438B

    Not directly comparable

Instruction following

  • IFBench

    Inkling79.8%
    Source
    Quasar 438B

    Not directly comparable

Frequently asked questions

Which is better, Inkling or Quasar 438B?

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Inkling or Quasar 438B?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

Which is better for agentic tasks, Inkling or Quasar 438B?

The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.

Which costs less, Inkling or Quasar 438B?

For the stated presets, chat costs $0.00421 on Inkling and $0.0015 on Quasar 438B; repository review costs $0.10754 and $0.0354; the cache-heavy agent loop costs $0.159 and $0.15. Quasar 438B has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Inkling or Quasar 438B?

Both models list the same context window, 1M.

Related comparisons

Last updated September 2, 2026

Watch Inkling vs Quasar 438B

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

Read a sample issue

Join 2,000+ readers.