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
Deepgram Aura-2

Deepgram

—

Evidence status unavailable

90% interval unavailable

Deepgram Aura-2 vs dots3-note Preview

Updated August 14, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
dots3-note Preview

Dots Studio

—

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.

No workload recommendation clears the current evidence threshold.

Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.

Show secondary and unsupported calls

  • 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

    Not enough matched evidence

    A complete context comparison is not sourced.

    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
0
Deepgram Aura-2 only
0
dots3-note Preview only
31
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
Deepgram Aura-2
Not measured
dots3-note Preview
83.3
Weighted basis
0 vs 1 rows
Reading
Not comparable

Coding

Not comparable
Deepgram Aura-2
Not measured
dots3-note Preview
71.7
Weighted basis
0 vs 2 rows
Reading
Not comparable

Reasoning

Not comparable
Deepgram Aura-2
Not measured
dots3-note Preview
81.4
Weighted basis
0 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
Deepgram Aura-2
Not measured
dots3-note Preview
52.6
Weighted basis
0 vs 1 rows
Reading
Not comparable

Math

Not comparable
Deepgram Aura-2
Not measured
dots3-note Preview
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Deepgram Aura-2
Not measured
dots3-note Preview
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Deepgram Aura-2
Not measured
dots3-note Preview
79.1
Weighted basis
0 vs 1 rows
Reading
Not comparable

Instruction following

Not comparable
Deepgram Aura-2
Not measured
dots3-note Preview
85.1
Weighted basis
0 vs 2 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

Deepgram Aura-2
API rate not published
Fit state unavailable
dots3-note Preview
Self-hosted; infrastructure cost varies
Fits in one request

Deepgram Aura-2 has no comparable published API token rate. dots3-note Preview has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Deepgram Aura-2
API rate not published
Fit state unavailable
dots3-note Preview
Self-hosted; infrastructure cost varies
Fits in one request

Deepgram Aura-2 has no comparable published API token rate. dots3-note Preview has no comparable published API token rate.

Cache-heavy agent loop

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

Deepgram Aura-2
API rate not published
Fit state unavailable
Cached-input rate unavailable
dots3-note Preview
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable

Deepgram Aura-2 has no comparable published API token rate. dots3-note Preview 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.

Documented inputs

Deepgram Aura-2

Not sourced

dots3-note Preview

Not sourced

Documented outputs

Deepgram Aura-2

Not sourced

dots3-note Preview

Not sourced

Provider availability

Deepgram Aura-2

Not sourced

dots3-note Preview

Not sourced

Reasoning profile

Deepgram Aura-2

Non-Reasoning

dots3-note Preview

Reasoning

Weight access

Deepgram Aura-2

Proprietary

dots3-note Preview

Open Weight

License

Deepgram Aura-2

Proprietary

dots3-note Preview

Open Weight

Release date

Deepgram Aura-2

Not sourced

dots3-note Preview

2026-08-14

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
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
A complete documented context comparison is not available.

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 evidence31 rows

Agentic

  • Claw-Eval

    Deepgram Aura-2—
    dots3-note Preview73.4%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Deepgram Aura-2—
    dots3-note Preview75.1%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Deepgram Aura-2—
    dots3-note Preview55.6%
    Source

    Not directly comparable

  • skillsBench

    Deepgram Aura-2—
    dots3-note Preview52.8%
    Source

    Not directly comparable

  • APEX-Agents

    Deepgram Aura-2—
    dots3-note Preview30.8%
    Source

    Not directly comparable

  • BrowseComp

    Deepgram Aura-2—
    dots3-note Preview83.3%
    Source

    Not directly comparable

  • HLE w/ tools

    Deepgram Aura-2—
    dots3-note Preview52.6%
    Source

    Not directly comparable

  • DeepSearchQA

    Deepgram Aura-2—
    dots3-note Preview92.1%
    Source

    Not directly comparable

  • WideResearch

    Deepgram Aura-2—
    dots3-note Preview78.9%
    Source

    Not directly comparable

Coding

  • Codeforces

    Deepgram Aura-2—
    dots3-note Preview3056.0
    Source

    Not directly comparable

  • LiveCodeBench v6

    Deepgram Aura-2—
    dots3-note Preview91.5%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Deepgram Aura-2—
    dots3-note Preview75.1%
    Source

    Not directly comparable

  • SWE-bench Verified

    Deepgram Aura-2—
    dots3-note Preview78.4%
    Source

    Not directly comparable

  • SWE Multilingual

    Deepgram Aura-2—
    dots3-note Preview75.7%
    Source

    Not directly comparable

  • SWE-bench Pro

    Deepgram Aura-2—
    dots3-note Preview61%
    Source

    Not directly comparable

  • NL2Repo

    Deepgram Aura-2—
    dots3-note Preview49.8%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    Deepgram Aura-2—
    dots3-note Preview81.4%
    Source

    Not directly comparable

Knowledge

  • HLE

    Deepgram Aura-2—
    dots3-note Preview52.6%
    Source

    Not directly comparable

Math

  • IMOAnswerBench

    Deepgram Aura-2—
    dots3-note Preview90.9%
    Source

    Not directly comparable

Multimodal

  • SimpleVQA

    Deepgram Aura-2—
    dots3-note Preview72.5%
    Source

    Not directly comparable

  • MMMU-Pro

    Deepgram Aura-2—
    dots3-note Preview79.1%
    Source

    Not directly comparable

  • MathVision

    Deepgram Aura-2—
    dots3-note Preview87.7%
    Source

    Not directly comparable

  • ZeroBench

    Deepgram Aura-2—
    dots3-note Preview19.0%
    Source

    Not directly comparable

  • CharXiv w/o tools

    Deepgram Aura-2—
    dots3-note Preview83.1%
    Source

    Not directly comparable

  • GDP.pdf (no tools)

    Deepgram Aura-2—
    dots3-note Preview60.7%
    Source

    Not directly comparable

  • PerceptionBench

    Deepgram Aura-2—
    dots3-note Preview53.4%
    Source

    Not directly comparable

  • BabyVision

    Deepgram Aura-2—
    dots3-note Preview50.0%
    Source

    Not directly comparable

  • MMVU

    Deepgram Aura-2—
    dots3-note Preview79.9%
    Source

    Not directly comparable

  • VideoMMMU

    Deepgram Aura-2—
    dots3-note Preview86.8%
    Source

    Not directly comparable

Instruction following

  • IFBench

    Deepgram Aura-2—
    dots3-note Preview80.4%
    Source

    Not directly comparable

  • IFEval

    Deepgram Aura-2—
    dots3-note Preview93.9%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Deepgram Aura-2 or dots3-note Preview?

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, Deepgram Aura-2 or dots3-note Preview?

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, Deepgram Aura-2 or dots3-note Preview?

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, Deepgram Aura-2 or dots3-note Preview?

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, Deepgram Aura-2 or dots3-note Preview?

A complete documented context-window comparison is not available.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 14, 2026

Watch Deepgram Aura-2 vs dots3-note Preview

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

Read a sample issue

Join 2,000+ readers.