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
Agents-A1

InternScience

60.2/100

Estimated · Public rank #53

90% interval 50.4–70.1

Agents-A1 vs DeepSeek V4 Pro 0813

Updated August 13, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
DeepSeek V4 Pro 0813

DeepSeek

60.9/100

Estimated · Public rank #48

90% interval 51.1–70.8

Decision reading

DeepSeek V4 Pro 0813 has the higher public score estimate, 60.93 versus 60.24, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

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

    DeepSeek V4 Pro 0813

    DeepSeek V4 Pro 0813 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

    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

    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
Agents-A1 only
3
DeepSeek V4 Pro 0813 only
31
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
Agents-A1
75.5
DeepSeek V4 Pro 0813
74.5
Weighted basis
1 vs 2 rows
Reading
Directional only

Knowledge

Directional only
Agents-A1
47.6
DeepSeek V4 Pro 0813
62.5
Weighted basis
1 vs 4 rows
Reading
Directional only

Coding

Not comparable
Agents-A1
Not measured
DeepSeek V4 Pro 0813
70.9
Weighted basis
0 vs 2 rows
Reading
Not comparable

Reasoning

Not comparable
Agents-A1
60.2
DeepSeek V4 Pro 0813
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Math

Not comparable
Agents-A1
Not measured
DeepSeek V4 Pro 0813
95.2
Weighted basis
0 vs 1 rows
Reading
Not comparable

Multilingual

Not comparable
Agents-A1
Not measured
DeepSeek V4 Pro 0813
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Agents-A1
Not measured
DeepSeek V4 Pro 0813
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Agents-A1
94.8
DeepSeek V4 Pro 0813
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

Agents-A1
API rate not published
Fits in one request
DeepSeek V4 Pro 0813
$0.00087
Fits in one request

Agents-A1 has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Agents-A1
API rate not published
Fits in one request
DeepSeek V4 Pro 0813
$0.02436
Fits in one request

Agents-A1 has no comparable published API token rate.

Cache-heavy agent loop

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

Agents-A1
API rate not published
Fits in one request
Cached-input rate unavailable
DeepSeek V4 Pro 0813
$0.01812
Fits in one request

Agents-A1 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.

Agents-A1

262K

DeepSeek V4 Pro 0813

1M

DeepSeek models and pricing

Cached-input rate

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

Agents-A1

No comparable hosted API rate

DeepSeek V4 Pro 0813

$0.003625 per 1M cached input tokens

Reasoning profile

Agents-A1

Reasoning

DeepSeek V4 Pro 0813

Reasoning

Weight access

Agents-A1

Open Weight

DeepSeek V4 Pro 0813

Proprietary

License

Agents-A1

Open Weight

DeepSeek V4 Pro 0813

Proprietary

Release date

Agents-A1

2026-06-26

DeepSeek V4 Pro 0813

2026-08-13

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
DeepSeek V4 Pro 0813 has the higher public score estimate, 60.93 versus 60.24, but the 90% score intervals overlap.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
DeepSeek V4 Pro 0813 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 evidence37 rows

Agentic

  • BrowseComp

    Agents-A175.5%
    Source
    DeepSeek V4 Pro 081383.4%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • HLE w/ tools

    Agents-A147.6%
    Source
    DeepSeek V4 Pro 081360.0%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • VITA-Bench

    Agents-A138.8%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Terminal-Bench 2.0

    Agents-A1—
    DeepSeek V4 Pro 081367.9%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Agents-A1—
    DeepSeek V4 Pro 081387.9%
    Source

    Not directly comparable

  • MCP Atlas

    Agents-A1—
    DeepSeek V4 Pro 081373.6%
    Source

    Not directly comparable

  • Toolathlon

    Agents-A1—
    DeepSeek V4 Pro 081351.8%
    Source

    Not directly comparable

  • CyberGym

    Agents-A1—
    DeepSeek V4 Pro 081383.3%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Agents-A1—
    DeepSeek V4 Pro 081374.1%
    Source

    Not directly comparable

  • Agents' Last Exam

    Agents-A1—
    DeepSeek V4 Pro 081325.7%
    Source

    Not directly comparable

  • AutomationBench

    Agents-A1—
    DeepSeek V4 Pro 081331.8%
    Source

    Not directly comparable

Coding

  • LiveCodeBench Pass@1-COT

    Agents-A1—
    DeepSeek V4 Pro 081393.5%
    Source

    Not directly comparable

  • Codeforces

    Agents-A1—
    DeepSeek V4 Pro 08133206.0
    Source

    Not directly comparable

  • SWE-bench Verified

    Agents-A1—
    DeepSeek V4 Pro 081380.6%
    Source

    Not directly comparable

  • SWE-bench Pro

    Agents-A1—
    DeepSeek V4 Pro 081355.4%
    Source

    Not directly comparable

  • SWE Multilingual

    Agents-A1—
    DeepSeek V4 Pro 081376.2%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Agents-A1—
    DeepSeek V4 Pro 081367.9%
    Source

    Not directly comparable

  • Vibe Code Bench

    Agents-A1—
    DeepSeek V4 Pro 081349.93%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Agents-A1—
    DeepSeek V4 Pro 081387.9%
    Source

    Not directly comparable

  • NL2Repo

    Agents-A1—
    DeepSeek V4 Pro 081361.5%
    Source

    Not directly comparable

  • deepSwe

    Agents-A1—
    DeepSeek V4 Pro 081362.7%
    Source

    Not directly comparable

  • DSBench-FullStack

    Agents-A1—
    DeepSeek V4 Pro 081371.1%
    Source

    Not directly comparable

  • DSBench-Hard

    Agents-A1—
    DeepSeek V4 Pro 081367.2%
    Source

    Not directly comparable

Reasoning

  • LongBench v2

    Agents-A160.2%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • MRCR 1M

    Agents-A1—
    DeepSeek V4 Pro 081383.5%
    Source

    Not directly comparable

  • CorpusQA 1M

    Agents-A1—
    DeepSeek V4 Pro 081362.0%
    Source

    Not directly comparable

Knowledge

  • HLE

    Agents-A147.6%
    Source
    DeepSeek V4 Pro 081342.7%
    Source

    Agents-A1 leads this result

  • MMLU-Pro

    Agents-A1—
    DeepSeek V4 Pro 081387.5%
    Source

    Not directly comparable

  • SimpleQA

    Agents-A1—
    DeepSeek V4 Pro 081357.9%
    Source

    Not directly comparable

  • Chinese-SimpleQA

    Agents-A1—
    DeepSeek V4 Pro 081384.4%
    Source

    Not directly comparable

  • GPQA

    Agents-A1—
    DeepSeek V4 Pro 081390.1%
    Source

    Not directly comparable

  • GPQA-D

    Agents-A1—
    DeepSeek V4 Pro 081390.1%
    Source

    Not directly comparable

Math

  • HMMT Feb 2026

    Agents-A1—
    DeepSeek V4 Pro 081395.2%
    Source

    Not directly comparable

  • IMOAnswerBench

    Agents-A1—
    DeepSeek V4 Pro 081389.8%
    Source

    Not directly comparable

  • Apex

    Agents-A1—
    DeepSeek V4 Pro 081338.3%
    Source

    Not directly comparable

  • Apex Shortlist

    Agents-A1—
    DeepSeek V4 Pro 081390.2%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Agents-A194.8%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

Frequently asked questions

Which is better, Agents-A1 or DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 has the higher public score estimate, 60.93 versus 60.24, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Agents-A1 or DeepSeek V4 Pro 0813?

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, Agents-A1 or DeepSeek V4 Pro 0813?

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, Agents-A1 or DeepSeek V4 Pro 0813?

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, Agents-A1 or DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 has the larger documented context window: 1M, compared with 262K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 13, 2026

Watch Agents-A1 vs DeepSeek V4 Pro 0813

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

Read a sample issue

Join 2,000+ readers.