Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

Claude Sonnet 4.6 vs DeepSeek V4 Pro 0813

Decision reading

DeepSeek V4 Pro 0813 has the higher public score estimate, 63.69 versus 62.86, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

12 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Anthropic logo
Model A
Claude Sonnet 4.6

Anthropic

62.86/100

Supported · Public rank #48

90% interval 51.0–74.8

DeepSeek logo
Model B
DeepSeek V4 Pro 0813

DeepSeek

63.69/100

Estimated · Public rank #44

90% interval 46.0–75.2

Updated September 18, 2026. Rank says DeepSeek V4 Pro 0813 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

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.

  • Coding work

    Code generation, repair, and software-engineering tasks

    Claude Sonnet 4.6

    Claude Sonnet 4.6 leads on the public coding lane, 52.2 to 51.6, with Supported evidence for both models, although the 90% intervals overlap.

    Confidence: limited

  • Agentic work

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

    DeepSeek V4 Pro 0813

    DeepSeek V4 Pro 0813 leads on the public agentic lane, 55 to 43.8, with Supported evidence for both models, although the 90% intervals overlap.

    Confidence: limited

  • 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

  • Chat turn cost

    1K fresh input + 500 output tokens

    DeepSeek V4 Pro 0813

    DeepSeek V4 Pro 0813 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Repository review cost

    50K fresh input + 3K output tokens

    DeepSeek V4 Pro 0813

    DeepSeek V4 Pro 0813 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

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

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
12
Claude Sonnet 4.6 only
14
DeepSeek V4 Pro 0813 only
28
Like-for-like categories
2 / 8

1 category rests 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

Like-for-like
Claude Sonnet 4.6
43.8
Supported · #95/154
DeepSeek V4 Pro 0813
55.0
Supported · #37/154
Basis
BenchAlign lane · 9 vs 11 public rows
Reading
DeepSeek V4 Pro 0813 leads · intervals overlap

Coding

Like-for-like
Claude Sonnet 4.6
52.2
Supported · #49/154
DeepSeek V4 Pro 0813
51.6
Supported · #51/154
Basis
BenchAlign lane · 8 vs 15 public rows
Reading
Claude Sonnet 4.6 leads · intervals overlap

Knowledge

Directional only
Claude Sonnet 4.6
55.7
Supported · #51/184
DeepSeek V4 Pro 0813
58.1
Estimated · #41/184
Basis
BenchAlign lane · 6 vs 8 public rows
Reading
Directional only

Reasoning

Not comparable
Claude Sonnet 4.6
67.9
Unranked · 2 rankable rows
DeepSeek V4 Pro 0813
60.3
#15/20
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Claude Sonnet 4.6
48.8
Unranked · 2 rankable rows
DeepSeek V4 Pro 0813
80.2
Unranked · 4 rankable rows
Basis
Provisional lane · 2 vs 1 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Claude Sonnet 4.6
Not ranked
DeepSeek V4 Pro 0813
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Claude Sonnet 4.6
54.1
#33/48
DeepSeek V4 Pro 0813
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Claude Sonnet 4.6
46.6
#88/124
DeepSeek V4 Pro 0813
Not ranked
Basis
Provisional lane · 0 vs 0 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

Claude Sonnet 4.6
$0.0105
Fits in one request
DeepSeek V4 Pro 0813
$0.00087
Fits in one request

DeepSeek V4 Pro 0813 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Sonnet 4.6
$0.195
Fits in one request
DeepSeek V4 Pro 0813
$0.02436
Fits in one request

DeepSeek V4 Pro 0813 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Claude Sonnet 4.6
$0.81
Does not fit in one request
Cached input priced at the published list-input rate
DeepSeek V4 Pro 0813
$0.01812
Fits in one request

Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 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.

Claude Sonnet 4.6

200K

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.

Claude Sonnet 4.6

Not published

DeepSeek V4 Pro 0813

$0.003625 per 1M cached input tokens

Reasoning profile

Claude Sonnet 4.6

Non-Reasoning

DeepSeek V4 Pro 0813

Reasoning

Weight access

Claude Sonnet 4.6

Proprietary

DeepSeek V4 Pro 0813

Proprietary

License

Claude Sonnet 4.6

Proprietary

DeepSeek V4 Pro 0813

Proprietary

Release date

Claude Sonnet 4.6

2026-02-01

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, 63.69 versus 62.86, but the 90% score intervals overlap.
Workload cost
Repository review: $0.195 vs $0.02436. Cache-heavy agent loop: $0.81 vs $0.01812.
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 evidence54 rows

Agentic

  • Terminal-Bench 2.0

    Claude Sonnet 4.659.1%
    Source
    DeepSeek V4 Pro 081367.9%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • OSWorld-Verified

    Claude Sonnet 4.672.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Claw-Eval

    Claude Sonnet 4.667.8%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • CyberGym

    Claude Sonnet 4.665.2%
    Source
    DeepSeek V4 Pro 081383.3%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • Gert Labs

    Claude Sonnet 4.662.92%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • OSWorld 2.0

    Claude Sonnet 4.68.3%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • JobBench

    Claude Sonnet 4.636.9%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Sonnet 4.657.3%
    Source
    DeepSeek V4 Pro 081354.7%
    Source

    Claude Sonnet 4.6 leads this result

  • ApprenticeBench

    Claude Sonnet 4.62%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081387.9%
    Source

    Not directly comparable

  • BrowseComp

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081383.4%
    Source

    Not directly comparable

  • HLE w/ tools

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081360.0%
    Source

    Not directly comparable

  • MCP Atlas

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081373.6%
    Source

    Not directly comparable

  • Toolathlon

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081351.8%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081374.1%
    Source

    Not directly comparable

  • Agents' Last Exam

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081325.7%
    Source

    Not directly comparable

  • AutomationBench

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081331.8%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Claude Sonnet 4.679.6%
    Source
    DeepSeek V4 Pro 081380.6%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • SWE-Rebench

    Claude Sonnet 4.660.7%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • React Native Evals

    Claude Sonnet 4.680.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Vibe Code Bench

    Shared source
    Claude Sonnet 4.651.48%
    DeepSeek V4 Pro 081349.93%

    Claude Sonnet 4.6 leads this result

  • cursorBench31

    Claude Sonnet 4.648.8%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • FrontierCode 1.1 Main

    Claude Sonnet 4.624.3%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • LiveCodeBench (Vals)

    Claude Sonnet 4.682.1%
    Source
    DeepSeek V4 Pro 081387.5%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • SWE-bench (Vals)

    Claude Sonnet 4.677.4%
    Source
    DeepSeek V4 Pro 081396.4%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • LiveCodeBench Pass@1-COT

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081393.5%
    Source

    Not directly comparable

  • Codeforces

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 08133206.0
    Source

    Not directly comparable

  • SWE-bench Pro

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081355.4%
    Source

    Not directly comparable

  • SWE Multilingual

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081376.2%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081367.9%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081387.9%
    Source

    Not directly comparable

  • NL2Repo

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081361.5%
    Source

    Not directly comparable

  • DeepSWE

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081362.7%
    Source

    Not directly comparable

  • DSBench-FullStack

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081371.1%
    Source

    Not directly comparable

  • DSBench-Hard

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081367.2%
    Source

    Not directly comparable

  • OpenHarmony Bench

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081359.0%
    Source

    Not directly comparable

Reasoning

  • MRCR 1M

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081383.5%
    Source

    Not directly comparable

  • CorpusQA 1M

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081362.0%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Claude Sonnet 4.689.9%
    Source
    DeepSeek V4 Pro 081390.1%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • SuperGPQA

    Claude Sonnet 4.695%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • MMLU-Pro

    Claude Sonnet 4.679.2%
    Source
    DeepSeek V4 Pro 081387.5%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • HLE

    Claude Sonnet 4.649%
    Source
    DeepSeek V4 Pro 081342.7%
    Source

    Claude Sonnet 4.6 leads this result

  • GPQA Diamond (Vals)

    Claude Sonnet 4.685.6%
    Source
    DeepSeek V4 Pro 081392.4%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • MMLU-Pro (Vals)

    Claude Sonnet 4.687.3%
    Source
    DeepSeek V4 Pro 081387.0%
    Source

    Claude Sonnet 4.6 leads this result

  • SimpleQA

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081357.9%
    Source

    Not directly comparable

  • Chinese-SimpleQA

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081384.4%
    Source

    Not directly comparable

  • GPQA-D

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081390.1%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Claude Sonnet 4.632.400%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Claude Sonnet 4.68.300%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HMMT Feb 2026

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081395.2%
    Source

    Not directly comparable

  • IMOAnswerBench

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081389.8%
    Source

    Not directly comparable

  • Apex

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081338.3%
    Source

    Not directly comparable

  • Apex Shortlist

    Claude Sonnet 4.6—
    DeepSeek V4 Pro 081390.2%
    Source

    Not directly comparable

Multimodal

  • CharXiv

    Claude Sonnet 4.677.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

Questions

Which is better, Claude Sonnet 4.6 or DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 has the higher public score estimate, 63.69 versus 62.86, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Claude Sonnet 4.6 or DeepSeek V4 Pro 0813?

Claude Sonnet 4.6 leads the public coding lane, 52.2 to 51.6, with Supported evidence for both models, although the 90% intervals overlap.

Which is better for agentic tasks, Claude Sonnet 4.6 or DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 leads the public agentic tasks lane, 55 to 43.8, with Supported evidence for both models, although the 90% intervals overlap.

Which costs less, Claude Sonnet 4.6 or DeepSeek V4 Pro 0813?

For the stated presets, chat costs $0.0105 on Claude Sonnet 4.6 and $0.00087 on DeepSeek V4 Pro 0813; repository review costs $0.195 and $0.02436; the cache-heavy agent loop costs $0.81 and $0.01812. Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude Sonnet 4.6 or DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 has the larger documented context window: 1M, compared with 200K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 18, 2026

Watch Claude Sonnet 4.6 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.