Skip to main content
BenchLM

Claude Opus 5 vs DeepSeek V4 Pro 0813

Updated September 27, 2026. Rank says Claude Opus 5 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

Decision reading

Claude Opus 5 has the higher public score, 79.81 versus 63.48, and the 90% score intervals do not overlap. 17 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Anthropic logo
Claude Opus 5

Anthropic

79.81/100

Supported · Public rank #5

90% interval 76.3–83.4

Model B
DeepSeek logo
DeepSeek V4 Pro 0813

DeepSeek

63.48/100

Estimated · Public rank #33

90% interval 52.0–75.0

Shared results
17
Claude Opus 5 only
57
DeepSeek V4 Pro 0813 only
25
Like-for-like categories
2 / 8
Supported: Claude Opus 5 · Estimated: DeepSeek V4 Pro 0813How the comparison works

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 Opus 5

    Claude Opus 5 leads on the public coding lane, 72.8 to 50.3, with Supported evidence for both models and non-overlapping 90% intervals.

    Confidence: stronger

  • Agentic work

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

    Claude Opus 5

    Claude Opus 5 leads on the public agentic lane, 77.4 to 55, with Supported evidence for both models and non-overlapping 90% intervals.

    Confidence: stronger

  • 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
Show secondary and unsupported calls

  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K 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

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

72.8Claude Opus 550.3DeepSeek V4 Pro 0813

Like-for-like · BenchAlign v5.7

Claude Opus 5 leads the like-for-like coding row.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboardShortlist models for this job
Same basis rules as the category table below

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

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.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.7 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 Opus 5
77.4
Supported · #3/105
DeepSeek V4 Pro 0813
55.0
Supported · #29/105
Basis
BenchAlign v5.7 lane · 20 vs 11 public rows
Reading
Claude Opus 5 leads

Coding

Like-for-like
Claude Opus 5
72.8
Supported · #5/135
DeepSeek V4 Pro 0813
50.3
Supported · #39/135
Basis
BenchAlign v5.7 lane · 16 vs 15 public rows
Reading
Claude Opus 5 leads

Knowledge

Directional only
Claude Opus 5
81.4
Supported · #5/158
DeepSeek V4 Pro 0813
63.4
Estimated · #29/158
Basis
BenchAlign v5.7 lane · 19 vs 8 public rows
Reading
Directional only

Reasoning

Not comparable
Claude Opus 5
77.3
#6/19
DeepSeek V4 Pro 0813
56.9
Unranked · 4 rankable rows
Basis
Provisional lane · 2 vs 1 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Claude Opus 5
88.8
#2/50
DeepSeek V4 Pro 0813
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Claude Opus 5
Not ranked
DeepSeek V4 Pro 0813
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Claude Opus 5
Not ranked
DeepSeek V4 Pro 0813
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Claude Opus 5
Not ranked
DeepSeek V4 Pro 0813
80.2
Unranked · 4 rankable rows
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

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 Opus 5
$0.0175
Fits in one request
DeepSeek V4 Pro 0813
$0.0033
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 Opus 5
$0.325
Fits in one request
DeepSeek V4 Pro 0813
$0.07788
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 Opus 5
$0.45
Fits in one request
DeepSeek V4 Pro 0813
$0.0748
Fits in one request

DeepSeek V4 Pro 0813 has the lower modeled cost

Costs use the listed standard API rates.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Cached-input rate

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

Claude Opus 5

$0.5 per 1M cached input tokens

Claude API pricing

DeepSeek V4 Pro 0813

$0.044 per 1M cached input tokens

DeepSeek: Models & Pricing

Reasoning profile

Claude Opus 5

Reasoning

DeepSeek V4 Pro 0813

Reasoning

Weight access

Claude Opus 5

Proprietary

DeepSeek V4 Pro 0813

Open Weight

License

Claude Opus 5

Proprietary

DeepSeek V4 Pro 0813

Open Weight

Release date

Claude Opus 5

2026-07-24

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
Claude Opus 5 has the higher public score, 79.81 versus 63.48, and the 90% score intervals do not overlap.
Workload cost
Repository review: $0.325 vs $0.07788. Cache-heavy agent loop: $0.45 vs $0.0748.
Context tradeoff
Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Claude Opus 5 or DeepSeek V4 Pro 0813?

Claude Opus 5 has the higher public score, 79.81 versus 63.48, 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, Claude Opus 5 or DeepSeek V4 Pro 0813?

Claude Opus 5 leads the public coding lane, 72.8 to 50.3, with Supported evidence for both models and non-overlapping 90% intervals.

Which is better for agentic tasks, Claude Opus 5 or DeepSeek V4 Pro 0813?

Claude Opus 5 leads the public agentic tasks lane, 77.4 to 55, with Supported evidence for both models and non-overlapping 90% intervals.

Which costs less, Claude Opus 5 or DeepSeek V4 Pro 0813?

For the stated presets, chat costs $0.0175 on Claude Opus 5 and $0.0033 on DeepSeek V4 Pro 0813; repository review costs $0.325 and $0.07788; the cache-heavy agent loop costs $0.45 and $0.0748. Costs use the listed standard API rates.

Which has the larger context window, Claude Opus 5 or DeepSeek V4 Pro 0813?

Both models list the same context window, 1M.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence99 rows

Agentic

  • Terminal-Bench 3.0

    Claude Opus 542.7%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • BrowseComp

    Claude Opus 590.8%
    Source
    DeepSeek V4 Pro 081383.4%
    Source

    Claude Opus 5 leads this result

  • HLE w/ tools

    Claude Opus 564.7%
    Source
    DeepSeek V4 Pro 081360.0%
    Source

    Claude Opus 5 leads this result

  • DeepSearchQA

    Claude Opus 595.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • DRACO

    Claude Opus 588.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • BrowseComp (10-agent, prerelease)

    Claude Opus 593.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • OSWorld 2.0

    Claude Opus 570.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • MCP Atlas

    Claude Opus 585.8%
    Source
    DeepSeek V4 Pro 081373.6%
    Source

    Claude Opus 5 leads this result

  • MCP-Atlas claim coverage

    Claude Opus 589.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • LAB all-pass (Anthropic harness)

    Claude Opus 523.58%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • LAB criterion-pass (Anthropic harness)

    Claude Opus 593.74%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • LAB all-pass (Harvey held-out)

    Claude Opus 511.7%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • LAB criterion-pass (Harvey held-out)

    Claude Opus 594.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Toolathlon-Verified

    Claude Opus 580.6%
    Source
    DeepSeek V4 Pro 081374.1%
    Source

    Claude Opus 5 leads this result

  • Toolathlon Verified Pass@3

    Claude Opus 587.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Toolathlon Verified Pass³

    Claude Opus 573.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Toolathlon Verified avg. turns

    Claude Opus 523.5 turns
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • AutomationBench

    Claude Opus 526.0%
    Source
    DeepSeek V4 Pro 081331.8%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • Terminal-Bench 2.1 (Vals)

    Claude Opus 584.6%
    Source
    DeepSeek V4 Pro 081354.7%
    Source

    Claude Opus 5 leads this result

  • ApprenticeBench

    Claude Opus 536%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Opus 5—
    DeepSeek V4 Pro 081367.9%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Opus 5—
    DeepSeek V4 Pro 081387.9%
    Source

    Not directly comparable

  • Toolathlon

    Claude Opus 5—
    DeepSeek V4 Pro 081351.8%
    Source

    Not directly comparable

  • CyberGym

    Claude Opus 5—
    DeepSeek V4 Pro 081383.3%
    Source

    Not directly comparable

  • Agents' Last Exam

    Claude Opus 5—
    DeepSeek V4 Pro 081325.7%
    Source

    Not directly comparable

Coding

  • Bug Hunt Bench

    Claude Opus 527 fixes
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • SWE-bench Verified

    Claude Opus 596%
    Source
    DeepSeek V4 Pro 081380.6%
    Source

    Claude Opus 5 leads this result

  • SWE-bench Pro

    Claude Opus 579.2%
    Source
    DeepSeek V4 Pro 081355.4%
    Source

    Claude Opus 5 leads this result

  • SWE Multilingual

    Claude Opus 589.5%
    Source
    DeepSeek V4 Pro 081376.2%
    Source

    Claude Opus 5 leads this result

  • SWE Multimodal

    Claude Opus 559.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • DeepSWE

    Claude Opus 568.8%
    Source
    DeepSeek V4 Pro 081362.7%
    Source

    Claude Opus 5 leads this result

  • FrontierCode 1.1 Main

    Claude Opus 553.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • FrontierCode 1.1 Extended

    Claude Opus 563.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • FrontierSWE v2

    Claude Opus 552.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • ProgramBench (episode 1)

    Claude Opus 583.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • ProgramBench

    Claude Opus 593.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • cursorBench32

    Claude Opus 570.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • VulcanBench v3

    Claude Opus 587.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • VulcanBench CII v1

    Claude Opus 596.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • LiveCodeBench (Vals)

    Claude Opus 589.0%
    Source
    DeepSeek V4 Pro 081387.5%
    Source

    Claude Opus 5 leads this result

  • SWE-bench (Vals)

    Claude Opus 597.0%
    Source
    DeepSeek V4 Pro 081396.4%
    Source

    Claude Opus 5 leads this result

  • LiveCodeBench Pass@1-COT

    Claude Opus 5—
    DeepSeek V4 Pro 081393.5%
    Source

    Not directly comparable

  • Codeforces

    Claude Opus 5—
    DeepSeek V4 Pro 08133206.0
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Opus 5—
    DeepSeek V4 Pro 081367.9%
    Source

    Not directly comparable

  • Vibe Code Bench

    Claude Opus 5—
    DeepSeek V4 Pro 081349.93%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Opus 5—
    DeepSeek V4 Pro 081387.9%
    Source

    Not directly comparable

  • NL2Repo

    Claude Opus 5—
    DeepSeek V4 Pro 081361.5%
    Source

    Not directly comparable

  • DSBench-FullStack

    Claude Opus 5—
    DeepSeek V4 Pro 081371.1%
    Source

    Not directly comparable

  • DSBench-Hard

    Claude Opus 5—
    DeepSeek V4 Pro 081367.2%
    Source

    Not directly comparable

  • OpenHarmony Bench

    Claude Opus 5—
    DeepSeek V4 Pro 081359.0%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-1

    Claude Opus 597.50%
    Source
    DeepSeek V4 Pro 081390.00%
    Source

    Claude Opus 5 leads this result

  • ARC-AGI-2

    Claude Opus 590.4%
    Source
    DeepSeek V4 Pro 081361.3%
    Source

    Claude Opus 5 leads this result

  • ARC-AGI-3

    Claude Opus 530.2%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • MRCR 1M

    Claude Opus 5—
    DeepSeek V4 Pro 081383.5%
    Source

    Not directly comparable

  • CorpusQA 1M

    Claude Opus 5—
    DeepSeek V4 Pro 081362.0%
    Source

    Not directly comparable

Multimodal

  • Chartography (no tools)

    Claude Opus 529.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Chartography (tools)

    Claude Opus 583.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • BenchCAD Vision2Code (no tools)

    Claude Opus 50.366
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • BenchCAD Vision2Code (tools)

    Claude Opus 50.821
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • GDP.pdf (no tools)

    Claude Opus 583.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • GDP.pdf (tools)

    Claude Opus 585.5%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • OfficeQA

    Claude Opus 578.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • OfficeQA Pro

    Claude Opus 566.9%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

Knowledge

  • HLE

    Claude Opus 564.7%
    Source
    DeepSeek V4 Pro 081342.7%
    Source

    Claude Opus 5 leads this result

  • HLE w/o tools

    Claude Opus 556.3%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HLE-Verified

    Claude Opus 554.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • LABBench2

    Claude Opus 584.2%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HealthBench (raw)

    Claude Opus 567.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HealthBench (length-adjusted)

    Claude Opus 557.8%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HealthBench Professional

    Claude Opus 559.8%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HealthBench Professional (raw)

    Claude Opus 573.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • BioMysteryBench (human-solvable)

    Claude Opus 590.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • BioMysteryBench (human-difficult)

    Claude Opus 549.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • SpatialBench Verified

    Claude Opus 572.5%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • SingleCellBench

    Claude Opus 560.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • ProteinGym Hard

    Claude Opus 547.7%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Protein Design

    Claude Opus 542.5%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Organic chemistry V2

    Claude Opus 561.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Protocols (troubleshooting)

    Claude Opus 561.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Protocols (understanding)

    Claude Opus 578.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • GPQA Diamond (Vals)

    Claude Opus 593.4%
    Source
    DeepSeek V4 Pro 081392.4%
    Source

    Claude Opus 5 leads this result

  • MMLU-Pro (Vals)

    Claude Opus 591.6%
    Source
    DeepSeek V4 Pro 081387.0%
    Source

    Claude Opus 5 leads this result

  • MMLU-Pro

    Claude Opus 5—
    DeepSeek V4 Pro 081387.5%
    Source

    Not directly comparable

  • SimpleQA

    Claude Opus 5—
    DeepSeek V4 Pro 081357.9%
    Source

    Not directly comparable

  • Chinese-SimpleQA

    Claude Opus 5—
    DeepSeek V4 Pro 081384.4%
    Source

    Not directly comparable

  • GPQA

    Claude Opus 5—
    DeepSeek V4 Pro 081390.1%
    Source

    Not directly comparable

  • GPQA-D

    Claude Opus 5—
    DeepSeek V4 Pro 081390.1%
    Source

    Not directly comparable

Multilingual

  • GMMLU

    Claude Opus 592.5%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • MILU

    Claude Opus 592.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • INCLUDE

    Claude Opus 589.8%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

Math

  • IMO 2026

    Claude Opus 542/42
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • RiemannBench (no tools)

    Claude Opus 560.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • RiemannBench (tools)

    Claude Opus 579.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • ArXivMath Jun. 2026 (no tools)

    Claude Opus 590.8%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • ArXivMath Jun. 2026 (tools)

    Claude Opus 591.3%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HMMT Feb 2026

    Claude Opus 5—
    DeepSeek V4 Pro 081395.2%
    Source

    Not directly comparable

  • IMOAnswerBench

    Claude Opus 5—
    DeepSeek V4 Pro 081389.8%
    Source

    Not directly comparable

  • Apex

    Claude Opus 5—
    DeepSeek V4 Pro 081338.3%
    Source

    Not directly comparable

  • Apex Shortlist

    Claude Opus 5—
    DeepSeek V4 Pro 081390.2%
    Source

    Not directly comparable

99 public results · 17 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Claude Opus 5 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.

Last updated September 27, 2026