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 Opus 5.5 vs DeepSeek V4 Pro 0813

Decision reading

Claude Opus 5.5 has the higher public score estimate, 81.03 versus 64.32, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

7 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 Opus 5.5

Anthropic

81.03/100

Estimated · Public rank #5

90% interval 56.4–92.5

DeepSeek logo
Model B
DeepSeek V4 Pro 0813

DeepSeek

64.32/100

Estimated · Public rank #43

90% interval 46.5–75.8

Updated September 22, 2026. Rank says Claude Opus 5.5 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

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.

  • Agentic work

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

    Claude Opus 5.5

    Claude Opus 5.5 leads on the public agentic lane, 82.7 to 55.5, 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

  • 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

Show secondary and unsupported calls

  • 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

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Claude Opus 5.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited

  • 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.

76.0Claude Opus 5.551.6DeepSeek V4 Pro 0813

Directional only · BenchAlign

Claude Opus 5.5 scores higher, but at least one score rests on Estimated evidence or a different benchmark set. Directional only, no winner.

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

Open the coding leaderboardShortlist models for this job

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
7
Claude Opus 5.5 only
41
DeepSeek V4 Pro 0813 only
33
Like-for-like categories
1 / 8

3 categories rest 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 Opus 5.5
82.7
Supported · #1/156
DeepSeek V4 Pro 0813
55.5
Supported · #39/156
Basis
BenchAlign lane · 11 vs 11 public rows
Reading
Claude Opus 5.5 leads

Coding

Directional only
Claude Opus 5.5
76.0
Estimated · #4/159
DeepSeek V4 Pro 0813
51.6
Supported · #54/159
Basis
BenchAlign lane · 9 vs 15 public rows
Reading
Directional only

Reasoning

Directional only
Claude Opus 5.5
78.5
#4/19
DeepSeek V4 Pro 0813
60.1
#14/19
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Directional only

Knowledge

Directional only
Claude Opus 5.5
81.5
Estimated · #3/187
DeepSeek V4 Pro 0813
58.0
Estimated · #43/187
Basis
BenchAlign lane · 17 vs 8 public rows
Reading
Directional only

Multimodal

Not comparable
Claude Opus 5.5
88.8
#3/50
DeepSeek V4 Pro 0813
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Claude Opus 5.5
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 5.5
Not ranked
DeepSeek V4 Pro 0813
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Claude Opus 5.5
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) 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 Opus 5.5
$0.014
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 Opus 5.5
$0.26
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 Opus 5.5
$0.32
Fits in one request
DeepSeek V4 Pro 0813
$0.01812
Fits in one request

DeepSeek V4 Pro 0813 has the lower modeled cost

Costs use the listed standard API rates.

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 5.5

$0.2 per 1M cached input tokens

Claude Opus 5.5 model documentation

DeepSeek V4 Pro 0813

$0.003625 per 1M cached input tokens

Reasoning profile

Claude Opus 5.5

Reasoning

DeepSeek V4 Pro 0813

Reasoning

Weight access

Claude Opus 5.5

Proprietary

DeepSeek V4 Pro 0813

Proprietary

License

Claude Opus 5.5

Proprietary

DeepSeek V4 Pro 0813

Proprietary

Release date

Claude Opus 5.5

2026-09-22

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 5.5 has the higher public score estimate, 81.03 versus 64.32, but the 90% score intervals overlap.
Workload cost
Repository review: $0.26 vs $0.02436. Cache-heavy agent loop: $0.32 vs $0.01812.
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 evidence81 rows

Agentic

  • Terminal-Bench 4.0

    Claude Opus 5.566.40%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Terminal-Bench-Science 0.1

    Claude Opus 5.558.7%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • AutomationBench

    Claude Opus 5.540.0%
    Source
    DeepSeek V4 Pro 081331.8%
    Source

    Claude Opus 5.5 leads this result

  • HLE w/ tools

    Claude Opus 5.567.7%
    Source
    DeepSeek V4 Pro 081360.0%
    Source

    Claude Opus 5.5 leads this result

  • OSWorld 2.0

    Claude Opus 5.548.7%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • LAB all-pass (Harvey held-out)

    Claude Opus 5.58.3%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • LAB criterion-pass (Harvey held-out)

    Claude Opus 5.591.2%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Toolathlon-Verified

    Claude Opus 5.577.8%
    Source
    DeepSeek V4 Pro 081374.1%
    Source

    Claude Opus 5.5 leads this result

  • Toolathlon Verified Pass@3

    Claude Opus 5.582.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Toolathlon Verified Pass³

    Claude Opus 5.572.2%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Toolathlon Verified avg. turns

    Claude Opus 5.526.9 turns
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Opus 5.5—
    DeepSeek V4 Pro 081367.9%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Opus 5.5—
    DeepSeek V4 Pro 081387.9%
    Source

    Not directly comparable

  • BrowseComp

    Claude Opus 5.5—
    DeepSeek V4 Pro 081383.4%
    Source

    Not directly comparable

  • MCP Atlas

    Claude Opus 5.5—
    DeepSeek V4 Pro 081373.6%
    Source

    Not directly comparable

  • Toolathlon

    Claude Opus 5.5—
    DeepSeek V4 Pro 081351.8%
    Source

    Not directly comparable

  • CyberGym

    Claude Opus 5.5—
    DeepSeek V4 Pro 081383.3%
    Source

    Not directly comparable

  • Agents' Last Exam

    Claude Opus 5.5—
    DeepSeek V4 Pro 081325.7%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Opus 5.5—
    DeepSeek V4 Pro 081354.7%
    Source

    Not directly comparable

Coding

  • FrontierCode 1.1 Main

    Claude Opus 5.554.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • cursorBench40

    Claude Opus 5.557.8%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • SWE-bench Pro

    Claude Opus 5.589.9%
    Source
    DeepSeek V4 Pro 081355.4%
    Source

    Claude Opus 5.5 leads this result

  • SWE Multilingual

    Claude Opus 5.593.9%
    Source
    DeepSeek V4 Pro 081376.2%
    Source

    Claude Opus 5.5 leads this result

  • SWE Multimodal

    Claude Opus 5.561.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • DeepSWE

    Claude Opus 5.574.2%
    Source
    DeepSeek V4 Pro 081362.7%
    Source

    Claude Opus 5.5 leads this result

  • FrontierCode 1.1 Extended

    Claude Opus 5.563.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • FrontierSWE v2

    Claude Opus 5.562.3%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • ProgramBench

    Claude Opus 5.591.2%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • LiveCodeBench Pass@1-COT

    Claude Opus 5.5—
    DeepSeek V4 Pro 081393.5%
    Source

    Not directly comparable

  • Codeforces

    Claude Opus 5.5—
    DeepSeek V4 Pro 08133206.0
    Source

    Not directly comparable

  • SWE-bench Verified

    Claude Opus 5.5—
    DeepSeek V4 Pro 081380.6%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Opus 5.5—
    DeepSeek V4 Pro 081367.9%
    Source

    Not directly comparable

  • Vibe Code Bench

    Claude Opus 5.5—
    DeepSeek V4 Pro 081349.93%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Opus 5.5—
    DeepSeek V4 Pro 081387.9%
    Source

    Not directly comparable

  • NL2Repo

    Claude Opus 5.5—
    DeepSeek V4 Pro 081361.5%
    Source

    Not directly comparable

  • DSBench-FullStack

    Claude Opus 5.5—
    DeepSeek V4 Pro 081371.1%
    Source

    Not directly comparable

  • DSBench-Hard

    Claude Opus 5.5—
    DeepSeek V4 Pro 081367.2%
    Source

    Not directly comparable

  • OpenHarmony Bench

    Claude Opus 5.5—
    DeepSeek V4 Pro 081359.0%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Claude Opus 5.5—
    DeepSeek V4 Pro 081387.5%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    Claude Opus 5.5—
    DeepSeek V4 Pro 081396.4%
    Source

    Not directly comparable

Reasoning

  • MRCR 1M

    Claude Opus 5.5—
    DeepSeek V4 Pro 081383.5%
    Source

    Not directly comparable

  • CorpusQA 1M

    Claude Opus 5.5—
    DeepSeek V4 Pro 081362.0%
    Source

    Not directly comparable

Multimodal

  • Chartography (tools)

    Claude Opus 5.589.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Chartography (no tools)

    Claude Opus 5.564.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • BenchCAD Vision2Code (no tools)

    Claude Opus 5.50.730
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • BenchCAD Vision2Code (tools)

    Claude Opus 5.50.962
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Biomedical image analysis

    Claude Opus 5.571.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • OfficeQA

    Claude Opus 5.578.9%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • OfficeQA Pro

    Claude Opus 5.567.7%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

Knowledge

  • HLE

    Claude Opus 5.567.7%
    Source
    DeepSeek V4 Pro 081342.7%
    Source

    Claude Opus 5.5 leads this result

  • HLE w/o tools

    Claude Opus 5.564.4%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HealthBench (raw)

    Claude Opus 5.568.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HealthBench (length-adjusted)

    Claude Opus 5.560.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HealthBench Professional

    Claude Opus 5.565.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HealthBench Professional (raw)

    Claude Opus 5.577.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • BioMysteryBench (human-solvable)

    Claude Opus 5.589.3%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • BioMysteryBench (human-difficult)

    Claude Opus 5.550.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • SpatialBench Verified

    Claude Opus 5.572.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • SingleCellBench

    Claude Opus 5.561.2%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Morphology-to-molecule matching

    Claude Opus 5.534.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Medicinal chemistry

    Claude Opus 5.563.5%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Protein Design

    Claude Opus 5.560.2%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Protein Design library ranking

    Claude Opus 5.556.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • De novo protein-binder design

    Claude Opus 5.582.6%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Protocols (troubleshooting)

    Claude Opus 5.573.7%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • Protocols (understanding)

    Claude Opus 5.569.0%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • MMLU-Pro

    Claude Opus 5.5—
    DeepSeek V4 Pro 081387.5%
    Source

    Not directly comparable

  • SimpleQA

    Claude Opus 5.5—
    DeepSeek V4 Pro 081357.9%
    Source

    Not directly comparable

  • Chinese-SimpleQA

    Claude Opus 5.5—
    DeepSeek V4 Pro 081384.4%
    Source

    Not directly comparable

  • GPQA

    Claude Opus 5.5—
    DeepSeek V4 Pro 081390.1%
    Source

    Not directly comparable

  • GPQA-D

    Claude Opus 5.5—
    DeepSeek V4 Pro 081390.1%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    Claude Opus 5.5—
    DeepSeek V4 Pro 081392.4%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    Claude Opus 5.5—
    DeepSeek V4 Pro 081387.0%
    Source

    Not directly comparable

Multilingual

  • GMMLU

    Claude Opus 5.594.3%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • MILU

    Claude Opus 5.593.1%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

Math

  • ArXivMath Aug. 2026 (no tools)

    Claude Opus 5.591.2%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • ArXivMath Aug. 2026 (tools)

    Claude Opus 5.596.9%
    Source
    DeepSeek V4 Pro 0813—

    Not directly comparable

  • HMMT Feb 2026

    Claude Opus 5.5—
    DeepSeek V4 Pro 081395.2%
    Source

    Not directly comparable

  • IMOAnswerBench

    Claude Opus 5.5—
    DeepSeek V4 Pro 081389.8%
    Source

    Not directly comparable

  • Apex

    Claude Opus 5.5—
    DeepSeek V4 Pro 081338.3%
    Source

    Not directly comparable

  • Apex Shortlist

    Claude Opus 5.5—
    DeepSeek V4 Pro 081390.2%
    Source

    Not directly comparable

Questions

Which is better, Claude Opus 5.5 or DeepSeek V4 Pro 0813?

Claude Opus 5.5 has the higher public score estimate, 81.03 versus 64.32, 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 Opus 5.5 or DeepSeek V4 Pro 0813?

Claude Opus 5.5 scores higher for coding on the public lane, 76 to 51.6. Claude Opus 5.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Claude Opus 5.5 or DeepSeek V4 Pro 0813?

Claude Opus 5.5 leads the public agentic tasks lane, 82.7 to 55.5, with Supported evidence for both models and non-overlapping 90% intervals.

Which costs less, Claude Opus 5.5 or DeepSeek V4 Pro 0813?

For the stated presets, chat costs $0.014 on Claude Opus 5.5 and $0.00087 on DeepSeek V4 Pro 0813; repository review costs $0.26 and $0.02436; the cache-heavy agent loop costs $0.32 and $0.01812. Costs use the listed standard API rates.

Which has the larger context window, Claude Opus 5.5 or DeepSeek V4 Pro 0813?

Both models list the same context window, 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 22, 2026

Watch Claude Opus 5.5 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.