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

DeepSeek V4 Pro 0813 vs GPT-5.5

Decision reading

GPT-5.5 has the higher public score estimate, 71.83 versus 63.99, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

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

DeepSeek logo
Model A
DeepSeek V4 Pro 0813

DeepSeek

63.99/100

Estimated · Public rank #45

90% interval 46.2–75.5

OpenAI logo
Model B
GPT-5.5

OpenAI

71.83/100

Supported · Public rank #11

90% interval 67.7–76.0

Updated September 21, 2026. Rank says GPT-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.

  • Coding work

    Code generation, repair, and software-engineering tasks

    GPT-5.5

    GPT-5.5 leads on the public coding lane, 68.1 to 52.5, with Supported evidence for both models and non-overlapping 90% intervals.

    Confidence: stronger

  • Agentic work

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

    GPT-5.5

    GPT-5.5 leads on the public agentic lane, 62.4 to 55.4, with Supported evidence for both models, although the 90% intervals overlap.

    Confidence: limited

  • 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.

52.5DeepSeek V4 Pro 081368.1GPT-5.5

Like-for-like · BenchAlign

GPT-5.5 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

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
16
DeepSeek V4 Pro 0813 only
24
GPT-5.5 only
23
Like-for-like categories
2 / 8

2 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
DeepSeek V4 Pro 0813
55.4
Supported · #36/154
GPT-5.5
62.4
Supported · #14/154
Basis
BenchAlign lane · 11 vs 14 public rows
Reading
GPT-5.5 leads · intervals overlap

Coding

Like-for-like
DeepSeek V4 Pro 0813
52.5
Supported · #50/156
GPT-5.5
68.1
Supported · #6/156
Basis
BenchAlign lane · 15 vs 9 public rows
Reading
GPT-5.5 leads

Reasoning

Directional only
DeepSeek V4 Pro 0813
60.3
#14/19
GPT-5.5
64.0
#12/19
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Directional only

Knowledge

Directional only
DeepSeek V4 Pro 0813
58.2
Estimated · #42/186
GPT-5.5
72.9
Supported · #7/186
Basis
BenchAlign lane · 8 vs 6 public rows
Reading
Directional only

Multimodal

Not comparable
DeepSeek V4 Pro 0813
Not ranked
GPT-5.5
71.4
#19/49
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Multilingual

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

Instruction following

Not comparable
DeepSeek V4 Pro 0813
Not ranked
GPT-5.5
91.9
#7/124
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
DeepSeek V4 Pro 0813
80.2
Unranked · 4 rankable rows
GPT-5.5
69.4
Unranked · 3 rankable rows
Basis
Provisional lane · 1 vs 2 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

DeepSeek V4 Pro 0813
$0.00087
Fits in one request
GPT-5.5
$0.02
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

DeepSeek V4 Pro 0813
$0.02436
Fits in one request
GPT-5.5
$0.34
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

DeepSeek V4 Pro 0813
$0.01812
Fits in one request
GPT-5.5
$0.5
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.

DeepSeek V4 Pro 0813

$0.003625 per 1M cached input tokens

GPT-5.5

$0.5 per 1M cached input tokens

OpenAI pricing

Reasoning profile

DeepSeek V4 Pro 0813

Reasoning

GPT-5.5

Reasoning

Weight access

DeepSeek V4 Pro 0813

Proprietary

GPT-5.5

Proprietary

License

DeepSeek V4 Pro 0813

Proprietary

GPT-5.5

Proprietary

Release date

DeepSeek V4 Pro 0813

2026-08-13

GPT-5.5

2026-04-23

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
GPT-5.5 has the higher public score estimate, 71.83 versus 63.99, but the 90% score intervals overlap.
Workload cost
Repository review: $0.02436 vs $0.34. Cache-heavy agent loop: $0.01812 vs $0.5.
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 evidence63 rows

Agentic

  • Terminal-Bench 2.0

    DeepSeek V4 Pro 081367.9%
    Source
    GPT-5.582%
    Source

    GPT-5.5 leads this result

  • Terminal-Bench 2.1

    DeepSeek V4 Pro 081387.9%
    Source
    GPT-5.5—

    Not directly comparable

  • BrowseComp

    DeepSeek V4 Pro 081383.4%
    Source
    GPT-5.584.4%
    Source

    GPT-5.5 leads this result

  • HLE w/ tools

    DeepSeek V4 Pro 081360.0%
    Source
    GPT-5.5—

    Not directly comparable

  • MCP Atlas

    DeepSeek V4 Pro 081373.6%
    Source
    GPT-5.575.3%
    Source

    GPT-5.5 leads this result

  • Toolathlon

    DeepSeek V4 Pro 081351.8%
    Source
    GPT-5.555.6%
    Source

    GPT-5.5 leads this result

  • CyberGym

    DeepSeek V4 Pro 081383.3%
    Source
    GPT-5.581.8%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • Toolathlon-Verified

    DeepSeek V4 Pro 081374.1%
    Source
    GPT-5.5—

    Not directly comparable

  • Agents' Last Exam

    DeepSeek V4 Pro 081325.7%
    Source
    GPT-5.5—

    Not directly comparable

  • AutomationBench

    DeepSeek V4 Pro 081331.8%
    Source
    GPT-5.5—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    DeepSeek V4 Pro 081354.7%
    Source
    GPT-5.576.4%
    Source

    GPT-5.5 leads this result

  • OSWorld-Verified

    DeepSeek V4 Pro 0813—
    GPT-5.578.7%
    Source

    Not directly comparable

  • τ²-bench results

    DeepSeek V4 Pro 0813—
    GPT-5.598%
    Source

    Not directly comparable

  • Gert Labs

    DeepSeek V4 Pro 0813—
    GPT-5.572.93%
    Source

    Not directly comparable

  • ResearchClawBench

    DeepSeek V4 Pro 0813—
    GPT-5.517.0%
    Source

    Not directly comparable

  • OSWorld 2.0

    DeepSeek V4 Pro 0813—
    GPT-5.513.0%
    Source

    Not directly comparable

  • JobBench

    DeepSeek V4 Pro 0813—
    GPT-5.542.7%
    Source

    Not directly comparable

  • ExploitGym

    DeepSeek V4 Pro 0813—
    GPT-5.513.4%
    Source

    Not directly comparable

  • ApprenticeBench

    DeepSeek V4 Pro 0813—
    GPT-5.520%
    Source

    Not directly comparable

Coding

  • LiveCodeBench Pass@1-COT

    DeepSeek V4 Pro 081393.5%
    Source
    GPT-5.5—

    Not directly comparable

  • Codeforces

    DeepSeek V4 Pro 08133206.0
    Source
    GPT-5.5—

    Not directly comparable

  • SWE-bench Verified

    DeepSeek V4 Pro 081380.6%
    Source
    GPT-5.5—

    Not directly comparable

  • SWE-bench Pro

    DeepSeek V4 Pro 081355.4%
    Source
    GPT-5.558.6%
    Source

    GPT-5.5 leads this result

  • SWE Multilingual

    DeepSeek V4 Pro 081376.2%
    Source
    GPT-5.5—

    Not directly comparable

  • Terminal-Bench 2.0

    DeepSeek V4 Pro 081367.9%
    Source
    GPT-5.582.0%
    Source

    GPT-5.5 leads this result

  • Vibe Code Bench

    Shared source
    DeepSeek V4 Pro 081349.93%
    GPT-5.569.85%

    GPT-5.5 leads this result

  • Terminal-Bench 2.1

    DeepSeek V4 Pro 081387.9%
    Source
    GPT-5.5—

    Not directly comparable

  • NL2Repo

    DeepSeek V4 Pro 081361.5%
    Source
    GPT-5.5—

    Not directly comparable

  • DeepSWE

    DeepSeek V4 Pro 081362.7%
    Source
    GPT-5.5—

    Not directly comparable

  • DSBench-FullStack

    DeepSeek V4 Pro 081371.1%
    Source
    GPT-5.5—

    Not directly comparable

  • DSBench-Hard

    DeepSeek V4 Pro 081367.2%
    Source
    GPT-5.5—

    Not directly comparable

  • OpenHarmony Bench

    DeepSeek V4 Pro 081359.0%
    Source
    GPT-5.5—

    Not directly comparable

  • LiveCodeBench (Vals)

    DeepSeek V4 Pro 081387.5%
    Source
    GPT-5.585.3%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • SWE-bench (Vals)

    DeepSeek V4 Pro 081396.4%
    Source
    GPT-5.582.6%
    Source

    DeepSeek V4 Pro 0813 leads this result

  • React Native Evals

    DeepSeek V4 Pro 0813—
    GPT-5.584.7%
    Source

    Not directly comparable

  • cursorBench31

    DeepSeek V4 Pro 0813—
    GPT-5.559.2%
    Source

    Not directly comparable

  • cursorBench32

    DeepSeek V4 Pro 0813—
    GPT-5.558.4%
    Source

    Not directly comparable

  • FrontierCode 1.1 Main

    DeepSeek V4 Pro 0813—
    GPT-5.543.0%
    Source

    Not directly comparable

Reasoning

  • MRCR 1M

    DeepSeek V4 Pro 081383.5%
    Source
    GPT-5.5—

    Not directly comparable

  • CorpusQA 1M

    DeepSeek V4 Pro 081362.0%
    Source
    GPT-5.5—

    Not directly comparable

  • MRCR v2 64K-128K

    DeepSeek V4 Pro 0813—
    GPT-5.583.1%
    Source

    Not directly comparable

  • MRCR v2 128K-256K

    DeepSeek V4 Pro 0813—
    GPT-5.587.5%
    Source

    Not directly comparable

  • ARC-AGI-2

    DeepSeek V4 Pro 0813—
    GPT-5.585%
    Source

    Not directly comparable

  • ARC-AGI-3

    DeepSeek V4 Pro 0813—
    GPT-5.50.4%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    DeepSeek V4 Pro 0813—
    GPT-5.581.2%
    Source

    Not directly comparable

  • MMMU-Pro w/ Python

    DeepSeek V4 Pro 0813—
    GPT-5.583.2%
    Source

    Not directly comparable

  • OfficeQA Pro

    DeepSeek V4 Pro 0813—
    GPT-5.554.1%
    Source

    Not directly comparable

Knowledge

  • MMLU-Pro

    DeepSeek V4 Pro 081387.5%
    Source
    GPT-5.5—

    Not directly comparable

  • SimpleQA

    DeepSeek V4 Pro 081357.9%
    Source
    GPT-5.5—

    Not directly comparable

  • Chinese-SimpleQA

    DeepSeek V4 Pro 081384.4%
    Source
    GPT-5.5—

    Not directly comparable

  • GPQA

    DeepSeek V4 Pro 081390.1%
    Source
    GPT-5.593.6%
    Source

    GPT-5.5 leads this result

  • GPQA-D

    DeepSeek V4 Pro 081390.1%
    Source
    GPT-5.593.6%
    Source

    GPT-5.5 leads this result

  • HLE

    DeepSeek V4 Pro 081342.7%
    Source
    GPT-5.552.2%
    Source

    GPT-5.5 leads this result

  • GPQA Diamond (Vals)

    DeepSeek V4 Pro 081392.4%
    Source
    GPT-5.593.2%
    Source

    GPT-5.5 leads this result

  • MMLU-Pro (Vals)

    DeepSeek V4 Pro 081387.0%
    Source
    GPT-5.588.1%
    Source

    GPT-5.5 leads this result

  • HLE w/o tools

    DeepSeek V4 Pro 0813—
    GPT-5.541.4%
    Source

    Not directly comparable

Math

  • HMMT Feb 2026

    DeepSeek V4 Pro 081395.2%
    Source
    GPT-5.5—

    Not directly comparable

  • IMOAnswerBench

    DeepSeek V4 Pro 081389.8%
    Source
    GPT-5.5—

    Not directly comparable

  • Apex

    DeepSeek V4 Pro 081338.3%
    Source
    GPT-5.5—

    Not directly comparable

  • Apex Shortlist

    DeepSeek V4 Pro 081390.2%
    Source
    GPT-5.5—

    Not directly comparable

  • FrontierMath (legacy)

    DeepSeek V4 Pro 0813—
    GPT-5.551.7%
    Source

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    DeepSeek V4 Pro 0813—
    GPT-5.551.700%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    DeepSeek V4 Pro 0813—
    GPT-5.535.400%
    Source

    Not directly comparable

Questions

Which is better, DeepSeek V4 Pro 0813 or GPT-5.5?

GPT-5.5 has the higher public score estimate, 71.83 versus 63.99, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, DeepSeek V4 Pro 0813 or GPT-5.5?

GPT-5.5 leads the public coding lane, 68.1 to 52.5, with Supported evidence for both models and non-overlapping 90% intervals.

Which is better for agentic tasks, DeepSeek V4 Pro 0813 or GPT-5.5?

GPT-5.5 leads the public agentic tasks lane, 62.4 to 55.4, with Supported evidence for both models, although the 90% intervals overlap.

Which costs less, DeepSeek V4 Pro 0813 or GPT-5.5?

For the stated presets, chat costs $0.00087 on DeepSeek V4 Pro 0813 and $0.02 on GPT-5.5; repository review costs $0.02436 and $0.34; the cache-heavy agent loop costs $0.01812 and $0.5. Costs use the listed standard API rates.

Which has the larger context window, DeepSeek V4 Pro 0813 or GPT-5.5?

Both models list the same context window, 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 21, 2026

Watch DeepSeek V4 Pro 0813 vs GPT-5.5

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

Read a sample issue

Join 2,000+ readers.