Long documents
Prompts that approach the documented context limit
DeepSeek V4 Pro
DeepSeek V4 Pro has the larger documented context window.
Updated November 18, 2026. Rank says DeepSeek V4 Pro is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
DeepSeek V4 Pro has the higher public point estimate, 62.71 versus 48.96. Their conditional score ranges overlap. These ranges do not establish rank confidence. 5 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
DeepSeek V4 Pro: $1.32 input / $3.96 output
GPT-5: $1.25 input / $10 output
DeepSeek V4 Pro: 1M
GPT-5: 400K
DeepSeek V4 Pro: August 13, 2026
GPT-5: August 7, 2025
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.
Prompts that approach the documented context limit
DeepSeek V4 Pro
DeepSeek V4 Pro has the larger documented context window.
1K fresh input + 500 output tokens
DeepSeek V4 Pro
DeepSeek V4 Pro has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
DeepSeek V4 Pro
DeepSeek V4 Pro has the lower estimated token cost for this stated workload. GPT-5 has no published cached-input rate, so cached tokens use its listed input rate.
50K fresh input + 3K output tokens
DeepSeek V4 Pro
DeepSeek V4 Pro has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Code generation, repair, and software-engineering tasks
Not enough matched evidence
GPT-5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GPT-5 is not ranked on the public lane for agentic, so no winner is named for agentic.
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.
Directional only · BenchAlign v5.8
DeepSeek V4 Pro has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
LiveCodeBench (Vals)Coding
Normalized gap 1.6MMLU-Pro (Vals)Knowledge
Normalized gap 0.5Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, 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.
| Category | DeepSeek V4 Pro | GPT-5 | Basis | Reading |
|---|---|---|---|---|
| Knowledge | 64.2Supported · #35/179 | 53.1Supported · #67/179 | Like-for-likeBenchAlign v5.8 lane · 7 vs 2 public rows | DeepSeek V4 Pro leads · intervals overlap |
| Coding | 51.4Supported · #41/160 | 36.7Estimated · #85/160 | Directional onlyBenchAlign v5.8 lane · 15 vs 3 public rows | Directional only |
| Reasoning | 58.1Supported · #33/159 | 43.7Estimated · #75/159 | Directional onlyBenchAlign v5.8 lane · 4 vs 0 public rows | Directional only |
| Instruction following | 93.8#7/157 | 89.4#35/157 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Agentic | 57.0Supported · #41/138 | Not ranked | Not comparableBenchAlign v5.8 lane · 13 vs 1 public rows | Not comparable |
| Multimodal | Not ranked | Not ranked | Not comparableBenchAlign v5.8 lane · 0 vs 0 public rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 73.9#4/13 | Not ranked | Not comparableProvisional lane · 3 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, and knowledge denominators (BenchAlign v5.8) 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.
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.
1K fresh input + 500 output tokens
DeepSeek V4 Pro has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
DeepSeek V4 Pro has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
DeepSeek V4 Pro has the lower modeled cost
GPT-5 has no published cached-input rate, so cached tokens use its listed input rate.
Enter a month of tokens to price it at both models’ listed API rates.
Standard listed rates, no batch or volume discounts.
Overall score against output price per 1M tokens, one model per family. Pricing as of November 18, 2026.
DeepSeek V4 ProGPT-5
Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.
See DeepSeek V4 Pro on the full price vs performance chartSourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
DeepSeek V4 Pro
GPT-5
400K
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek models and pricingGPT-5
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
DeepSeek V4 Pro
$0.044 per 1M cached input tokens
DeepSeek: Models & PricingGPT-5
Not published
DeepSeek V4 Pro
GPT-5
text, image
OpenAI model page for gpt-5DeepSeek V4 Pro
GPT-5
DeepSeek V4 Pro
Generally Available · DeepSeek API
DeepSeek models and pricing, V4 Pro continuation footnoteGPT-5
Not sourced
DeepSeek V4 Pro
Reasoning
GPT-5
Reasoning
DeepSeek V4 Pro
Open Weight
GPT-5
Proprietary
DeepSeek V4 Pro
Open Weight
GPT-5
Proprietary
DeepSeek V4 Pro
2026-08-13
GPT-5
2025-08-07
DeepSeek V4 Pro has the higher public point estimate, 62.71 versus 48.96. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
DeepSeek V4 Pro scores higher for coding on the public lane, 51.4 to 36.7. GPT-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.
GPT-5 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
For the stated presets, chat costs $0.0033 on DeepSeek V4 Pro and $0.00625 on GPT-5; repository review costs $0.07788 and $0.0925; the cache-heavy agent loop costs $0.0748 and $0.375. GPT-5 has no published cached-input rate, so cached tokens use its listed input rate.
DeepSeek V4 Pro has the larger documented context window: 1M, compared with 400K.
Estimates at 50,000 req/day · 1000 tokens/req average.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 4.1
Not directly comparable
Finch
Not directly comparable
Terminal-Bench 2.0
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
BrowseComp
Not directly comparable
HLE w/ tools
Not directly comparable
MCP Atlas
Not directly comparable
Toolathlon
Not directly comparable
CyberGym
Not directly comparable
Toolathlon-Verified
Not directly comparable
Agents' Last Exam
Not directly comparable
AutomationBench
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
JobBench
Not directly comparable
LiveCodeBench Pass@1-COT
Not directly comparable
Codeforces
Not directly comparable
SWE-bench Verified
Not directly comparable
SWE-bench Pro
Not directly comparable
SWE Multilingual
Not directly comparable
Terminal-Bench 2.0
Not directly comparable
Vibe Code Bench
Shared sourceDeepSeek V4 Pro leads this result
Terminal-Bench 2.1
Not directly comparable
NL2Repo
Not directly comparable
DeepSWE
Not directly comparable
DSBench-FullStack
Not directly comparable
DSBench-Hard
Not directly comparable
OpenHarmony Bench v1.0
Not directly comparable
LiveCodeBench (Vals)
DeepSeek V4 Pro leads this result
SWE-bench (Vals)
DeepSeek V4 Pro leads this result
MMLU-Pro
Not directly comparable
Chinese-SimpleQA
Not directly comparable
GPQA
Not directly comparable
GPQA-D
Not directly comparable
HLE
Not directly comparable
GPQA Diamond (Vals)
DeepSeek V4 Pro leads this result
MMLU-Pro (Vals)
DeepSeek V4 Pro leads this result
HMMT Feb 2026
Not directly comparable
IMOAnswerBench
Not directly comparable
Apex
Not directly comparable
Apex Shortlist
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Not directly comparable
FrontierMath v2 (Tier 4)
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 7,000+ subscribers.
Last updated November 18, 2026