Long documents
Prompts that approach the documented context limit
DeepSeek V4 Pro
DeepSeek V4 Pro has the larger documented context window.
Updated November 19, 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, 61.5 versus 59.9. Their conditional score ranges overlap. These ranges do not establish rank confidence. 13 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
dots3-note Preview: No comparable API price
DeepSeek V4 Pro: 1M
dots3-note Preview: 512K
DeepSeek V4 Pro: August 13, 2026
dots3-note Preview: August 14, 2026
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.
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Dots3-note Preview 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
Dots3-note Preview is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
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 v6.0
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.
6 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.
ARC-AGI-2Reasoning
Normalized gap 20.1HLEKnowledge
Normalized gap 9.9SWE-bench ProCoding
Normalized gap 5.6SWE-bench VerifiedCoding
Normalized gap 2.2SWE MultilingualCoding
Normalized gap 0.5Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.
| Category | DeepSeek V4 Pro | dots3-note Preview | Basis | Reading |
|---|---|---|---|---|
| Agentic | 59.3Supported · #60/177 | 60.2Estimated · #55/177 | Directional onlyBenchAlign v6.0 lane · 13 vs 9 public rows | Directional only |
| Coding | 59.6Supported · #55/177 | 59.5Estimated · #56/177 | Directional onlyBenchAlign v6.0 lane · 15 vs 7 public rows | Directional only |
| Multimodal | 60.6Estimated · #51/115 | 56.2Estimated · #57/115 | Directional onlyBenchAlign v6.0 lane · 0 vs 10 public rows | Directional only |
| Knowledge | 60.2Supported · #44/156 | 58.5Estimated · #56/156 | Directional onlyBenchAlign v6.0 lane · 7 vs 1 public rows | Directional only |
| Multilingual | 57.5Estimated · #31/86 | 56.7Estimated · #34/86 | Directional onlyBenchAlign v6.0 lane · 0 vs 0 public rows | Directional only |
| Instruction following | 56.5Supported · #46/142 | 56.6Estimated · #53/142 | Directional onlyBenchAlign v6.0 lane · 0 vs 2 public rows | Directional only |
| Reasoning | 64.6Supported · #33/160 | Not ranked | Not comparableBenchAlign v6.0 lane · 4 vs 1 public rows | Not comparable |
| Math | 59.5Supported · #33/124 | Not ranked | Not comparableBenchAlign v6.0 lane · 6 vs 1 public rows | Not comparable |
Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. 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
dots3-note Preview has no comparable published API token rate.
50K fresh input + 3K output tokens
dots3-note Preview has no comparable published API token rate.
200K cached + 20K fresh input + 10K output tokens
dots3-note Preview has no comparable published API token rate.
Overall score against output price per 1M tokens, one model per family. Pricing as of November 18, 2026.
DeepSeek V4 Pro
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
dots3-note Preview
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek models and pricingdots3-note Preview
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 & Pricingdots3-note Preview
No comparable hosted API rate
dots3-note Preview model cardDeepSeek V4 Pro
dots3-note Preview
text, image, video, audio
dots3-note-prev model cardDeepSeek V4 Pro
dots3-note Preview
DeepSeek V4 Pro
Generally Available · DeepSeek API
DeepSeek models and pricing, V4 Pro continuation footnotedots3-note Preview
Not sourced
DeepSeek V4 Pro
Reasoning
dots3-note Preview
Reasoning
DeepSeek V4 Pro
Open Weight
dots3-note Preview
Open Weight
DeepSeek V4 Pro
Open Weight
dots3-note Preview
Open Weight
DeepSeek V4 Pro
2026-08-13
dots3-note Preview
2026-08-14
DeepSeek V4 Pro has the higher public point estimate, 61.5 versus 59.9. 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, 59.6 to 59.5. Dots3-note Preview 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.
dots3-note Preview scores higher for agentic tasks on the public lane, 60.2 to 59.3. Dots3-note Preview is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
DeepSeek V4 Pro has the larger documented context window: 1M, compared with 512K.
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
DeepSeek V4 Pro leads this result
BrowseComp
DeepSeek V4 Pro leads this result
HLE w/ tools
DeepSeek V4 Pro leads this result
MCP Atlas
Not directly comparable
Toolathlon
Not directly comparable
CyberGym
Not directly comparable
Toolathlon-Verified
DeepSeek V4 Pro leads this result
Agents' Last Exam
Not directly comparable
AutomationBench
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
Claw-Eval
Not directly comparable
skillsBench
Not directly comparable
APEX-Agents
Not directly comparable
DeepSearchQA
Not directly comparable
WideResearch
Not directly comparable
LiveCodeBench Pass@1-COT
Not directly comparable
Codeforces
DeepSeek V4 Pro leads this result
SWE-bench Verified
DeepSeek V4 Pro leads this result
SWE-bench Pro
dots3-note Preview leads this result
SWE Multilingual
DeepSeek V4 Pro leads this result
Terminal-Bench 2.0
Not directly comparable
Vibe Code Bench
Not directly comparable
Terminal-Bench 2.1
DeepSeek V4 Pro leads this result
NL2Repo
DeepSeek V4 Pro leads this result
DeepSWE
Not directly comparable
DSBench-FullStack
Not directly comparable
DSBench-Hard
Not directly comparable
OpenHarmony Bench v1.0
Not directly comparable
LiveCodeBench (Vals)
Not directly comparable
SWE-bench (Vals)
Not directly comparable
LiveCodeBench v6
Not directly comparable
MRCR 1M
Not directly comparable
CorpusQA 1M
Not directly comparable
ARC-AGI-1
Not directly comparable
ARC-AGI-2
dots3-note Preview leads this result
SimpleVQA
Not directly comparable
MMMU-Pro
Not directly comparable
MathVision
Not directly comparable
ZeroBench
Not directly comparable
CharXiv w/o tools
Not directly comparable
GDP.pdf (no tools)
Not directly comparable
PerceptionBench
Not directly comparable
BabyVision
Not directly comparable
MMVU
Not directly comparable
VideoMMMU
Not directly comparable
MMLU-Pro
Not directly comparable
Chinese-SimpleQA
Not directly comparable
GPQA
Not directly comparable
GPQA-D
Not directly comparable
HLE
dots3-note Preview leads this result
GPQA Diamond (Vals)
Not directly comparable
MMLU-Pro (Vals)
Not directly comparable
HMMT Feb 2026
Not directly comparable
IMOAnswerBench
dots3-note Preview leads this result
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 19, 2026