Long documents
Prompts that approach the documented context limit
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 has the larger documented context window.
Confidence: documented
DeepSeek V4 Pro 0813 vs Qwen3.6-35B-A3B
Updated September 27, 2026. Rank says DeepSeek V4 Pro 0813 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Decision reading
DeepSeek V4 Pro 0813 has the higher public score, 63.48 versus 41.88, and the 90% score intervals do not overlap. 12 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 12
- DeepSeek V4 Pro 0813 only
- 30
- Qwen3.6-35B-A3B only
- 29
- Like-for-like categories
- 0 / 8
Estimated: DeepSeek V4 Pro 0813 and Qwen3.6-35B-A3BHow 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.
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Qwen3.6-35B-A3B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Qwen3.6-35B-A3B is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limitedChat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-ratesCache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-ratesRepository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
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.
50.3DeepSeek V4 Pro 081336.4Qwen3.6-35B-A3B
Directional only · BenchAlign v5.7
DeepSeek V4 Pro 0813 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.
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.
30 DeepSeek V4 Pro 0813 only
12 Shared
29 Qwen3.6-35B-A3B only
3 categories rest 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.
HLEKnowledge
Normalized gap 21.3DeepSeek V4 Pro 0813:42.7%Qwen3.6-35B-A3B:21.4%Terminal-Bench 2.0Agentic
Normalized gap 16.4DeepSeek V4 Pro 0813:67.9%Qwen3.6-35B-A3B:51.5%HMMT Feb 2026Math
Normalized gap 11.6DeepSeek V4 Pro 0813:95.2%Qwen3.6-35B-A3B:83.6%SWE MultilingualCoding
Normalized gap 9.0DeepSeek V4 Pro 0813:76.2%Qwen3.6-35B-A3B:67.2%SWE-bench VerifiedCoding
Normalized gap 7.2DeepSeek V4 Pro 0813:80.6%Qwen3.6-35B-A3B:73.4%
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
Directional only- DeepSeek V4 Pro 0813
- 55.0
- Supported · #29/105
- Qwen3.6-35B-A3B
- 29.6
- Estimated · #67/105
- Basis
- BenchAlign v5.7 lane · 11 vs 11 public rows
- Reading
- Directional only
Coding
Directional only- DeepSeek V4 Pro 0813
- 50.3
- Supported · #39/135
- Qwen3.6-35B-A3B
- 36.4
- Estimated · #68/135
- Basis
- BenchAlign v5.7 lane · 15 vs 6 public rows
- Reading
- Directional only
Knowledge
Directional only- DeepSeek V4 Pro 0813
- 63.4
- Estimated · #29/158
- Qwen3.6-35B-A3B
- 42.1
- Estimated · #82/158
- Basis
- BenchAlign v5.7 lane · 8 vs 5 public rows
- Reading
- Directional only
Reasoning
Not comparable- DeepSeek V4 Pro 0813
- 56.9
- Unranked · 4 rankable rows
- Qwen3.6-35B-A3B
- 71.4
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- DeepSeek V4 Pro 0813
- Not ranked
- Qwen3.6-35B-A3B
- 50.0
- #39/50
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- DeepSeek V4 Pro 0813
- Not ranked
- Qwen3.6-35B-A3B
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- DeepSeek V4 Pro 0813
- Not ranked
- Qwen3.6-35B-A3B
- 76.8
- #57/124
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- DeepSeek V4 Pro 0813
- 80.2
- Unranked · 4 rankable rows
- Qwen3.6-35B-A3B
- 70.7
- Unranked · 5 rankable rows
- Basis
- Provisional lane · 1 vs 2 weighted rows
- Reading
- Not comparable
| Category | DeepSeek V4 Pro 0813 | Qwen3.6-35B-A3B | Basis | Reading |
|---|---|---|---|---|
| Agentic | 55.0Supported · #29/105 | 29.6Estimated · #67/105 | Directional onlyBenchAlign v5.7 lane · 11 vs 11 public rows | Directional only |
| Coding | 50.3Supported · #39/135 | 36.4Estimated · #68/135 | Directional onlyBenchAlign v5.7 lane · 15 vs 6 public rows | Directional only |
| Knowledge | 63.4Estimated · #29/158 | 42.1Estimated · #82/158 | Directional onlyBenchAlign v5.7 lane · 8 vs 5 public rows | Directional only |
| Reasoning | 56.9Unranked · 4 rankable rows | 71.4Unranked · 2 rankable rows | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | 50.0#39/50 | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 76.8#57/124 | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 80.2Unranked · 4 rankable rows | 70.7Unranked · 5 rankable rows | Not comparableProvisional lane · 1 vs 2 weighted rows | 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
- DeepSeek V4 Pro 0813
- $0.0033
- Fits in one request
- Qwen3.6-35B-A3B
- API rate not published
- Fits in one request
Qwen3.6-35B-A3B has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- DeepSeek V4 Pro 0813
- $0.07788
- Fits in one request
- Qwen3.6-35B-A3B
- API rate not published
- Fits in one request
Qwen3.6-35B-A3B has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- DeepSeek V4 Pro 0813
- $0.0748
- Fits in one request
- Qwen3.6-35B-A3B
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Qwen3.6-35B-A3B has no comparable published API token rate.
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.
SpecificationDeepSeek V4 Pro 0813Qwen3.6-35B-A3B
Context window
Maximum documented context; output-token limits may be lower.
DeepSeek V4 Pro 0813
Qwen3.6-35B-A3B
262K
API model ID
DeepSeek V4 Pro 0813
deepseek-v4-pro
DeepSeek models and pricingQwen3.6-35B-A3B
Not sourced
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
$0.044 per 1M cached input tokens
DeepSeek: Models & PricingQwen3.6-35B-A3B
No comparable hosted API rate
Documented inputs
DeepSeek V4 Pro 0813
Qwen3.6-35B-A3B
Not sourced
Documented outputs
DeepSeek V4 Pro 0813
Qwen3.6-35B-A3B
Not sourced
Provider availability
DeepSeek V4 Pro 0813
Generally Available · DeepSeek API
DeepSeek models and pricing, V4 Pro continuation footnoteQwen3.6-35B-A3B
Not sourced
Reasoning profile
DeepSeek V4 Pro 0813
Reasoning
Qwen3.6-35B-A3B
Reasoning
Weight access
DeepSeek V4 Pro 0813
Open Weight
Qwen3.6-35B-A3B
Open Weight
License
DeepSeek V4 Pro 0813
Open Weight
Qwen3.6-35B-A3B
Open Weight
Release date
DeepSeek V4 Pro 0813
2026-08-13
Qwen3.6-35B-A3B
2026-04-15
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
- DeepSeek V4 Pro 0813 has the higher public score, 63.48 versus 41.88, and the 90% score intervals do not overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- DeepSeek V4 Pro 0813 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, DeepSeek V4 Pro 0813 or Qwen3.6-35B-A3B?
DeepSeek V4 Pro 0813 has the higher public score, 63.48 versus 41.88, 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, DeepSeek V4 Pro 0813 or Qwen3.6-35B-A3B?
DeepSeek V4 Pro 0813 scores higher for coding on the public lane, 50.3 to 36.4. Qwen3.6-35B-A3B 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, DeepSeek V4 Pro 0813 or Qwen3.6-35B-A3B?
DeepSeek V4 Pro 0813 scores higher for agentic tasks on the public lane, 55 to 29.6. Qwen3.6-35B-A3B 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.
Which costs less, DeepSeek V4 Pro 0813 or Qwen3.6-35B-A3B?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, DeepSeek V4 Pro 0813 or Qwen3.6-35B-A3B?
DeepSeek V4 Pro 0813 has the larger documented context window: 1M, compared with 262K.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence71 rows
Agentic
Terminal-Bench 2.0
DeepSeek V4 Pro 081367.9%SourceQwen3.6-35B-A3B51.5%SourceDeepSeek V4 Pro 0813 leads this result
Terminal-Bench 2.1
DeepSeek V4 Pro 081387.9%SourceQwen3.6-35B-A3B—Not directly comparable
BrowseComp
DeepSeek V4 Pro 081383.4%SourceQwen3.6-35B-A3B—Not directly comparable
HLE w/ tools
DeepSeek V4 Pro 081360.0%SourceQwen3.6-35B-A3B—Not directly comparable
MCP Atlas
DeepSeek V4 Pro 081373.6%SourceQwen3.6-35B-A3B62.8%SourceDeepSeek V4 Pro 0813 leads this result
Toolathlon
DeepSeek V4 Pro 081351.8%SourceQwen3.6-35B-A3B26.9%SourceDeepSeek V4 Pro 0813 leads this result
CyberGym
DeepSeek V4 Pro 081383.3%SourceQwen3.6-35B-A3B—Not directly comparable
Toolathlon-Verified
DeepSeek V4 Pro 081374.1%SourceQwen3.6-35B-A3B—Not directly comparable
Agents' Last Exam
DeepSeek V4 Pro 081325.7%SourceQwen3.6-35B-A3B—Not directly comparable
AutomationBench
DeepSeek V4 Pro 081331.8%SourceQwen3.6-35B-A3B—Not directly comparable
Terminal-Bench 2.1 (Vals)
DeepSeek V4 Pro 081354.7%SourceQwen3.6-35B-A3B—Not directly comparable
Claw-Eval
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B68.7%SourceNot directly comparable
QwenClawBench
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B52.6%SourceNot directly comparable
QwenWebBench
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B1397SourceNot directly comparable
τ³-bench results
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B67.2%SourceNot directly comparable
VITA-Bench
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B35.6%SourceNot directly comparable
DeepPlanning
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B25.9%SourceNot directly comparable
WideResearch
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B60.1%SourceNot directly comparable
Gert Labs
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B42.65%SourceNot directly comparable
Coding
LiveCodeBench Pass@1-COT
DeepSeek V4 Pro 081393.5%SourceQwen3.6-35B-A3B—Not directly comparable
Codeforces
DeepSeek V4 Pro 08133206.0SourceQwen3.6-35B-A3B—Not directly comparable
SWE-bench Verified
DeepSeek V4 Pro 081380.6%SourceQwen3.6-35B-A3B73.4%SourceDeepSeek V4 Pro 0813 leads this result
SWE-bench Pro
DeepSeek V4 Pro 081355.4%SourceQwen3.6-35B-A3B49.5%SourceDeepSeek V4 Pro 0813 leads this result
SWE Multilingual
DeepSeek V4 Pro 081376.2%SourceQwen3.6-35B-A3B67.2%SourceDeepSeek V4 Pro 0813 leads this result
Terminal-Bench 2.0
DeepSeek V4 Pro 081367.9%SourceQwen3.6-35B-A3B51.5%SourceDeepSeek V4 Pro 0813 leads this result
Vibe Code Bench
DeepSeek V4 Pro 081349.93%SourceQwen3.6-35B-A3B—Not directly comparable
Terminal-Bench 2.1
DeepSeek V4 Pro 081387.9%SourceQwen3.6-35B-A3B—Not directly comparable
NL2Repo
DeepSeek V4 Pro 081361.5%SourceQwen3.6-35B-A3B29.4%SourceDeepSeek V4 Pro 0813 leads this result
DeepSWE
DeepSeek V4 Pro 081362.7%SourceQwen3.6-35B-A3B—Not directly comparable
DSBench-FullStack
DeepSeek V4 Pro 081371.1%SourceQwen3.6-35B-A3B—Not directly comparable
DSBench-Hard
DeepSeek V4 Pro 081367.2%SourceQwen3.6-35B-A3B—Not directly comparable
OpenHarmony Bench
DeepSeek V4 Pro 081359.0%SourceQwen3.6-35B-A3B—Not directly comparable
LiveCodeBench (Vals)
DeepSeek V4 Pro 081387.5%SourceQwen3.6-35B-A3B—Not directly comparable
SWE-bench (Vals)
DeepSeek V4 Pro 081396.4%SourceQwen3.6-35B-A3B—Not directly comparable
LiveCodeBench
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B80.4%SourceNot directly comparable
Reasoning
MRCR 1M
DeepSeek V4 Pro 081383.5%SourceQwen3.6-35B-A3B—Not directly comparable
CorpusQA 1M
DeepSeek V4 Pro 081362.0%SourceQwen3.6-35B-A3B—Not directly comparable
ARC-AGI-1
DeepSeek V4 Pro 081390.00%SourceQwen3.6-35B-A3B—Not directly comparable
ARC-AGI-2
DeepSeek V4 Pro 081361.3%SourceQwen3.6-35B-A3B—Not directly comparable
Multimodal
MMMU
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B81.7%SourceNot directly comparable
MMMU-Pro
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B75.3%SourceNot directly comparable
RealWorldQA
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B85.3%SourceNot directly comparable
OmniDocBench 1.5
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B89.9%SourceNot directly comparable
CharXiv
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B78%SourceNot directly comparable
SimpleVQA
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B58.9%SourceNot directly comparable
CC-OCR
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B81.9%SourceNot directly comparable
AI2D_TEST
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B92.7%SourceNot directly comparable
RefCOCO (avg)
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B92.0%SourceNot directly comparable
ODINW13
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B50.8%SourceNot directly comparable
Video-MME (with subtitle)
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B86.6%SourceNot directly comparable
Video-MME (w/o subtitle)
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B82.5%SourceNot directly comparable
VideoMMMU
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B83.7%SourceNot directly comparable
MLVU (M-Avg)
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B86.2%SourceNot directly comparable
Knowledge
MMLU-Pro
DeepSeek V4 Pro 081387.5%SourceQwen3.6-35B-A3B85.2%SourceDeepSeek V4 Pro 0813 leads this result
SimpleQA
DeepSeek V4 Pro 081357.9%SourceQwen3.6-35B-A3B—Not directly comparable
Chinese-SimpleQA
DeepSeek V4 Pro 081384.4%SourceQwen3.6-35B-A3B—Not directly comparable
GPQA
DeepSeek V4 Pro 081390.1%SourceQwen3.6-35B-A3B86%SourceDeepSeek V4 Pro 0813 leads this result
GPQA-D
DeepSeek V4 Pro 081390.1%SourceQwen3.6-35B-A3B—Not directly comparable
HLE
DeepSeek V4 Pro 081342.7%SourceQwen3.6-35B-A3B21.4%SourceDeepSeek V4 Pro 0813 leads this result
GPQA Diamond (Vals)
DeepSeek V4 Pro 081392.4%SourceQwen3.6-35B-A3B—Not directly comparable
MMLU-Pro (Vals)
DeepSeek V4 Pro 081387.0%SourceQwen3.6-35B-A3B—Not directly comparable
SuperGPQA
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B64.7%SourceNot directly comparable
C-Eval
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B90%SourceNot directly comparable
Math
HMMT Feb 2026
DeepSeek V4 Pro 081395.2%SourceQwen3.6-35B-A3B83.6%SourceDeepSeek V4 Pro 0813 leads this result
IMOAnswerBench
DeepSeek V4 Pro 081389.8%SourceQwen3.6-35B-A3B—Not directly comparable
Apex
DeepSeek V4 Pro 081338.3%SourceQwen3.6-35B-A3B—Not directly comparable
Apex Shortlist
DeepSeek V4 Pro 081390.2%SourceQwen3.6-35B-A3B—Not directly comparable
HMMT Feb 2025
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B90.7%SourceNot directly comparable
HMMT Nov 2025
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B89.1%SourceNot directly comparable
MMAnswerBench
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B78.9%SourceNot directly comparable
AIME26
DeepSeek V4 Pro 0813—Qwen3.6-35B-A3B92.7%SourceNot directly comparable
71 public results · 12 shared
Watch DeepSeek V4 Pro 0813 vs Qwen3.6-35B-A3B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.
Last updated September 27, 2026