Coding work
Code generation, repair, and software-engineering tasks
Claude Opus 4.7
Claude Opus 4.7 leads on the public coding lane, 59.5 to 50.3, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Claude Opus 4.7 vs DeepSeek V4 Pro 0813
Updated September 27, 2026. Rank says Claude Opus 4.7 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
Claude Opus 4.7 has the higher public score estimate, 66.28 versus 63.48, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 6 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 6
- Claude Opus 4.7 only
- 8
- DeepSeek V4 Pro 0813 only
- 36
- Like-for-like categories
- 2 / 8
Estimated: Claude Opus 4.7 and DeepSeek V4 Pro 0813How 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.
Agentic work
Tool use, computer use, and multi-step task completion
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 leads on the public agentic lane, 55 to 53.2, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limitedChat 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. Claude Opus 4.7 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallbackRepository 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-ratesLong 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.
59.5Claude Opus 4.750.3DeepSeek V4 Pro 0813
Like-for-like · BenchAlign v5.7
Claude Opus 4.7 leads the like-for-like coding row, although the 90% intervals overlap.
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.
8 Claude Opus 4.7 only
6 Shared
36 DeepSeek V4 Pro 0813 only
1 category rests 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.
MMLU-Pro (Vals)Knowledge
Normalized gap 2.9Claude Opus 4.7:89.9%DeepSeek V4 Pro 0813:87.0%LiveCodeBench (Vals)Coding
Normalized gap 2.4Claude Opus 4.7:85.1%DeepSeek V4 Pro 0813:87.5%
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
Like-for-like- Claude Opus 4.7
- 53.2
- Supported · #32/105
- DeepSeek V4 Pro 0813
- 55.0
- Supported · #29/105
- Basis
- BenchAlign v5.7 lane · 5 vs 11 public rows
- Reading
- DeepSeek V4 Pro 0813 leads · intervals overlap
Coding
Like-for-like- Claude Opus 4.7
- 59.5
- Supported · #18/135
- DeepSeek V4 Pro 0813
- 50.3
- Supported · #39/135
- Basis
- BenchAlign v5.7 lane · 5 vs 15 public rows
- Reading
- Claude Opus 4.7 leads · intervals overlap
Knowledge
Directional only- Claude Opus 4.7
- 63.9
- Estimated · #28/158
- DeepSeek V4 Pro 0813
- 63.4
- Estimated · #29/158
- Basis
- BenchAlign v5.7 lane · 2 vs 8 public rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Opus 4.7
- Not ranked
- DeepSeek V4 Pro 0813
- 56.9
- Unranked · 4 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Opus 4.7
- Not ranked
- DeepSeek V4 Pro 0813
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 4.7
- 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 4.7
- Not ranked
- DeepSeek V4 Pro 0813
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 4.7
- 60.6
- Unranked · 2 rankable rows
- DeepSeek V4 Pro 0813
- 80.2
- Unranked · 4 rankable rows
- Basis
- Provisional lane · 2 vs 1 weighted rows
- Reading
- Not comparable
| Category | Claude Opus 4.7 | DeepSeek V4 Pro 0813 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 53.2Supported · #32/105 | 55.0Supported · #29/105 | Like-for-likeBenchAlign v5.7 lane · 5 vs 11 public rows | DeepSeek V4 Pro 0813 leads · intervals overlap |
| Coding | 59.5Supported · #18/135 | 50.3Supported · #39/135 | Like-for-likeBenchAlign v5.7 lane · 5 vs 15 public rows | Claude Opus 4.7 leads · intervals overlap |
| Knowledge | 63.9Estimated · #28/158 | 63.4Estimated · #29/158 | Directional onlyBenchAlign v5.7 lane · 2 vs 8 public rows | Directional only |
| Reasoning | Not ranked | 56.9Unranked · 4 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multimodal | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 60.6Unranked · 2 rankable rows | 80.2Unranked · 4 rankable rows | Not comparableProvisional lane · 2 vs 1 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
- Claude Opus 4.7
- $0.0175
- Fits in one request
- DeepSeek V4 Pro 0813
- $0.0033
- 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 4.7
- $0.325
- Fits in one request
- DeepSeek V4 Pro 0813
- $0.07788
- 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 4.7
- $1.35
- Fits in one request
- Cached input priced at the published list-input rate
- DeepSeek V4 Pro 0813
- $0.0748
- Fits in one request
DeepSeek V4 Pro 0813 has the lower modeled cost
Claude Opus 4.7 has no published cached-input rate, so cached tokens use its listed input 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.
SpecificationClaude Opus 4.7DeepSeek V4 Pro 0813
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 4.7
DeepSeek V4 Pro 0813
API model ID
Claude Opus 4.7
claude-opus-4-7
Anthropic model ID documentationDeepSeek V4 Pro 0813
deepseek-v4-pro
DeepSeek models and pricingCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 4.7
Not published
DeepSeek V4 Pro 0813
$0.044 per 1M cached input tokens
DeepSeek: Models & PricingDocumented inputs
Claude Opus 4.7
text, image
Anthropic model overviewDeepSeek V4 Pro 0813
Documented outputs
Claude Opus 4.7
DeepSeek V4 Pro 0813
Provider availability
Claude Opus 4.7
Generally Available · Claude API
Anthropic model overviewDeepSeek V4 Pro 0813
Generally Available · DeepSeek API
DeepSeek models and pricing, V4 Pro continuation footnoteReasoning profile
Claude Opus 4.7
Non-Reasoning
DeepSeek V4 Pro 0813
Reasoning
Weight access
Claude Opus 4.7
Proprietary
DeepSeek V4 Pro 0813
Open Weight
License
Claude Opus 4.7
Proprietary
DeepSeek V4 Pro 0813
Open Weight
Release date
Claude Opus 4.7
2026-04-16
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 4.7 has the higher public score estimate, 66.28 versus 63.48, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.325 vs $0.07788. Cache-heavy agent loop: $1.35 vs $0.0748.
- Context tradeoff
- Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Claude Opus 4.7 or DeepSeek V4 Pro 0813?
Claude Opus 4.7 has the higher public score estimate, 66.28 versus 63.48, 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 4.7 or DeepSeek V4 Pro 0813?
Claude Opus 4.7 leads the public coding lane, 59.5 to 50.3, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, Claude Opus 4.7 or DeepSeek V4 Pro 0813?
DeepSeek V4 Pro 0813 leads the public agentic tasks lane, 55 to 53.2, with Supported evidence for both models, although the 90% intervals overlap.
Which costs less, Claude Opus 4.7 or DeepSeek V4 Pro 0813?
For the stated presets, chat costs $0.0175 on Claude Opus 4.7 and $0.0033 on DeepSeek V4 Pro 0813; repository review costs $0.325 and $0.07788; the cache-heavy agent loop costs $1.35 and $0.0748. Claude Opus 4.7 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Opus 4.7 or DeepSeek V4 Pro 0813?
Both models list the same context window, 1M.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence50 rows
Agentic
Gert Labs
Claude Opus 4.765.59%SourceDeepSeek V4 Pro 0813—Not directly comparable
ResearchClawBench
Claude Opus 4.720.7%SourceDeepSeek V4 Pro 0813—Not directly comparable
OSWorld 2.0
Claude Opus 4.713.9%SourceDeepSeek V4 Pro 0813—Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Opus 4.768.5%SourceDeepSeek V4 Pro 081354.7%SourceClaude Opus 4.7 leads this result
ApprenticeBench
Claude Opus 4.77%SourceDeepSeek V4 Pro 0813—Not directly comparable
Terminal-Bench 2.0
Claude Opus 4.7—DeepSeek V4 Pro 081367.9%SourceNot directly comparable
Terminal-Bench 2.1
Claude Opus 4.7—DeepSeek V4 Pro 081387.9%SourceNot directly comparable
BrowseComp
Claude Opus 4.7—DeepSeek V4 Pro 081383.4%SourceNot directly comparable
HLE w/ tools
Claude Opus 4.7—DeepSeek V4 Pro 081360.0%SourceNot directly comparable
MCP Atlas
Claude Opus 4.7—DeepSeek V4 Pro 081373.6%SourceNot directly comparable
Toolathlon
Claude Opus 4.7—DeepSeek V4 Pro 081351.8%SourceNot directly comparable
CyberGym
Claude Opus 4.7—DeepSeek V4 Pro 081383.3%SourceNot directly comparable
Toolathlon-Verified
Claude Opus 4.7—DeepSeek V4 Pro 081374.1%SourceNot directly comparable
Agents' Last Exam
Claude Opus 4.7—DeepSeek V4 Pro 081325.7%SourceNot directly comparable
AutomationBench
Claude Opus 4.7—DeepSeek V4 Pro 081331.8%SourceNot directly comparable
Coding
Vibe Code Bench
Shared sourceClaude Opus 4.771.00%DeepSeek V4 Pro 081349.93%Claude Opus 4.7 leads this result
React Native Evals
Claude Opus 4.782.8%SourceDeepSeek V4 Pro 0813—Not directly comparable
FrontierCode 1.1 Main
Claude Opus 4.738.5%SourceDeepSeek V4 Pro 0813—Not directly comparable
LiveCodeBench (Vals)
Claude Opus 4.785.1%SourceDeepSeek V4 Pro 081387.5%SourceDeepSeek V4 Pro 0813 leads this result
SWE-bench (Vals)
Claude Opus 4.782.0%SourceDeepSeek V4 Pro 081396.4%SourceDeepSeek V4 Pro 0813 leads this result
LiveCodeBench Pass@1-COT
Claude Opus 4.7—DeepSeek V4 Pro 081393.5%SourceNot directly comparable
Codeforces
Claude Opus 4.7—DeepSeek V4 Pro 08133206.0SourceNot directly comparable
SWE-bench Verified
Claude Opus 4.7—DeepSeek V4 Pro 081380.6%SourceNot directly comparable
SWE-bench Pro
Claude Opus 4.7—DeepSeek V4 Pro 081355.4%SourceNot directly comparable
SWE Multilingual
Claude Opus 4.7—DeepSeek V4 Pro 081376.2%SourceNot directly comparable
Terminal-Bench 2.0
Claude Opus 4.7—DeepSeek V4 Pro 081367.9%SourceNot directly comparable
Terminal-Bench 2.1
Claude Opus 4.7—DeepSeek V4 Pro 081387.9%SourceNot directly comparable
NL2Repo
Claude Opus 4.7—DeepSeek V4 Pro 081361.5%SourceNot directly comparable
DeepSWE
Claude Opus 4.7—DeepSeek V4 Pro 081362.7%SourceNot directly comparable
DSBench-FullStack
Claude Opus 4.7—DeepSeek V4 Pro 081371.1%SourceNot directly comparable
DSBench-Hard
Claude Opus 4.7—DeepSeek V4 Pro 081367.2%SourceNot directly comparable
OpenHarmony Bench
Claude Opus 4.7—DeepSeek V4 Pro 081359.0%SourceNot directly comparable
Reasoning
MRCR 1M
Claude Opus 4.7—DeepSeek V4 Pro 081383.5%SourceNot directly comparable
CorpusQA 1M
Claude Opus 4.7—DeepSeek V4 Pro 081362.0%SourceNot directly comparable
ARC-AGI-1
Claude Opus 4.7—DeepSeek V4 Pro 081390.00%SourceNot directly comparable
ARC-AGI-2
Claude Opus 4.7—DeepSeek V4 Pro 081361.3%SourceNot directly comparable
Knowledge
GPQA Diamond (Vals)
Claude Opus 4.790.2%SourceDeepSeek V4 Pro 081392.4%SourceDeepSeek V4 Pro 0813 leads this result
MMLU-Pro (Vals)
Claude Opus 4.789.9%SourceDeepSeek V4 Pro 081387.0%SourceClaude Opus 4.7 leads this result
MMLU-Pro
Claude Opus 4.7—DeepSeek V4 Pro 081387.5%SourceNot directly comparable
SimpleQA
Claude Opus 4.7—DeepSeek V4 Pro 081357.9%SourceNot directly comparable
Chinese-SimpleQA
Claude Opus 4.7—DeepSeek V4 Pro 081384.4%SourceNot directly comparable
GPQA
Claude Opus 4.7—DeepSeek V4 Pro 081390.1%SourceNot directly comparable
GPQA-D
Claude Opus 4.7—DeepSeek V4 Pro 081390.1%SourceNot directly comparable
HLE
Claude Opus 4.7—DeepSeek V4 Pro 081342.7%SourceNot directly comparable
Math
FrontierMath v2 (Tiers 1-3)
Claude Opus 4.743.793%SourceDeepSeek V4 Pro 0813—Not directly comparable
FrontierMath v2 (Tier 4)
Claude Opus 4.722.917%SourceDeepSeek V4 Pro 0813—Not directly comparable
HMMT Feb 2026
Claude Opus 4.7—DeepSeek V4 Pro 081395.2%SourceNot directly comparable
IMOAnswerBench
Claude Opus 4.7—DeepSeek V4 Pro 081389.8%SourceNot directly comparable
Apex
Claude Opus 4.7—DeepSeek V4 Pro 081338.3%SourceNot directly comparable
Apex Shortlist
Claude Opus 4.7—DeepSeek V4 Pro 081390.2%SourceNot directly comparable
50 public results · 6 shared
Watch Claude Opus 4.7 vs DeepSeek V4 Pro 0813
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