Agentic
Like-for-like- DeepSeek V4 Pro 0813
- 74.5
- GPT-5.6 Terra
- 87.4
- Weighted basis
- 2 vs 2 rows
- Reading
- GPT-5.6 Terra leads
DeepSeek V4 Pro 0813 vs GPT-5.6 Terra
Updated August 13, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
GPT-5.6 Terra has the higher public score estimate, 72.55 versus 60.93, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
9 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
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
GPT-5.6 Terra
GPT-5.6 Terra leads on the same 2 weighted benchmark rows.
Confidence: limited
Long documents
Prompts that approach the documented context limit
GPT-5.6 Terra
GPT-5.6 Terra has the larger documented context window.
Confidence: documented
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
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
25 DeepSeek V4 Pro 0813 only
9 Shared
15 GPT-5.6 Terra only
- Shared results
- 9
- DeepSeek V4 Pro 0813 only
- 25
- GPT-5.6 Terra only
- 15
- Like-for-like categories
- 1 / 8
2 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Coding
Directional only- DeepSeek V4 Pro 0813
- 70.9
- GPT-5.6 Terra
- 63.4
- Weighted basis
- 2 vs 1 rows
- Reading
- Directional only
Knowledge
Directional only- DeepSeek V4 Pro 0813
- 62.5
- GPT-5.6 Terra
- 92.9
- Weighted basis
- 4 vs 1 rows
- Reading
- Directional only
Reasoning
Not comparable- DeepSeek V4 Pro 0813
- Not measured
- GPT-5.6 Terra
- 83.9
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Math
Not comparable- DeepSeek V4 Pro 0813
- 95.2
- GPT-5.6 Terra
- 80.8
- Weighted basis
- 1 vs 2 rows
- Reading
- Not comparable
Multilingual
Not comparable- DeepSeek V4 Pro 0813
- Not measured
- GPT-5.6 Terra
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- DeepSeek V4 Pro 0813
- Not measured
- GPT-5.6 Terra
- 80.7
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Instruction following
Not comparable- DeepSeek V4 Pro 0813
- Not measured
- GPT-5.6 Terra
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | DeepSeek V4 Pro 0813 | GPT-5.6 Terra | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 74.5 | 87.4 | Like-for-like2 vs 2 rows | GPT-5.6 Terra leads |
| Coding | 70.9 | 63.4 | Directional only2 vs 1 rows | Directional only |
| Knowledge | 62.5 | 92.9 | Directional only4 vs 1 rows | Directional only |
| Reasoning | Not measured | 83.9 | Not comparable0 vs 1 rows | Not comparable |
| Math | 95.2 | 80.8 | Not comparable1 vs 2 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | 80.7 | Not comparable0 vs 1 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
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.
Terminal-Bench 2.0
Agentic
DeepSeek V4 Pro 0813: 67.9%GPT-5.6 Terra: 87.4%Normalized gap 19.5DeepSeek V4 Pro 0813 source GPT-5.6 Terra sourceSWE-bench Pro
Coding
DeepSeek V4 Pro 0813: 55.4%GPT-5.6 Terra: 63.4%Normalized gap 8.0DeepSeek V4 Pro 0813 source GPT-5.6 Terra sourceBrowseComp
Agentic
DeepSeek V4 Pro 0813: 83.4%GPT-5.6 Terra: 87.5%Normalized gap 4.1DeepSeek V4 Pro 0813 source GPT-5.6 Terra sourceGPQA
Knowledge
DeepSeek V4 Pro 0813: 90.1%GPT-5.6 Terra: 92.9%Normalized gap 2.8DeepSeek V4 Pro 0813 source GPT-5.6 Terra source
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-5.6 Terra
- $0.008
- 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-5.6 Terra
- $0.136
- 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-5.6 Terra
- $0.2
- 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.
SpecificationDeepSeek V4 Pro 0813GPT-5.6 Terra
Context window
Maximum documented context; output-token limits may be lower.
DeepSeek V4 Pro 0813
GPT-5.6 Terra
1.05M
OpenAI model catalogAPI model ID
DeepSeek V4 Pro 0813
deepseek-v4-pro
DeepSeek models and pricingGPT-5.6 Terra
gpt-5.6-terra
OpenAI model catalogCached-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-5.6 Terra
$0.2 per 1M cached input tokens
OpenAI pricingDocumented inputs
DeepSeek V4 Pro 0813
GPT-5.6 Terra
text, image
OpenAI model catalogDocumented outputs
DeepSeek V4 Pro 0813
GPT-5.6 Terra
Provider availability
DeepSeek V4 Pro 0813
Generally Available · DeepSeek API
DeepSeek models and pricingGPT-5.6 Terra
Generally Available · OpenAI Responses API
OpenAI model catalogReasoning profile
DeepSeek V4 Pro 0813
Reasoning
GPT-5.6 Terra
Reasoning
Weight access
DeepSeek V4 Pro 0813
Proprietary
GPT-5.6 Terra
Proprietary
License
DeepSeek V4 Pro 0813
Proprietary
GPT-5.6 Terra
Proprietary
Release date
DeepSeek V4 Pro 0813
2026-08-13
GPT-5.6 Terra
2026-07-09
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-5.6 Terra has the higher public score estimate, 72.55 versus 60.93, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.02436 vs $0.136. Cache-heavy agent loop: $0.01812 vs $0.2.
- Context tradeoff
- GPT-5.6 Terra has the larger documented window (1.05M).
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 evidence49 rows
Agentic
Terminal-Bench 2.0
DeepSeek V4 Pro 081367.9%SourceGPT-5.6 Terra87.4%SourceGPT-5.6 Terra leads this result
Terminal-Bench 2.1
DeepSeek V4 Pro 081387.9%SourceGPT-5.6 Terra—Not directly comparable
BrowseComp
DeepSeek V4 Pro 081383.4%SourceGPT-5.6 Terra87.5%SourceGPT-5.6 Terra leads this result
HLE w/ tools
DeepSeek V4 Pro 081360.0%SourceGPT-5.6 Terra—Not directly comparable
MCP Atlas
DeepSeek V4 Pro 081373.6%SourceGPT-5.6 Terra—Not directly comparable
Toolathlon
DeepSeek V4 Pro 081351.8%SourceGPT-5.6 Terra53.1%SourceGPT-5.6 Terra leads this result
CyberGym
DeepSeek V4 Pro 081383.3%SourceGPT-5.6 Terra81.8%SourceDeepSeek V4 Pro 0813 leads this result
Toolathlon-Verified
DeepSeek V4 Pro 081374.1%SourceGPT-5.6 Terra—Not directly comparable
Agents' Last Exam
DeepSeek V4 Pro 081325.7%SourceGPT-5.6 Terra—Not directly comparable
AutomationBench
DeepSeek V4 Pro 081331.8%SourceGPT-5.6 Terra—Not directly comparable
Terminal-Bench 3.0
DeepSeek V4 Pro 0813—GPT-5.6 Terra20.8%SourceNot directly comparable
OSWorld 2.0
DeepSeek V4 Pro 0813—GPT-5.6 Terra50.2%SourceNot directly comparable
ExploitGym
DeepSeek V4 Pro 0813—GPT-5.6 Terra23.2%SourceNot directly comparable
Coding
LiveCodeBench Pass@1-COT
DeepSeek V4 Pro 081393.5%SourceGPT-5.6 Terra—Not directly comparable
Codeforces
DeepSeek V4 Pro 08133206.0SourceGPT-5.6 Terra—Not directly comparable
SWE-bench Verified
DeepSeek V4 Pro 081380.6%SourceGPT-5.6 Terra—Not directly comparable
SWE-bench Pro
DeepSeek V4 Pro 081355.4%SourceGPT-5.6 Terra63.4%SourceGPT-5.6 Terra leads this result
SWE Multilingual
DeepSeek V4 Pro 081376.2%SourceGPT-5.6 Terra—Not directly comparable
Terminal-Bench 2.0
DeepSeek V4 Pro 081367.9%SourceGPT-5.6 Terra87.4%SourceGPT-5.6 Terra leads this result
Vibe Code Bench
DeepSeek V4 Pro 081349.93%SourceGPT-5.6 Terra—Not directly comparable
Terminal-Bench 2.1
DeepSeek V4 Pro 081387.9%SourceGPT-5.6 Terra—Not directly comparable
NL2Repo
DeepSeek V4 Pro 081361.5%SourceGPT-5.6 Terra—Not directly comparable
deepSwe
DeepSeek V4 Pro 081362.7%SourceGPT-5.6 Terra69.6%SourceGPT-5.6 Terra leads this result
DSBench-FullStack
DeepSeek V4 Pro 081371.1%SourceGPT-5.6 Terra—Not directly comparable
DSBench-Hard
DeepSeek V4 Pro 081367.2%SourceGPT-5.6 Terra—Not directly comparable
FrontierCode 1.1 Extended
DeepSeek V4 Pro 0813—GPT-5.6 Terra55.8%SourceNot directly comparable
cursorBench32
DeepSeek V4 Pro 0813—GPT-5.6 Terra64.9%SourceNot directly comparable
EEBench
DeepSeek V4 Pro 0813—GPT-5.6 Terra30.8%SourceNot directly comparable
Reasoning
MRCR 1M
DeepSeek V4 Pro 081383.5%SourceGPT-5.6 Terra—Not directly comparable
CorpusQA 1M
DeepSeek V4 Pro 081362.0%SourceGPT-5.6 Terra—Not directly comparable
ARC-AGI-2
DeepSeek V4 Pro 0813—GPT-5.6 Terra83.9%SourceNot directly comparable
ARC-AGI-3
DeepSeek V4 Pro 0813—GPT-5.6 Terra0.8%SourceNot directly comparable
Knowledge
MMLU-Pro
DeepSeek V4 Pro 081387.5%SourceGPT-5.6 Terra—Not directly comparable
SimpleQA
DeepSeek V4 Pro 081357.9%SourceGPT-5.6 Terra—Not directly comparable
Chinese-SimpleQA
DeepSeek V4 Pro 081384.4%SourceGPT-5.6 Terra—Not directly comparable
GPQA
DeepSeek V4 Pro 081390.1%SourceGPT-5.6 Terra92.9%SourceGPT-5.6 Terra leads this result
GPQA-D
DeepSeek V4 Pro 081390.1%SourceGPT-5.6 Terra92.9%SourceGPT-5.6 Terra leads this result
HLE
DeepSeek V4 Pro 081342.7%SourceGPT-5.6 Terra—Not directly comparable
HealthBench Professional
DeepSeek V4 Pro 0813—GPT-5.6 Terra57.7%SourceNot directly comparable
HealthBench Hard
DeepSeek V4 Pro 0813—GPT-5.6 Terra32.7%SourceNot directly comparable
Math
HMMT Feb 2026
DeepSeek V4 Pro 081395.2%SourceGPT-5.6 Terra—Not directly comparable
IMOAnswerBench
DeepSeek V4 Pro 081389.8%SourceGPT-5.6 Terra—Not directly comparable
Apex
DeepSeek V4 Pro 081338.3%SourceGPT-5.6 Terra—Not directly comparable
Apex Shortlist
DeepSeek V4 Pro 081390.2%SourceGPT-5.6 Terra—Not directly comparable
FrontierMath (legacy)
DeepSeek V4 Pro 0813—GPT-5.6 Terra84.9%SourceNot directly comparable
FrontierMath v2 (Tiers 1-3)
DeepSeek V4 Pro 0813—GPT-5.6 Terra84.900%SourceNot directly comparable
FrontierMath v2 (Tier 4)
DeepSeek V4 Pro 0813—GPT-5.6 Terra68.300%SourceNot directly comparable
Multimodal
Frequently asked questions
Which is better, DeepSeek V4 Pro 0813 or GPT-5.6 Terra?
GPT-5.6 Terra has the higher public score estimate, 72.55 versus 60.93, 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-5.6 Terra?
The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. 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 GPT-5.6 Terra?
GPT-5.6 Terra leads the like-for-like agentic tasks comparison across 2 shared weighted benchmark rows.
Which costs less, DeepSeek V4 Pro 0813 or GPT-5.6 Terra?
For the stated presets, chat costs $0.00087 on DeepSeek V4 Pro 0813 and $0.008 on GPT-5.6 Terra; repository review costs $0.02436 and $0.136; the cache-heavy agent loop costs $0.01812 and $0.2. Costs use the listed standard API rates.
Which has the larger context window, DeepSeek V4 Pro 0813 or GPT-5.6 Terra?
GPT-5.6 Terra has the larger documented context window: 1.05M, compared with 1M.
Related comparisons
Last updated August 13, 2026
Watch DeepSeek V4 Pro 0813 vs GPT-5.6 Terra
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.