Model profile
DeepSeek V4 Pro Base
Evidence coverage
24 of 323 tracked benchmarks are published. 24 are verified and 0 provisional. 5 of 8 categories are measured.
- Published / tracked
- 24 / 323
- Verified
- 24
- Provisional
- 0
- Categories with evidence
- 5 / 8
Evidence by category
- Agentic0 benchmarksNot measured
- Coding2 benchmarksVerified
- Reasoning6 benchmarksVerified
- Knowledge12 benchmarksVerified
- Math3 benchmarksVerified
- Multilingual1 benchmarkVerified
- Multimodal0 benchmarksNot measured
- Inst. Following0 benchmarksNot measured
BenchLM is tracking DeepSeek V4 Pro Base, but this profile is currently excluded from the public leaderboard because it still lacks enough non-generated benchmark coverage to rank safely. Only non-generated public benchmark rows appear below.
DeepSeek V4 Pro Base is a open weight model with a 1M token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.
DeepSeek V4 Pro Base sits inside the DeepSeek V4 family alongside DeepSeek V4 Pro (Max), DeepSeek V4 Pro (High), DeepSeek V4 Flash (Max), DeepSeek V4 Flash (High), DeepSeek V4 Pro, DeepSeek V4 Flash Base, DeepSeek V4 Flash. This profile currently has 24 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.
Its strongest category is Knowledge (#28). This performance profile makes it particularly effective for knowledge-intensive tasks like research, analysis, and factual Q&A.
Peer position
Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.
Range 77.44–83.93
- Claude Mythos 5AnthropicCompare#183.93Claude Mythos 5 is #1 with a score of 83.93.
- Claude Fable 5AnthropicCompare#283.68Claude Fable 5 is #2 with a score of 83.68.
- GPT-5.6 SolOpenAICompare#381.96GPT-5.6 Sol is #3 with a score of 81.96.
- Kimi K3Moonshot AICompare#480.96Kimi K3 is #4 with a score of 80.96.
- Claude Opus 4.8AnthropicCompare#578.34Claude Opus 4.8 is #5 with a score of 78.34.
- Muse Spark 1.1MetaCompare#677.44Muse Spark 1.1 is #6 with a score of 77.44.
- DeepSeek V4 Pro BaseCurrent modelDeepSeekUnrankedNot measuredDeepSeek V4 Pro Base is Unranked with a score of Not measured.
Category percentile
More
Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.
- Knowledge47%Eligible cohort rank #28 of 52Category score 70.7
Category evidence
Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticWeight 22%0 benchmarksNot measured | Not measured | Not ranked | Not available | 22% | 0 benchmarks | Not measured |
| CodingWeight 20%2 benchmarksVerified | Score pending | Not ranked | Not available | 20% | 2 benchmarks | Verified |
| ReasoningRank Not rankedWeight 17%6 benchmarksVerified | 45.8 | Not ranked | Not available | 17% | 6 benchmarks | Verified |
| KnowledgeRank #28 of 52Percentile 47thWeight 12%12 benchmarksVerified | 70.7 | #28 of 52 | 47th | 12% | 12 benchmarks | Verified |
| MathWeight 5%3 benchmarksVerified | Score pending | Not ranked | Not available | 5% | 3 benchmarks | Verified |
| MultilingualWeight 7%1 benchmarkVerified | Score pending | Not ranked | Not available | 7% | 1 benchmark | Verified |
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | Not ranked | Not available | 12% | 0 benchmarks | Not measured |
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
Benchmark Details
Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.
Coding2 benchmarks
Evaluating Large Language Models Trained on Code
Reasoning6 benchmarks
BIG-Bench Hard
Discrete Reasoning Over Paragraphs
Knowledge12 benchmarks
Massive Multitask Language Understanding Professional
Measuring Short-Form Factuality in Large Language Models
SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines
Massive Multitask Language Understanding
Chinese Massive Multitask Language Understanding
Math3 benchmarks
Grade School Math 8K
Multilingual1 benchmark
Multilingual Grade School Math
Frequently Asked Questions
How does DeepSeek V4 Pro Base perform overall in AI benchmarks?
DeepSeek V4 Pro Base has 24 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.
Is DeepSeek V4 Pro Base good for knowledge and understanding?
DeepSeek V4 Pro Base ranks #28 out of 52 models in knowledge and understanding benchmarks with an average score of 70.7. There are stronger options in this category.
Is DeepSeek V4 Pro Base good for coding and programming?
DeepSeek V4 Pro Base has visible benchmark coverage in coding and programming, but BenchLM does not currently assign it a global category rank there.
Is DeepSeek V4 Pro Base good for mathematics?
DeepSeek V4 Pro Base has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.
Is DeepSeek V4 Pro Base good for reasoning and logic?
DeepSeek V4 Pro Base has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.
Is DeepSeek V4 Pro Base good for multilingual tasks?
DeepSeek V4 Pro Base has visible benchmark coverage in multilingual tasks, but BenchLM does not currently assign it a global category rank there.
Is DeepSeek V4 Pro Base open source?
Yes, DeepSeek V4 Pro Base is an open weight model created by DeepSeek, meaning it can be downloaded and run locally or fine-tuned for specific use cases.
Which sibling models are related to DeepSeek V4 Pro Base?
DeepSeek V4 Pro Base belongs to the DeepSeek V4 family. Related variants on BenchLM include DeepSeek V4 Pro (Max), DeepSeek V4 Pro (High), DeepSeek V4 Flash (Max), DeepSeek V4 Flash (High), DeepSeek V4 Pro, DeepSeek V4 Flash Base, DeepSeek V4 Flash.
Does DeepSeek V4 Pro Base have full benchmark coverage on BenchLM?
Not yet. DeepSeek V4 Pro Base currently has 24 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.
What is the context window size of DeepSeek V4 Pro Base?
DeepSeek V4 Pro Base has a published context window of 1M, which determines how much text it can process in a single interaction.
Related Resources
Choose with this week’s evidence
Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.
Free. One email per week.