Model profile
DeepSeek V4 Pro
Evidence coverage
23 of 323 tracked benchmarks are published. 22 are verified and 1 provisional. 6 of 8 categories are measured.
- Published / tracked
- 23 / 323
- Verified
- 22
- Provisional
- 1
- Categories with evidence
- 6 / 8
Evidence by category
- Agentic6 benchmarksVerified
- Coding4 benchmarksVerified
- Reasoning2 benchmarksVerified
- Knowledge6 benchmarksVerified
- Math4 benchmarksVerified
- Multilingual0 benchmarksNot measured
- Multimodal1 benchmarkReported
- Inst. Following0 benchmarksNot measured
DeepSeek V4 Pro ranks #46 out of 200 models on the public leaderboard with an overall score of 60.66/100. It also ranks #35 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.
DeepSeek V4 Pro 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 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 Base, DeepSeek V4 Flash Base, DeepSeek V4 Flash. This profile currently has 23 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 (#51), while its weakest is Coding (#99). 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 60.42–60.89
- GPT-5.4 ProOpenAICompare#4460.89GPT-5.4 Pro is #44 with a score of 60.89.
- Qwen3.5-27BAlibabaCompare#4560.7Qwen3.5-27B is #45 with a score of 60.7.
- DeepSeek V4 ProCurrent modelDeepSeek#4660.66DeepSeek V4 Pro is #46 with a score of 60.66.
- Qwen3.5-122B-A10BAlibabaCompare#4760.56Qwen3.5-122B-A10B is #47 with a score of 60.56.
- Grok 4.1 Fast (Reasoning)xAICompare#4860.51Grok 4.1 Fast (Reasoning) is #48 with a score of 60.51.
- Gemini 3 FlashGoogleCompare#4960.49Gemini 3 Flash is #49 with a score of 60.49.
- Grok 4xAICompare#5060.42Grok 4 is #50 with a score of 60.42.
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.
- Knowledge2%Eligible cohort rank #51 of 52Category score 43.8
- Agentic31%Eligible cohort rank #82 of 119Category score 43.8
- Coding19%Eligible cohort rank #99 of 122Category score 43.5
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 |
|---|---|---|---|---|---|---|
| AgenticRank #82 of 119Percentile 31stWeight 22%6 benchmarksVerified | 43.8 | #82 of 119 | 31st | 22% | 6 benchmarks | Verified |
| CodingRank #99 of 122Percentile 19thWeight 20%4 benchmarksVerified | 43.5 | #99 of 122 | 19th | 20% | 4 benchmarks | Verified |
| ReasoningWeight 17%2 benchmarksVerified | Score pending | Not ranked | Not available | 17% | 2 benchmarks | Verified |
| KnowledgeRank #51 of 52Percentile 2ndWeight 12%6 benchmarksVerified | 43.8 | #51 of 52 | 2nd | 12% | 6 benchmarks | Verified |
| MathRank Not rankedWeight 5%4 benchmarksVerified | 18.1 | Not ranked | Not available | 5% | 4 benchmarks | Verified |
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | Not ranked | Not available | 7% | 0 benchmarks | Not measured |
| MultimodalWeight 12%1 benchmarkReported | Score pending | Not ranked | Not available | 12% | 1 benchmark | Reported |
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
Chatbot Arena performance
Scroll horizontally to inspect confidence intervals and vote counts.
| View | Elo | Confidence interval | Votes |
|---|---|---|---|
| Text Overall | 1457 | ±4.4 | 44,418 |
| Coding | 1501 | ±6.7 | 13,142 |
| Math | 1444 | ±12.5 | 2,392 |
| Instruction Following | 1453 | ±6.3 | 14,929 |
| Creative Writing | 1444 | ±8.2 | 7,179 |
| Multi-turn | 1473 | ±7.8 | 8,027 |
| Hard Prompts | 1480 | ±5.2 | 29,323 |
| Hard Prompts (English) | 1483 | ±6.5 | 14,187 |
| Longer Query | 1473 | ±6.1 | 19,139 |
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.
Agentic6 benchmarks
Gert Labs Composite Game Benchmark
Coding4 benchmarks
Software Engineering Benchmark Verified
Reasoning2 benchmarks
Knowledge6 benchmarks
Humanity's Last Exam
Massive Multitask Language Understanding Professional
Measuring Short-Form Factuality in Large Language Models
Graduate-Level Google-Proof Q&A
GPQA Diamond
Math4 benchmarks
Harvard-MIT Mathematics Tournament February 2026
Multimodal1 benchmark
Design Arena Website Elo
Frequently Asked Questions
How does DeepSeek V4 Pro perform overall in AI benchmarks?
DeepSeek V4 Pro currently ranks #46 out of 200 models on BenchLM's provisional leaderboard with an overall score of 60.66. It also ranks #35 out of 99 on the verified leaderboard. It is created by DeepSeek. Its published context window is 1M.
Is DeepSeek V4 Pro good for knowledge and understanding?
DeepSeek V4 Pro ranks #51 out of 52 models in knowledge and understanding benchmarks with an average score of 43.8. There are stronger options in this category.
Is DeepSeek V4 Pro good for coding and programming?
DeepSeek V4 Pro ranks #99 out of 122 models in coding and programming benchmarks with an average score of 43.5. There are stronger options in this category.
Is DeepSeek V4 Pro good for mathematics?
DeepSeek V4 Pro has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.
Is DeepSeek V4 Pro good for reasoning and logic?
DeepSeek V4 Pro has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.
Is DeepSeek V4 Pro good for agentic tool use and computer tasks?
DeepSeek V4 Pro ranks #82 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 43.8. There are stronger options in this category.
Is DeepSeek V4 Pro good for multimodal and grounded tasks?
DeepSeek V4 Pro has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.
Is DeepSeek V4 Pro open source?
Yes, DeepSeek V4 Pro 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?
DeepSeek V4 Pro 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 Base, DeepSeek V4 Flash Base, DeepSeek V4 Flash.
Does DeepSeek V4 Pro have full benchmark coverage on BenchLM?
Not yet. DeepSeek V4 Pro currently has 23 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?
DeepSeek V4 Pro 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.