Model profile
DeepSeek V4 Pro (Max)
Evidence coverage
48 of 323 tracked benchmarks are published. 24 are verified and 24 provisional. 7 of 8 categories are measured.
- Published / tracked
- 48 / 323
- Verified
- 24
- Provisional
- 24
- Categories with evidence
- 7 / 8
Evidence by category
- Agentic17 benchmarksMixed evidence
- Coding8 benchmarksMixed evidence
- Reasoning4 benchmarksMixed evidence
- Knowledge13 benchmarksMixed evidence
- Math4 benchmarksVerified
- Multilingual0 benchmarksNot measured
- Multimodal1 benchmarkReported
- Inst. Following1 benchmarkReported
BenchLM is tracking DeepSeek V4 Pro (Max), 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 (Max) is a open weight model with a 1M token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.
DeepSeek V4 Pro (Max) sits inside the DeepSeek V4 family alongside DeepSeek V4 Pro (High), DeepSeek V4 Flash (Max), DeepSeek V4 Flash (High), DeepSeek V4 Pro, DeepSeek V4 Pro Base, DeepSeek V4 Flash Base, DeepSeek V4 Flash. This profile currently has 48 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 (#21), while its weakest is Coding (#58). 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 (Max)Current modelDeepSeekUnrankedNot measuredDeepSeek V4 Pro (Max) 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.
- Knowledge61%Eligible cohort rank #21 of 52Category score 73.5
- Agentic78%Eligible cohort rank #27 of 119Category score 53.9
- Coding53%Eligible cohort rank #58 of 122Category score 51.4
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 #27 of 119Percentile 78thWeight 22%17 benchmarksMixed sources | 53.9 | #27 of 119 | 78th | 22% | 17 benchmarks | Mixed sources |
| CodingRank #58 of 122Percentile 53rdWeight 20%8 benchmarksMixed sources | 51.4 | #58 of 122 | 53rd | 20% | 8 benchmarks | Mixed sources |
| ReasoningWeight 17%4 benchmarksMixed sources | Score pending | Not ranked | Not available | 17% | 4 benchmarks | Mixed sources |
| KnowledgeRank #21 of 52Percentile 61stWeight 12%13 benchmarksMixed sources | 73.5 | #21 of 52 | 61st | 12% | 13 benchmarks | Mixed sources |
| MathRank Not rankedWeight 5%4 benchmarksVerified | 82.0 | 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%1 benchmarkReported | Score pending | Not ranked | Not available | 5% | 1 benchmark | Reported |
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.
Agentic17 benchmarks
Humanity's Last Exam with tools
Artificial Analysis Agentic Index
τ²-Bench Tool-Agent-User Evaluation
GDPval-AA normalized
Artificial Analysis Briefcase
Artificial Analysis EnterpriseOps-Gym
Artificial Analysis Harvey LAB-AA
Artificial Analysis ITBench-AA
Artificial Analysis Tau3-Banking
Coding8 benchmarks
Software Engineering Benchmark Verified
Codeforces Rating
Vibe Code Bench v1.1
Artificial Analysis Coding Index
Artificial Analysis SciCode
Reasoning4 benchmarks
Artificial Analysis Long Context Reasoning
Critical Physics Tasks
Knowledge13 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
Artificial Analysis GPQA Diamond
Artificial Analysis Humanity's Last Exam
Artificial Analysis Omniscience Index
Artificial Analysis Omniscience Accuracy
Artificial Analysis Omniscience Hallucination Rate
Artificial Analysis Openness Index
Math4 benchmarks
Harvard-MIT Mathematics Tournament February 2026
Multimodal1 benchmark
Design Arena Website Elo
Inst. Following1 benchmark
Artificial Analysis IFBench
Frequently Asked Questions
How does DeepSeek V4 Pro (Max) perform overall in AI benchmarks?
DeepSeek V4 Pro (Max) has 48 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 (Max) good for knowledge and understanding?
DeepSeek V4 Pro (Max) ranks #21 out of 52 models in knowledge and understanding benchmarks with an average score of 73.5. There are stronger options in this category.
Is DeepSeek V4 Pro (Max) good for coding and programming?
DeepSeek V4 Pro (Max) ranks #58 out of 122 models in coding and programming benchmarks with an average score of 51.4. There are stronger options in this category.
Is DeepSeek V4 Pro (Max) good for mathematics?
DeepSeek V4 Pro (Max) has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.
Is DeepSeek V4 Pro (Max) good for reasoning and logic?
DeepSeek V4 Pro (Max) has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.
Is DeepSeek V4 Pro (Max) good for agentic tool use and computer tasks?
DeepSeek V4 Pro (Max) ranks #27 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 53.9. There are stronger options in this category.
Is DeepSeek V4 Pro (Max) good for multimodal and grounded tasks?
DeepSeek V4 Pro (Max) 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 (Max) good for instruction following?
DeepSeek V4 Pro (Max) has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.
Is DeepSeek V4 Pro (Max) open source?
Yes, DeepSeek V4 Pro (Max) 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 (Max)?
DeepSeek V4 Pro (Max) belongs to the DeepSeek V4 family. Related variants on BenchLM include DeepSeek V4 Pro (High), DeepSeek V4 Flash (Max), DeepSeek V4 Flash (High), DeepSeek V4 Pro, DeepSeek V4 Pro Base, DeepSeek V4 Flash Base, DeepSeek V4 Flash.
Does DeepSeek V4 Pro (Max) have full benchmark coverage on BenchLM?
Not yet. DeepSeek V4 Pro (Max) currently has 48 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 (Max)?
DeepSeek V4 Pro (Max) 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.