Skip to main content

Model profile

DeepSeek V3.1

DeepSeekEstablishedReleased Aug 21, 2025
Data verified
Overall Score
53.64Public #95 of 200Verified #53 of 99
Arena Elo
1418
Eligible category ranks
0of 8
Price (1M tokens)
$0 in / $0 out
API pricing
Speed
Not listed
Context
128K

Evidence coverage

12 of 321 tracked benchmarks are published. 0 are verified and 12 provisional. 6 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
12 / 321
Verified
0
Provisional
12
Categories with evidence
6 / 8

Evidence by category

  • Agentic1 benchmark
    Reported
  • Coding1 benchmark
    Reported
  • Reasoning2 benchmarks
    Reported
  • Knowledge6 benchmarks
    Reported
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal1 benchmark
    Reported
  • Inst. Following1 benchmark
    Reported
Open WeightSelf-hostNon-Reasoning
Confidence:
Low
base

DeepSeek V3.1 ranks #95 out of 200 models on the public leaderboard with an overall score of 53.64/100. It also ranks #53 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

DeepSeek V3.1 is a open weight model with a 128K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

DeepSeek V3.1 sits inside the DeepSeek V3.1 family alongside DeepSeek V3.1 (Reasoning). This profile currently has 12 of 321 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

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 53.4354.06

  1. MiMo-V2-Flash
    Xiaomi
    #9154.06
    MiMo-V2-Flash is #91 with a score of 54.06.
    Compare
  2. DeepSeek V4 Flash (High)
    DeepSeek
    #9253.95
    DeepSeek V4 Flash (High) is #92 with a score of 53.95.
    Compare
  3. Qwen3.6-27B
    Alibaba
    #9353.82
    Qwen3.6-27B is #93 with a score of 53.82.
    Compare
  4. GPT-5.1
    OpenAI
    #9453.65
    GPT-5.1 is #94 with a score of 53.65.
    Compare
  5. DeepSeek V3.1Current model
    DeepSeek
    #9553.64
    DeepSeek V3.1 is #95 with a score of 53.64.
  6. Claude Sonnet 4.5
    Anthropic
    #9653.61
    Claude Sonnet 4.5 is #96 with a score of 53.61.
    Compare
  7. DeepSeek V3.1 (Reasoning)
    DeepSeek
    #9753.43
    DeepSeek V3.1 (Reasoning) is #97 with a score of 53.43.
    Compare

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.

No eligible category percentile is available from the published evidence yet.

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank Not rankedWeight 22%1 benchmarkReported33.2
CodingRank Not rankedWeight 20%1 benchmarkReported14.5
ReasoningRank Not rankedWeight 17%2 benchmarksReported46.9
KnowledgeRank Not rankedWeight 12%6 benchmarksReported24.5
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank Not rankedWeight 12%1 benchmarkReported39.0
Inst. FollowingRank Not rankedWeight 5%1 benchmarkReported67.0

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1418±6.014,948
Coding1448±11.62,623
Math1415±18.3991
Instruction Following1404±9.83,691
Creative Writing1389±13.32,003
Multi-turn1406±11.82,483
Hard Prompts1433±7.86,802
Hard Prompts (English)1435±10.23,357
Longer Query1421±10.53,213

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.

Agentic1 benchmark
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

34.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Coding1 benchmark
AA-SciCodeReported

Artificial Analysis SciCode

36.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

45.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

0.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge6 benchmarks
Artificial Analysis Intelligence IndexReported
21.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

73.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

6.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-41.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

23.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

83.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Multimodal1 benchmark
Design Arena WebsiteReported

Design Arena Website Elo

1155Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

37.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.

DeepSeek V3.1 Family

Base entry

Frequently Asked Questions

How does DeepSeek V3.1 perform overall in AI benchmarks?

DeepSeek V3.1 has 12 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is DeepSeek V3.1 good for knowledge and understanding?

DeepSeek V3.1 has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek V3.1 good for coding and programming?

DeepSeek V3.1 has visible benchmark coverage in coding and programming, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek V3.1 good for reasoning and logic?

DeepSeek V3.1 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek V3.1 good for agentic tool use and computer tasks?

DeepSeek V3.1 has visible benchmark coverage in agentic tool use and computer tasks, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek V3.1 good for multimodal and grounded tasks?

DeepSeek V3.1 has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek V3.1 good for instruction following?

DeepSeek V3.1 has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Is DeepSeek V3.1 open source?

Yes, DeepSeek V3.1 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 V3.1?

DeepSeek V3.1 belongs to the DeepSeek V3.1 family. Related variants on BenchLM include DeepSeek V3.1 (Reasoning).

Does DeepSeek V3.1 have full benchmark coverage on BenchLM?

Not yet. DeepSeek V3.1 currently has 12 published benchmark scores out of the 321 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 V3.1?

DeepSeek V3.1 has a published context window of 128K, which determines how much text it can process in a single interaction.

Last updated: July 20, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

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.