Skip to main content
BenchLM
Data

Data as of October 17, 2026 · How the score is built

EstablishedOpen WeightNon-Reasoning

Released Aug 21, 2025128K context

DeepSeek V3.1

Decision readingDeepSeek V3.1 scores 40.8 out of 100 and ranks #137 of 224. This profile shows 6 source-displayable benchmark rows; its strongest eligible category is Knowledge at #121. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.

Released Aug 21, 2025 — see all recent releases

Find alternativesCompare DeepSeek V3.1
Share or export
Share on XLinkedIn
Social cardBenchmarks CSVAPI/MCP query guide

Decision snapshot

Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.

Capability

40.8/100

field median 49.6#137 of 224 ranked models

Public

#137of 224

Verified #71 of 88

Price

Self-hosted; infrastructure cost varies

input median $0.75No comparable first-party hosted token rate

Speed

98tok/s

field median 92 tok/sFirst token 1.41 s

Context

128Ktokens

field median 256,000Reported for this model; direct source link not stored

Strongest published evidence

Knowledge ranks #121. Particularly effective for knowledge-intensive tasks like research, analysis, and factual Q&A.

Validate before choosing

6 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.

Source-linked · 6 displayable benchmark rows

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticWeight 22%0 benchmarksNot measured
Not measured
CodingRank Not rankedWeight 20%2 benchmarksVerified
32.5
ReasoningWeight 17%0 benchmarksNot measured
Not measured
MultimodalWeight 12%0 benchmarksNot measured
Not measured
KnowledgeRank #121 of 184Percentile 34thWeight 12%2 benchmarksVerified
38.6
MultilingualWeight 7%0 benchmarksNot measured
Not measured
Inst. FollowingWeight 5%0 benchmarksNot measured
Not measured
MathWeight 5%2 benchmarksVerified
Score pending

6 of 681 tracked benchmark slots have displayable evidence · bars run 0–100

Coverage details

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

  1. AgenticNot measured
  2. Coding2/2 verified
  3. ReasoningNot measured
  4. MultimodalNot measured
  5. Knowledge2/2 verified
  6. MultilingualNot measured
  7. Inst. FollowingNot measured
  8. Math2/2 verified
Verified sourceProvisionalNot measured

Capability shape

Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.

DeepSeek V3.1 category percentile values

  • AgenticNot eligible
  • CodingNot eligible
  • ReasoningNot eligible
  • MultimodalNot eligible
  • Knowledge34th percentile
  • MultilingualNot eligible
  • Instruction followingNot eligible
  • MathNot eligible

The dashed outline is median of 6 nearest peers.

Eligible category ranks

  1. AgenticNot ranked
  2. CodingNot ranked
  3. ReasoningNot ranked
  4. MultimodalNot ranked
  5. Knowledge#121/184
  6. MultilingualNot ranked
  7. Inst. FollowingNot ranked
  8. MathNot ranked
Top decileTop quartileMid-fieldNot eligible

Benchmark ledger

Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.

Coding2 rows
Coding benchmark values, best verified comparison, weight, and source status
SWE-bench VerifiedSoftware Engineering Benchmark VerifiedScore66%Versus best verified row

Best verified: Claude Opus 5 · 96%

Gap30 behindWeightDisplay only
Provider exact
DeepSeek-V3.1 model card
LiveCodeBenchLiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for CodeScore56.4%Versus best verified row

Best verified: Solar Pro 4 · 87.8%

Gap31.4 behindWeightDisplay only
Provider exact
DeepSeek-V3.1 model card
Knowledge2 rows
Knowledge benchmark values, best verified comparison, weight, and source status
MMLU-ProMassive Multitask Language Understanding ProfessionalScore83.7%Versus best verified row

Best verified: Qwen3.7 Max · 89.6%

Gap5.9 behindWeight6% ref. weight
Provider exact
DeepSeek-V3.1 model card
GPQAGraduate-Level Google-Proof Q&AScore74.9%Versus best verified row

Best verified: GPT-6 Astra · 96%

Gap21.1 behindWeight3% ref. weight
Provider exact
DeepSeek-V3.1 model card
Math2 rows
Math benchmark values, best verified comparison, weight, and source status
AIME 2024American Invitational Mathematics Examination 2024Score66.3%Versus best verified row

Best verified: GPT-OSS 120B · 95.8%

Gap29.5 behindWeightDisplay only
Provider exact
DeepSeek-V3.1 model card
AIME 2025American Invitational Mathematics Examination 2025Score49.8%Versus best verified row

Best verified: GPT-5.2 · 100%

Gap50.2 behindWeightDisplay only
Provider exact
DeepSeek-V3.1 model card

Bars run 0–100; the dark tick marks the best source-verified value

All 6 rows

Lineage

The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. Aug 21, 2025 · you are here

    DeepSeek V3.1

    Score 40.8 · Price not listed

Base entry

DeepSeek V3.1 (Reasoning) · 39.2

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

API model ID
Not published
Context window
128K
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Input modalities
Not sourced yet
Output modalities
Not sourced yet
Parameters
Not sourced yet
Availability
Not sourced yet
Cloud regions
Not tracked yet
Lifecycle
Established
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Not documented in the pricing record
Self-host
Open weights available; hardware estimate not sourced
Rate limits
Not tracked yet

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

DeepSeek V3.1 ranks #137 of 224 on the public leaderboard with a score of 40.78/100. Its source-verified position is #71 of 88.

DeepSeek V3.1 is a open weight model with a 128K context window. No explicit reasoning mode is documented in this profile.

DeepSeek V3.1 sits in the DeepSeek V3.1 family with DeepSeek V3.1 (Reasoning). 6 of 681 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Its strongest eligible category is Knowledge at #121. particularly effective for knowledge-intensive tasks like research, analysis, and factual Q&A.

Last updated October 17, 2026. Runtime fields remain blank until a sourced snapshot exists.

Deployment options

Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.

Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.

Estimate VRAM from known parameters

Questions

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

DeepSeek V3.1 ranks #137 out of 224 models on the public BenchAlign leaderboard, with a score of 40.78/100. Its evidence status is Supported, and this profile shows 6 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.

Is DeepSeek V3.1 good for knowledge and understanding?

DeepSeek V3.1 ranks #121 out of 184 eligible models for knowledge and understanding, with a public category score of 38.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is DeepSeek V3.1 good for coding and programming?

DeepSeek V3.1 has source-displayable benchmark coverage for coding and programming, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is DeepSeek V3.1 good for mathematics?

DeepSeek V3.1 has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is DeepSeek V3.1 open source?

DeepSeek V3.1 is an open-weight model from DeepSeek. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.

Which sibling models are related to DeepSeek V3.1?

DeepSeek V3.1 belongs to the DeepSeek V3.1 family. Related tracked variants include DeepSeek V3.1 (Reasoning). A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.

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

No. DeepSeek V3.1 currently has 17 source-displayable rows across 681 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of DeepSeek V3.1?

DeepSeek V3.1 has a reported context window of 128K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.

Watch DeepSeek V3.1 in the weekly brief

Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.

Read a sample issue

Join 5,600+ readers.

Compare DeepSeek V3.1 with every tracked model953 comparisons