Skip to content

DeepSeek · Chat

DeepSeek Reasoner

DeepSeek 🇨🇳ChatDeepSeek familyOpen weights. One of its sources says the weights are publicly available.The maker lists this model as deprecated (24 Jul 2026).
From Aiml API's listing:
DeepSeek R1 excels in reasoning tasks with advanced features like chain-of-thought processing and efficient parameter activation
llminfo IQ
127.1
Maker's price
$0.315 blended / 1M
Max context
1M
Listings
9

Evidence and sources

llminfo IQ 127.1, ranked among chat models. From 94 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 101.4, 95% interval 94–109. From 8 benchmark families across 4 sources. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (59.4). Cheaper per task than its benchmark results predict. From 1 benchmark with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 20 Jan 2025Maker HQ: CN (according to DeepSeek's own website)
Sources: GenAI Prices data, Models.dev data, LiteLLM data, AI/ML API data, llminfo researchPrimary data from GenAI Prices from Models.dev: name, weights availability from LiteLLM: deprecation date from AI/ML API: primary mode, description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 2 of the 6 peers that say either way have open weights.

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (24 Jul 2026).

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 8 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingPrompt caching

Listings

 DeepSeekdeepseek-reasonerSources: GenAI Prices data, LiteLLM data131K$0.28cache read $0.028$0.42
 302aideepseek-reasonerSource: 302.ai data64K$0.29$0.43
 Evolinkdeepseek-reasonerSources: EvoLink data, EvoLink PricingNot published by the provider$0.2941$1.1765
 RequestyInference by DeepSeekdeepseek/deepseek-reasonerSource: Requesty data1M$0.14cache read $0.028$0.28
 Orcarouterdeepseek/deepseek-reasonerSource: Models.dev data1M$0.242cache read $0.0077$0.726

4 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Coding

Agentic

Reasoning

t2-benchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Factuality

Math

AIME 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
HMMT 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Human preference

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Instruction following

Knowledge

MMLU-ProSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Other

Horangi36 related benchmarks · 36 results
Nejumi 428 related benchmarks · 28 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
Show 22 more resultsHide 22 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_表現
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
deepseek/DeepSeek-V3.2 (Thinking Mode)

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats · HalluHard: Fan, Delsad, Flammarion and Andriushchenko (EPFL), arXiv:2602.01031 · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results

Around the web

Also known as: deepseek/deepseek-reasoner

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works