Skip to content

DeepSeek · Chat

DeepSeek V2.5

DeepSeek 🇨🇳ChatDeepSeek family

Newer version: DeepSeek V4. Our catalogue has no release date for DeepSeek V4. We compared the version names in our catalogue.

llminfo IQ
112.6
Market median price
$0.20 blended / 1M
Max context
33K
Listings
3

Evidence and sources

🤗 deepseek-ai/DeepSeek-V2.5llminfo IQ 112.6, ranked among chat models. From 82 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 82.2, 95% interval 70–94. From 6 benchmark families across 5 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 computedPoor value (40.6). Costs more 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 5 Sep 2024Maker HQ: CN (according to DeepSeek's own website)
Sources: LMArena data, AIHubMix data docs, Hugging FacePrimary data from LMArena from AIHubMix: name from Hugging Face: release date

Advantages and trade-offs

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

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 9 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Text

Listings

 302aideepseek-ai/DeepSeek-V2.5Source: 302.ai data32K$0.15$0.30
 Aihubmixdeepseek-ai/DeepSeek-V2.5Source: AIHubMix data docsNot published by the provider$0.16$0.32
 Fireworks AIfireworks_ai/accounts/fireworks/models/deepseek-v2p5Source: LiteLLM data33K$1.20$1.20

Benchmarks

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

Human preference

Arena27 related benchmarks · 50 results
ELO
Source: LMArena data · Nov 2026
Setting not stated
ELO - Chinese
Source: LMArena data · Nov 2026
Setting not stated
ELO - Creative Writing
Source: LMArena data · Nov 2026
Setting not stated
ELO - English
Source: LMArena data · Nov 2026
Setting not stated
ELO - Exclude Ties
Source: LMArena data · Nov 2026
Setting not stated
ELO - Expert
Source: LMArena data · Nov 2026
Setting not stated
Show 38 more resultsHide 38 results
ELO - French
Source: LMArena data · Nov 2026
ELO - German
Source: LMArena data · Nov 2026
Setting not stated
ELO - Hard Prompts
Source: LMArena data · Nov 2026
Setting not stated
ELO - Hard Prompts English
Source: LMArena data · Nov 2026
Setting not stated
ELO - Industry Business and Management and Financial Operations
Source: LMArena data · Nov 2026
Setting not stated
ELO - Industry Entertainment and Sports and Media
Source: LMArena data · Nov 2026
Setting not stated
ELO - Industry Life and Physical and Social Science
Source: LMArena data · Nov 2026
Setting not stated
ELO - Industry Mathematical
Source: LMArena data · Nov 2026
Setting not stated
ELO - Industry Medicine and Healthcare
Source: LMArena data · Nov 2026
Setting not stated
ELO - Industry Software and It Services
Source: LMArena data · Nov 2026
Setting not stated
ELO - Industry Writing and Literature and Language
Source: LMArena data · Nov 2026
Setting not stated
ELO - Japanese
Source: LMArena data · Nov 2026
Setting not stated
ELO - Korean
Source: LMArena data · Nov 2026
ELO - Longer Query
Source: LMArena data · Nov 2026
Setting not stated
ELO - Multi Turn
Source: LMArena data · Nov 2026
Setting not stated
ELO - Non English
Source: LMArena data · Nov 2026
Setting not stated
ELO - Russian
Source: LMArena data · Nov 2026
Setting not stated
ELO - Spanish
Source: LMArena data · Nov 2026
ELO Style-Controlled
Source: LMArena data · Nov 2026
Setting not stated
Hard
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MT-BenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Coding

AiderSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
CodeElo28 related benchmarks · 28 results

Math

GSM8KSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MATHSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Instruction following

Knowledge

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

General

Reasoning

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

Other

Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · CodeElo (Qwen). Aggregate scores from the official results file; no results licence asserted. The evaluation scaffold agreement is not presented as a licence for these scores · Hugging Face official benchmark leaderboards; licence varies by benchmark

Around the web

Also known as: deepseek-ai/deepseek-v2.5, deepseek-v2.5-1210, fireworks_ai/accounts/fireworks/models/deepseek-v2p5

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