This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.

DeepSeek has launched a newer release, DeepSeek V3 0324. We suggest considering it instead.

DeepSeek

•

Open weights model

•

Released December 2024

DeepSeek-V2.5 (Dec '24) Intelligence, Performance & Price Analysis

Name: Intelligence
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Try it out API Provider Benchmarks

IntelligenceUpdated

N/A

Artificial Analysis Intelligence Index

Speed

N/A

Output tokens per second

Cost

In -Out -

N/A

Cost per Intelligence Index task

Verbosity

N/A

Output tokens from Intelligence Index

DeepSeek-V2.5 (Dec '24) supports text input, outputs text, and has a 128k tokens context window.

Reasoning	No This page shows the non-reasoning version of this model. A reasoning variant may also exist.
Input modality	Supports: text
Output modality	Supports: text
Context window	128k ~192 A4 pages of size 12 Arial font
Total parameters	236B
Active parameters	21B Number of parameters active per token during inference
License	DEEPSEEK LICENSE AGREEMENT
Model weights	Hugging Face

Metrics are compared against models of the same class:

Non-reasoning models → compared only with other non-reasoning models
Reasoning models → compared across both reasoning and non-reasoning
Open weights models → compared only with other open weights models of the same size class:

Tiny: ≤4B parameters
Small: 4B–40B parameters
Medium: 40B–150B parameters
Large: >150B parameters

Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:

<$0.15 per 1M tokens
$0.15–$1 per 1M tokens
>$1 per 1M tokens

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

No publicly available API

Speed

Output tokens per second · Higher is better

No publicly available API

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better

No publicly available API

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

No publicly available API

Artificial Analysis Intelligence Index v5.0 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

No publicly available API

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

Intelligence Index vs. Cost per Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

Pareto line

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Benchmarks

Evaluations

Evaluations measured independently by Artificial Analysis · AA-PersonalityBench scores are percentile ranks from 1 to 100

No publicly available API

AA-Briefcase v1.1

Agentic knowledge work, Elo

AA-Omniscience v1.1 AccuracyUpdated

Knowledge

AA-Omniscience v1.1 Non-Hallucination RateUpdated

1 - hallucination rate

AutomationBench-AA

Agentic SaaS workflows

Terminal-Bench-Science 0.1New

Agentic scientific research workflows in a terminal

FrontierCode 2.0New

Agentic software engineering in open-source repositories

HLE-DiamondNew

Reasoning & knowledge

GDP.pdf

Professional document reasoning, All-pass

Terminal-Bench 4.0

Agentic coding & terminal use

CritPt v2 (Hard Subset)

Physics reasoning

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

Harvey LAB-AA v1.1Updated

Legal agentic work, Hallucination-Gated All-Pass Rate

EnterpriseOps-Gym-AA

Agentic business operations

GDPval-AA v2.1

Agentic real-world work tasks, Elo

AA-3DNew

Agentic interactive 3D experiences, Elo

Code2Video-AANew

Product and brand videos designed in code, Elo

ITBench-AA

Kubernetes incident root-cause analysis

MLCR-AAUpdated

Medical long context reasoning

MMMU-Pro

Visual reasoning

AA-PersonalityBench: Expressiveness ScoreNew

Rich, varied, well-crafted language

AA-PersonalityBench: Organization ScoreNew

Well-structured, scannable, answer-first

AA-PersonalityBench: Transparency ScoreNew

Truthful, acknowledges uncertainty, non-sycophantic

AA-PersonalityBench: Slop ScoreNew

Use of filler and generic language

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Openness Index

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)

Intelligence Index Comparisons

Intelligence Index vs. Cost per Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

Pareto line

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

No publicly available API

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index

No publicly available API

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)

No publicly available API

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Context Window

Context window: tokens limit · Higher is better

No publicly available API

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference (billions)

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

Frequently Asked Questions

Common questions about DeepSeek-V2.5 (Dec '24)

DeepSeek-V2.5 (Dec '24) was released on December 10, 2024.

DeepSeek-V2.5 (Dec '24) was created by DeepSeek.

No, DeepSeek-V2.5 (Dec '24) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

DeepSeek-V2.5 (Dec '24) supports text input.

DeepSeek-V2.5 (Dec '24) supports text output.

No, DeepSeek-V2.5 (Dec '24) does not support image input. It can only process text.

No, DeepSeek-V2.5 (Dec '24) is not multimodal. It only supports text input.

DeepSeek-V2.5 (Dec '24) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, DeepSeek-V2.5 (Dec '24) is open weights. The model weights are publicly available and can be downloaded for self-hosting.

DeepSeek-V2.5 (Dec '24) has 236 billion parameters (21 billion active).

DeepSeek-V2.5 (Dec '24) is a Mixture of Experts (MoE) model with 236 billion total parameters, but only 21 billion active parameters are used during inference.

DeepSeek-V2.5 (Dec '24) is released under the DEEPSEEK LICENSE AGREEMENT license. This license allows commercial use. View license

DeepSeek-V2.5 (Dec '24) is an open weights model that can be self-hosted. View providers

DeepSeek-V2.5 (Dec '24) is an open weights model that can be downloaded and self-hosted. Compare providers

DeepSeek-V2.5 (Dec '24) Intelligence, Performance & Price Analysis

Model summary

IntelligenceUpdated

Speed

Cost

Verbosity

Comparison Summary

Technical specifications

47 models in this class

Intelligence

Speed

Cost per Task

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index

Open Weights

Intelligence Index vs. Cost per Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Benchmarks

Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Openness Index

Artificial Analysis Openness Index: Score

Intelligence Index Comparisons

Intelligence Index vs. Cost per Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Cost

Cost per Intelligence Index Task

Cost per Intelligence Index Task

Cost to Run Artificial Analysis Intelligence Index

Cost to Run Artificial Analysis Intelligence Index

Pricing: Cache Hit, Input, and Output

Cache Hit

Context Window

Context Window

Context Window for RAG

Context Window

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Total Parameters

Active Parameters at Inference Time

Frequently Asked Questions

When was DeepSeek-V2.5 (Dec '24) released?

Who created DeepSeek-V2.5 (Dec '24)?

Is DeepSeek-V2.5 (Dec '24) a reasoning model?

What input modalities does DeepSeek-V2.5 (Dec '24) support?

What output modalities does DeepSeek-V2.5 (Dec '24) support?

Can DeepSeek-V2.5 (Dec '24) process images?

Is DeepSeek-V2.5 (Dec '24) multimodal?

What is the context window of DeepSeek-V2.5 (Dec '24)?

Is DeepSeek-V2.5 (Dec '24) open source?

How many parameters does DeepSeek-V2.5 (Dec '24) have?

What are the active parameters of DeepSeek-V2.5 (Dec '24)?

What is the license for DeepSeek-V2.5 (Dec '24)?

Is DeepSeek-V2.5 (Dec '24) available via API?

Where can I use DeepSeek-V2.5 (Dec '24)?