40 models

DeepSeek Models: Intelligence, Performance & Price

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

DeepSeek

Intelligence

Updated

DeepSeek V4.1 Flash 1017 (max)

DeepSeek V4.1 Flash 1017 (high)

DeepSeek V4 Pro 0813 (max)

DeepSeek V4.1 Flash 1017 (non-reasoning)

DeepSeek V4 Pro 0813 (non-reasoning)

Artificial Analysis Intelligence Index

Time per Task

DeepSeek V4.1 Flash 1017 (non-reasoning)

7.2 min

DeepSeek V4.1 Flash 1017 (high)

10.6 min

DeepSeek V4.1 Flash 1017 (max)

13.6 min

DeepSeek V4 Pro 0813 (non-reasoning)

14.8 min

DeepSeek V4 Pro 0813 (max)

22.9 min

Per Intelligence Index Task

Cost

DeepSeek V4.1 Flash 1017 (non-reasoning)

$0.43

DeepSeek V4.1 Flash 1017 (high)

$0.46

DeepSeek V4.1 Flash 1017 (max)

$0.60

DeepSeek V4 Pro 0813 (non-reasoning)

$0.98

DeepSeek V4 Pro 0813 (max)

$1.77

Per Intelligence Index Task

Artificial Analysis has benchmarked 40 models from DeepSeek. Below is a comparison of the key metrics across these models.

For intelligence, the top model from DeepSeek is DeepSeek V4.1 Flash 1017 (Max) at 33.
For speed, DeepSeek V4.1 Flash 1017 (Non-reasoning) at 7.2 min has the lowest time per task.
For latency, DeepSeek V4.1 Flash 1017 (Non-reasoning) at 1.32s offers the lowest time to first answer token.
For pricing, DeepSeek V4.1 Flash 1017 (Non-reasoning) at $0.43 offers the lowest cost per task. Prices vary up to 4.2x across models.

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 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

Artificial Analysis Intelligence Index v5.0.1 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.

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.

Cost

Cost per Intelligence Index Task

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

Speed & Latency

Time per Intelligence Index Task

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Speed at the model's own endpoint or the median across providers · Lower is better

The weighted average time (minutes) per Artificial Analysis Intelligence Index task: output tokens per task divided by output speed, weighted by each benchmark's weight in the Intelligence Index.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Capability Scores

Capability Indexes

Measures the performance of models on specific capabilities and industries

Finance & Accounting Index

Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better

Engineering Index

Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode 2.0, AA-Briefcase v1.1 · Higher is better

Economics Index

Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better

All DeepSeek Releases

Further details

								Weights		Provider Benchmarks
DeepSeek V4.1 Flash 1017 (Max)	DeepSeek	33	552B 16B active at inference time	1M	$0.2	13.6	171	🤗	+19	View
DeepSeek V4.1 Flash 1017 (High)	DeepSeek	29	552B 16B active at inference time	1M	$0.2	10.6	174	🤗		View
DeepSeek V4 Pro 0813 (Max)	DeepSeek	23	1.6T 49B active at inference time	1M	$0.7	22.9	72	🤗	+6	View
DeepSeek V4.1 Flash 1017 (Non-reasoning)	DeepSeek	19	552B 16B active at inference time	1M	$0.2	7.2	151	🤗	+3	View
DeepSeek V4 Pro 0813 (Non-reasoning)	DeepSeek	13	1.6T 49B active at inference time	1M	$0.7	14.8	80	🤗		View
DeepSeek V3.2 Exp (Non-reasoning)	DeepSeek	-	685B 37B active at inference time	128k	$0.1	-	-	🤗		View
DeepSeek V3.1 Terminus (Reasoning)	DeepSeek	-	685B 37B active at inference time	128k	$1.7	-	-	🤗		View
DeepSeek R1 (Jan '25)	DeepSeek	-	685B 37B active at inference time	128k	$2.2	-	124	🤗		View
DeepSeek R1 Distill Llama 8B	DeepSeek	-	8B	128k	-	-	-	🤗	-	View
DeepSeek V3.1 (Reasoning)	DeepSeek	-	685B 37B active at inference time	128k	$0.5	-	117	🤗		View
DeepSeek-V2-Chat	DeepSeek	-	236B 21B active at inference time	128k	-	-	-	🤗	-	View
DeepSeek V3 (Dec '24)	DeepSeek	-	671B 37B active at inference time	128k	$0.4	-	74	🤗		View
DeepSeek R1 Distill Qwen 1.5B	DeepSeek	-	1.5B	128k	-	-	-	🤗	-	View
DeepSeek R1 Distill Llama 70B	DeepSeek	-	70B	128k	$0.7	-	-	🤗		View
DeepSeek V3.2 Speciale	DeepSeek	-	685B 37B active at inference time	128k	-	-	-	🤗	-	View
DeepSeek V4 Pro 0424 (High)	DeepSeek	-	1.6T 49B active at inference time	1M	$0.7	-	-	🤗	+2	View
DeepSeek R1 0528 Qwen3 8B	DeepSeek	-	8.2B	33k	-	-	-	🤗	-	View
DeepSeek V3.2 (Non-reasoning)	DeepSeek	-	685B 37B active at inference time	128k	$0.3	-	37	🤗	+5	View
DeepSeek V4 Pro 0424 (Non-reasoning)	DeepSeek	-	1.6T 49B active at inference time	1M	$0.8	-	161	🤗		View
DeepSeek V4.1 Flash (Non-reasoning)	DeepSeek	-	552B 16B active at inference time	1M	$0.2	-	221	🤗	+5	View
DeepSeek V3 0324	DeepSeek	-	671B 37B active at inference time	128k	$0.2	-	155	🤗		View
DeepSeek V4 Flash Vision (Max)	DeepSeek	-	284B 13B active at inference time	1M	$0.2	-	160	Not available		View
DeepSeek LLM 67B Chat (V1)	DeepSeek	-	7B	4k	-	-	-	🤗	-	View
DeepSeek V4 Flash 0420 (High)	DeepSeek	-	284B 13B active at inference time	1M	$0.1	-	-	🤗		View
DeepSeek-V2.5	DeepSeek	-	236B 21B active at inference time	128k	-	-	-	🤗	-	View
DeepSeek-Coder-V2	DeepSeek	-	236B 21B active at inference time	128k	-	-	-	🤗	-	View
DeepSeek R1 0528 (May '25)	DeepSeek	-	685B 37B active at inference time	128k	$1.8	-	24	🤗		View
DeepSeek V4 Flash 0420 (Non-reasoning)	DeepSeek	-	284B 13B active at inference time	1M	$0.1	-	-	🤗		View
DeepSeek V3.2 Exp (Reasoning)	DeepSeek	-	685B 37B active at inference time	128k	$0.1	-	-	🤗		View
DeepSeek R1 Distill Qwen 14B	DeepSeek	-	14B	128k	-	-	-	🤗	-	View
DeepSeek-V2.5 (Dec '24)	DeepSeek	-	236B 21B active at inference time	128k	-	-	-	🤗	-	View
DeepSeek V4 Pro 0424 (Max)	DeepSeek	-	1.6T 49B active at inference time	1M	$0.6	-	75	🤗	+4	View
DeepSeek Coder V2 Lite Instruct	DeepSeek	-	16B 2.4B active at inference time	128k	-	-	-	🤗	-	View
DeepSeek V3.2 (Reasoning)	DeepSeek	-	685B 37B active at inference time	128k	$0.1	-	35	🤗	+3	View
DeepSeek V4 Flash 0420 (Max)	DeepSeek	-	284B 13B active at inference time	1M	$0.1	-	38	🤗		View
DeepSeek V4.1 Flash (Max)	DeepSeek	-	552B 16B active at inference time	1M	$0.2	-	211	🤗	+13	View
DeepSeek R1 Distill Qwen 32B	DeepSeek	-	32B	128k	-	-	-	🤗	-	View
DeepSeek V3.1 Terminus (Non-reasoning)	DeepSeek	-	685B 37B active at inference time	128k	$0.2	-	68	🤗		View
DeepSeek V3.1 (Non-reasoning)	DeepSeek	-	685B 37B active at inference time	128k	$0.5	-	72	🤗	+3	View
DeepSeek V4 Flash 0731 (Max)	DeepSeek	-	284B 13B active at inference time	1M	$0.1	-	123	🤗	+8	View

DeepSeek Models: Intelligence, Performance & Price

Intelligence

Time per Task

Cost

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

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

Speed & Latency

Time per Intelligence Index Task

Time per Intelligence Index Task

Time Period

Capability Scores

Capability Indexes

All DeepSeek Releases

Further details