DeepSeek V4.1 Flash 1017 vs Claude Haiku 5.5: Release Comparison

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

Comparison of the DeepSeek V4.1 Flash 1017 and Claude Haiku 5.5 releases: 3 and 5 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 8 models.

For intelligence, Claude Haiku 5.5 scores highest: Claude Haiku 5.5 (Max) at 36, against DeepSeek V4.1 Flash 1017 (Max) at 32 for DeepSeek V4.1 Flash 1017.
For output speed, Claude Haiku 5.5 is fastest: Claude Haiku 5.5 (Max) at 235 t/s, against DeepSeek V4.1 Flash 1017 (Non-reasoning) at 185 t/s for DeepSeek V4.1 Flash 1017.
For cost per task, Claude Haiku 5.5 is cheapest: Claude Haiku 5.5 (Low) at $0.04, against DeepSeek V4.1 Flash 1017 (Non-reasoning) at $0.43 for DeepSeek V4.1 Flash 1017.

Model Playground

Releases compared


	Claude Haiku 5.5 (max)	Claude Haiku 5.5 (xhigh)	DeepSeek V4.1 Flash 1017 (max)	Claude Haiku 5.5 (high)	DeepSeek V4.1 Flash 1017 (high)	Claude Haiku 5.5 (medium)	Claude Haiku 5.5 (low)	DeepSeek V4.1 Flash 1017 (non-reasoning)
Intelligence Index	36	34	32	30	29	25	19	19
Finance & Accounting	44	41	42	38	39	35	29	37
Strategy & Ops	39	39	49	37	48	33	27	40
Legal	39	37	38	35	34	33	27	32
Healthcare & Medical	37	34	41	32	--	31	25	--
Engineering	42	40	37	36	34	32	27	25
Economics	44	43	40	39	37	36	30	34
AA-Briefcase v1.1	1576	1525	1570	1441	1416	1369	1114	1426
AutomationBench-AA	35.4%	36.0%	66.6%	33.7%	68.5%	28.6%	22.9%	48.8%
Terminal-Bench 4.0	32.8%	29.3%	33.8%	21.7%	28.8%	15.2%	12.6%	9.1%
FrontierCode 2.0	34.9%	29.9%	28.5%	23.2%	16.8%	16.1%	8.0%	6.1%
AA-Omniscience v1.1	12	8	1	5	2	4	2	2
GDP.pdf	20.8%	18.2%	17.2%	17.2%	14.2%	15.2%	11.2%	4.4%
HLE-Diamond	29.6%	28.8%	25.3%	23.7%	20.8%	16.8%	14.1%	7.1%
CritPt v2 (Hard Subset)	41.0%	44.5%	24.0%	42.5%	26.5%	30.0%	21.5%	1.0%
Terminal-Bench-Science 0.1	20.0%	18.1%	12.9%	10.0%	10.5%	7.1%	1.9%	2.4%

Cost per TaskUSD	$0.41	$0.25	$0.60	$0.16	--	$0.09	$0.04	$0.43
Input PriceUSD/1M Tokens	$0.10	$0.10	$0.30	$0.10	$0.30	$0.10	$0.10	$0.30
Output PriceUSD/1M Tokens	$0.50	$0.50	$1.20	$0.50	$1.20	$0.50	$0.50	$1.20
Cache Hit PriceUSD/1M Tokens	$0.01	$0.01	$0.006	$0.01	$0.006	$0.01	$0.01	$0.006
Cache Write PriceUSD/1M Tokens	$0.125	$0.125	--	$0.125	--	$0.125	$0.125	--

Output SpeedTokens/s	235	200	170	181	--	172	167	185
Time to First Tokens	370.08	71.52	1.28	31.69	--	13.77	8.83	1.38
Time to First Answer Tokens	370.08	71.52	13.01	31.69	--	13.77	8.83	1.38
End-to-End Response Times	372.20	74.02	15.94	34.46	--	16.67	11.83	4.08
Time per Tasks	592.59	433.39	596.73	298.12	--	193.73	103.55	349.80

Context Window	1M	1M	1M	1M	1M	1M	1M	1M
Creator	Anthropic	Anthropic	DeepSeek	Anthropic	DeepSeek	Anthropic	Anthropic	DeepSeek
License	Proprietary	Proprietary	Open	Proprietary	Open	Proprietary	Proprietary	Open
Input Modality	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image
Output Modality	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text
Providers			+16

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Cost per Task

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

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

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.

Intelligence Index vs. Cost per Task

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

Most attractive quadrant

DeepSeek V4.1 Flash 1017

Claude Haiku 5.5

Pareto line

AA-Briefcase v1.1

AutomationBench-AA

Cost per Task (USD, Log Scale)

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

Output Speed

Output tokens per second · Higher is better

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

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

Benchmarks

AA-PersonalityBenchNew

Model AvsModel B

AA-PersonalityBench: Expressiveness Index, DeepSeek V4.1 Flash 1017 (max) vs Claude Haiku 5.5 (max)

Chance each model’s answer is judged to show more of each trait from their Elo gap · 50% is an even match

DeepSeek V4.1 Flash 1017 (max)

Claude Haiku 5.5 (max)

Natural Sounding

11%

89%

Lexically Varied

12%

88%

Literate

27%

73%

Metaphorical

39%

61%

Eloquent

47%

53%

DeepSeek V4.1 Flash 1017 vs Claude Haiku 5.5: Release Comparison

Intelligence

Speed

Cost per Task

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

Output Speed

Output Speed

Model Performance Representation

Capability Scores

Capability Indexes

Benchmarks

AA-PersonalityBenchNew

AA-PersonalityBench: Expressiveness Index, DeepSeek V4.1 Flash 1017 (max) vs Claude Haiku 5.5 (max)