Claude Haiku 5.5 vs GLM-5.3: Release Comparison

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

Comparison of the Claude Haiku 5.5 and GLM-5.3 releases: 5 and 2 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 7 models.

For intelligence, GLM-5.3 scores highest: GLM-5.3 (Max) at 45, against Claude Haiku 5.5 (Max) at 43 for Claude Haiku 5.5.
For output speed, Claude Haiku 5.5 is fastest: Claude Haiku 5.5 (Max) at 240 t/s, against GLM-5.3 (Low) at 88 t/s for GLM-5.3.
For cost per task, Claude Haiku 5.5 is cheapest: Claude Haiku 5.5 (Low) at $0.02, against GLM-5.3 (Low) at $0.85 for GLM-5.3.

Model Playground

Releases compared


	GLM-5.3 (max)	Claude Haiku 5.5 (max)	Claude Haiku 5.5 (xhigh)	Claude Haiku 5.5 (high)	Claude Haiku 5.5 (medium)	GLM-5.3 (low)	Claude Haiku 5.5 (low)
Intelligence Index	45	43	41	38	34	34	29
Finance & Accounting	45	44	41	38	35	35	29
Strategy & Ops	48	40	39	37	34	39	28
Legal	42	42	40	38	36	33	31
Healthcare & Medical	42	40	35	34	32	33	27
Engineering	47	45	43	39	35	38	31
Economics	51	51	49	46	43	41	37
AA-Briefcase v1.1	1504	1575	1524	1440	1369	1184	1114
GDPval-AA v2.1	1658	1628	1521	1425	1283	1334	1131
AutomationBench-AA	62.2%	35.4%	36.0%	33.7%	28.6%	52.0%	22.9%
Terminal-Bench 4.0	41.9%	32.8%	29.3%	21.7%	15.2%	34.8%	12.6%
SciCode	59.0%	55.0%	51.7%	48.7%	49.0%	42.0%	49.2%
Humanity's Last Exam	42.3%	44.4%	42.7%	37.3%	33.8%	36.6%	27.0%
GDP.pdf	11.2%	20.8%	18.2%	17.2%	15.2%	8.8%	11.2%
CritPt	19.1%	18.9%	22.6%	18.6%	12.9%	14.6%	9.1%
AA-Omniscience	14	11	6	6	4	−8	3
AA-LCR v1.1	79.7%	82.7%	78.3%	77.3%	77.3%	72.7%	72.0%

Cost per TaskUSD	$2.01	$0.21	$0.12	$0.08	$0.05	$0.85	$0.02
Input PriceUSD/1M Tokens	$1.40	$0.10	$0.10	$0.10	$0.10	$1.40	$0.10
Output PriceUSD/1M Tokens	$4.40	$0.50	$0.50	$0.50	$0.50	$4.40	$0.50
Cache Hit PriceUSD/1M Tokens	$0.26	$0.01	$0.01	$0.01	$0.01	$0.26	$0.01
Cache Write PriceUSD/1M Tokens	--	$0.125	$0.125	$0.125	$0.125	--	$0.125

Output SpeedTokens/s	86	240	195	185	174	88	181
Time to First Tokens	2.74	332.02	69.39	25.05	11.39	2.89	8.04
Time to First Answer Tokens	26.08	332.02	69.39	25.05	11.39	25.69	8.04
End-to-End Response Times	31.92	334.10	71.95	27.75	14.26	31.39	10.81
Time per Tasks	634.16	425.91	289.00	189.58	119.37	336.01	60.85

Context Window	1M	1M	1M	1M	1M	1M	1M
Creator	Z AI	Anthropic	Anthropic	Anthropic	Anthropic	Z AI	Anthropic
License	Open	Proprietary	Proprietary	Proprietary	Proprietary	Open	Proprietary
Input Modality	Supports: text	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text	Supports: text and image
Output Modality	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text
Providers	+19					+3

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

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, and AA-LCR v1.1

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. 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

Claude Haiku 5.5

GLM-5.3

Pareto line

AA-Briefcase v1.1

GDPval-AA v2.1

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 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 6 evaluations: GDPval-AA v2.1, AA-Briefcase v1.1, AA-Omniscience, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better

Engineering Index

Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better

Economics Index

Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better

Benchmarks

AA-PersonalityBenchNew

Model AvsModel B

AA-PersonalityBench: Expressiveness Index, Claude Haiku 5.5 (max) vs GLM-5.3 (max)

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

Claude Haiku 5.5 (max)

GLM-5.3 (max)

Eloquent

97%

Lexically Varied

12%

88%

Natural Sounding

12%

88%

Metaphorical

17%

83%

Literate

68%

32%

Claude Haiku 5.5 vs GLM-5.3: Release Comparison

Intelligence

Speed

Cost per Task

Intelligence

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, Claude Haiku 5.5 (max) vs GLM-5.3 (max)