LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Haiku 5.5 vs GLM 5.3

Updated October 21, 2026. 54 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Haiku 5.5 Replace GLM 5.3
Claude Haiku 5.5Anthropic
Coding
75.9
Overall
43.4
Output $/M
$0.50
29
GLM 5.3Z.ai
Coding
73.1
Overall
44.8
Output $/M
$1.40
25
vs boards won of 54 shared

Decision reading

Pick Claude Haiku 5.5 for coding: it scores 75.9 on the Vibe Coding Index against 73.1 for GLM 5.3.

Pick GLM 5.3 when the context window is larger, 1.05M against 1M tokens, or when what matters is LMArena WebDev or Terminal-Bench 4 (Vals AI), where it leads.

Model AClaude Haiku 5.5Anthropic75.9/1002 independent benchmarksNo cost per solved taskModel BGLM 5.3Z.ai73.1/1002 independent benchmarks$0.36 per solved task
Shared results
54
Claude Haiku 5.5 only
8
GLM 5.3 only
46
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Claude Haiku 5.5 75.9 from 2 benchmarks, GLM 5.3 73.1 from 2 benchmarks.
Widest category
Math, 17.8 points apart on average over 4 shared benchmarks.
Widest single gap
LiveBench browser: Claude Haiku 5.5 80.0% against GLM 5.3 0.0%, 80.0 points apart on a 0 to 100 scale.
Output price
Claude Haiku 5.5 $0.50 against GLM 5.3 $1.40 per million output tokens, 2.8x apart.
Context window
Claude Haiku 5.5 takes 1M tokens, GLM 5.3 1.05M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryClaude Haiku 5.5BarsGLM 5.3Ties
Coding86
Intelligence11
Agentic work57
Reasoning33
Math40
Knowledge11
Web design43
General34
All shared boards2925
CodingLike-for-likeFour of these boards feed the Vibe Coding Index86
Coding benchmarks for Claude Haiku 5.5 and GLM 5.3
BenchmarkClaude Haiku 5.5GLM 5.3Leader
LiveBench coding91.4%82.8%Claude Haiku 5.5
LMArena WebDev15861621GLM 5.3
AA Coding IndexNot measured74.8Only GLM 5.3 measured
LiveCodeBench (Vals AI)Not measured80.5%Only GLM 5.3 measured
SWE-bench Verified (Vals AI)Not measured95.4%Only GLM 5.3 measured
Terminal-Bench 4 (Vals AI)36.4%38.9%GLM 5.3
Vibe Code Bench (Vals AI)90.4%78.1%Claude Haiku 5.5
Code migration (Vals AI)44.6%44.2%Claude Haiku 5.5
ProgramBench (Vals AI)2.5%1.5%Claude Haiku 5.5
IOI (Vals AI)47.3%68.4%GLM 5.3
Terminal-Bench 2.1 (Vals AI)Not measured71.5%Only GLM 5.3 measured
SWE-bench Multimodal (Vals AI)44.0%Not measuredOnly Claude Haiku 5.5 measured
Vibe Code Bench 1-100 (Vals AI)20.4%20.0%Claude Haiku 5.5
SkillsBench (Vals AI)Not measured47.5%Only GLM 5.3 measured
CyberBench (Vals AI)75.5%72.1%Claude Haiku 5.5
SciCode55.0%59.0%GLM 5.3
FrontierCode46.4%40.1%Claude Haiku 5.5
FrontierSWE43.8%30.2%Claude Haiku 5.5
WeirdMLNot measured75.4%Only GLM 5.3 measured
ALE-BenchNot measured1317.4Only GLM 5.3 measured
LMArena Text: codingNot measured1497Only GLM 5.3 measured
LMArena Text: software and ITNot measured1493Only GLM 5.3 measured
LMArena WebDev: React16051641GLM 5.3
LMArena WebDev: HTML15691595GLM 5.3
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Claude Haiku 5.5 and GLM 5.3
BenchmarkClaude Haiku 5.5GLM 5.3Leader
AA Intelligence Index43.444.8GLM 5.3
Epoch Capabilities Index159.3156.0Claude Haiku 5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index57
Agentic work benchmarks for Claude Haiku 5.5 and GLM 5.3
BenchmarkClaude Haiku 5.5GLM 5.3Leader
AA Agentic IndexNot measured53.1Only GLM 5.3 measured
Design Arena: agents building mobile appsNot measured1194Only GLM 5.3 measured
Design Arena: HTML slidesNot measured1189Only GLM 5.3 measured
Design Arena: PowerPoint slidesNot measured1255Only GLM 5.3 measured
LiveBench research81.9%73.2%Claude Haiku 5.5
LiveBench browser80.0%0.0%Claude Haiku 5.5
LiveBench long agentic57.6%35.9%Claude Haiku 5.5
SREBench (Vals AI)5.7%9.2%GLM 5.3
Finance Agent (Vals AI)54.1%55.8%GLM 5.3
Tax Agent Bench (Vals AI)31.9%39.7%GLM 5.3
Legal Research Bench (Vals AI)43.3%49.0%GLM 5.3
Harvey's Legal Agent Benchmark (Vals AI)4.2%14.6%GLM 5.3
Excel Modeling Benchmark (Vals AI)59.0%56.3%Claude Haiku 5.5
BioMysteryBench (Vals AI)70.4%Not measuredOnly Claude Haiku 5.5 measured
Terminal-Bench-Science (Vals AI)10.0%5.7%Claude Haiku 5.5
Vals Science Index38.5%Not measuredOnly Claude Haiku 5.5 measured
APEX-Agents56.1%56.6%GLM 5.3
Vending-Bench 2$3,602$8,164GLM 5.3
Neither model has a result on the other 21 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index33
Reasoning benchmarks for Claude Haiku 5.5 and GLM 5.3
BenchmarkClaude Haiku 5.5GLM 5.3Leader
GPQA DiamondNot measured88.1%Only GLM 5.3 measured
LiveBench reasoning82.4%85.8%GLM 5.3
MysteryMechanism (Vals AI)35.1%23.0%Claude Haiku 5.5
GPQA Diamond (Artificial Analysis run)Not measured91.7%Only GLM 5.3 measured
Humanity's Last Exam (Artificial Analysis run)44.4%42.3%Claude Haiku 5.5
GPQA Diamond (Epoch AI run)89.6%90.9%GLM 5.3
ARC-AGI89.0%Not measuredOnly Claude Haiku 5.5 measured
ARC-AGI-261.3%Not measuredOnly Claude Haiku 5.5 measured
Chess puzzles55.0%37.0%Claude Haiku 5.5
Mystery game puzzles30.0%33.0%GLM 5.3
EBR-bench43.8%Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: hard promptsNot measured1490Only GLM 5.3 measured
LMArena Text: expertNot measured1514Only GLM 5.3 measured
LMArena Text: hard prompts in EnglishNot measured1496Only GLM 5.3 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Claude Haiku 5.5 and GLM 5.3
BenchmarkClaude Haiku 5.5GLM 5.3Leader
OTIS Mock AIME98.9%91.1%Claude Haiku 5.5
FrontierMath, tiers 1 to 375.1%68.8%Claude Haiku 5.5
FrontierMath, tier 446.3%29.3%Claude Haiku 5.5
ProofBench89.0%49.0%Claude Haiku 5.5
LMArena Text: mathNot measured1495Only GLM 5.3 measured
LMArena Text: mathematical workNot measured1497Only GLM 5.3 measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index11
Knowledge benchmarks for Claude Haiku 5.5 and GLM 5.3
BenchmarkClaude Haiku 5.5GLM 5.3Leader
MMLU ProNot measured86.8%Only GLM 5.3 measured
LegalBench (Vals AI)Not measured84.8%Only GLM 5.3 measured
TaxEval (Vals AI)Not measured72.4%Only GLM 5.3 measured
MedCode (Vals AI)51.5%42.9%Claude Haiku 5.5
SimpleQA Verified23.8%41.0%GLM 5.3
LMArena Text: scienceNot measured1498Only GLM 5.3 measured
LMArena Text: medicine and healthcareNot measured1481Only GLM 5.3 measured
LMArena Text: legal and governmentNot measured1473Only GLM 5.3 measured
LMArena Text: business and financeNot measured1459Only GLM 5.3 measured
Neither model has a result on the other 8 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index43
Web design benchmarks for Claude Haiku 5.5 and GLM 5.3
BenchmarkClaude Haiku 5.5GLM 5.3Leader
Design Arena: websites12631295GLM 5.3
Design Arena: UI components12951314GLM 5.3
Design Arena: game dev13151311Claude Haiku 5.5
Design Arena: data viz12921260Claude Haiku 5.5
Design Arena: 3D13431332Claude Haiku 5.5
Design Arena: all code categories12791304GLM 5.3
Design Arena: SVGNot measured1292Only GLM 5.3 measured
Design Arena: ASCII artNot measured1213Only GLM 5.3 measured
LiveBench design83.1%77.3%Claude Haiku 5.5
GeneralLike-for-likePublic boards, shown as published, kept out of the index34
General benchmarks for Claude Haiku 5.5 and GLM 5.3
BenchmarkClaude Haiku 5.5GLM 5.3Leader
Vals Index58.7%59.7%GLM 5.3
LiveBench data analysis53.1%70.2%GLM 5.3
Public Benefits Bench (Vals AI)63.2%68.5%GLM 5.3
SAGE (Vals AI)45.8%Not measuredOnly Claude Haiku 5.5 measured
MedScribe (Vals AI)89.5%88.8%Claude Haiku 5.5
Long context reasoning (AA-LCR)82.7%79.7%Claude Haiku 5.5
DTBench95.0%87.7%Claude Haiku 5.5
LMCA51.1%55.5%GLM 5.3
Furniture assembly47.5%Not measuredOnly Claude Haiku 5.5 measured
LMArena TextNot measured1474Only GLM 5.3 measured
LMArena Text: instruction followingNot measured1479Only GLM 5.3 measured
LMArena Text: creative writingNot measured1458Only GLM 5.3 measured
LMArena Text: EnglishNot measured1482Only GLM 5.3 measured
LMArena Text: non-EnglishNot measured1459Only GLM 5.3 measured
LMArena Text: ChineseNot measured1532Only GLM 5.3 measured
LMArena Text: GermanNot measured1488Only GLM 5.3 measured
LMArena Text: JapaneseNot measured1460Only GLM 5.3 measured
LMArena Text: KoreanNot measured1460Only GLM 5.3 measured
LMArena Text: FrenchNot measured1503Only GLM 5.3 measured
LMArena Text: SpanishNot measured1462Only GLM 5.3 measured
LMArena Text: RussianNot measured1469Only GLM 5.3 measured
LMArena Text: PolishNot measured1466Only GLM 5.3 measured
LMArena Text: multi-turnNot measured1472Only GLM 5.3 measured
LMArena Text: longer queriesNot measured1483Only GLM 5.3 measured
LMArena Text: writing and languageNot measured1469Only GLM 5.3 measured
LMArena Text: entertainment and mediaNot measured1447Only GLM 5.3 measured
Neither model has a result on the other 20 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Haiku 5.5 and GLM 5.3
BenchmarkClaude Haiku 5.5GLM 5.3Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Claude Haiku 5.5$0.0003Fits in one request
GLM 5.3$0.0008Fits in one request

Claude Haiku 5.5 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 5.5$0.0065Fits in one request
GLM 5.3$0.0081Fits in one request

Claude Haiku 5.5 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 5.5$0.025Fits in one request
GLM 5.3$0.030Fits in one request

Claude Haiku 5.5 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Claude Haiku 5.5 and GLM 5.3
SpecificationAnthropic Claude Haiku 5.5Z.ai GLM 5.3
MakerAnthropicZ.ai
WeightsNo public weights listedOpen weights
ReleasedOctober 7, 2026August 18, 2026
Context window1M1.05M
Input $/Mtok$0.10$0.079
Output $/Mtok$0.50$1.40
Coding index75.973.1
Independent measurements behind it22
Cost per solved taskNot computable$0.36
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 5.5 better than GLM 5.3 for coding?

Pick Claude Haiku 5.5 for coding: it scores 75.9 on the Vibe Coding Index against 73.1 for GLM 5.3. Pick GLM 5.3 when the context window is larger, 1.05M against 1M tokens, or when what matters is LMArena WebDev or Terminal-Bench 4 (Vals AI), where it leads.

Which is cheaper, Claude Haiku 5.5 or GLM 5.3?

Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; GLM 5.3 costs $0.079 and $1.40. Cost per solved task is known for GLM 5.3 only.

Which has the bigger context window, Claude Haiku 5.5 or GLM 5.3?

GLM 5.3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Haiku 5.5 vs GLM 5.3 comparison based on?

54 benchmarks have a result for both models as of October 21, 2026. Claude Haiku 5.5's coding index rests on 2 independent benchmarks and GLM 5.3's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/claude-haiku-5-5-vs-glm-5-3" title="Claude Haiku 5.5 vs GLM 5.3, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-haiku-5-5-vs-glm-5-3">LLMBenchmark.ai, Claude Haiku 5.5 vs GLM 5.3</a></p>