Skip to main content
BenchLM
Data

Claude Haiku 5.5 vs GLM-5.3

Updated November 21, 2026. Rank cannot separate these two. Price, access, and your workload decide. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Claude Haiku 5.5 and GLM-5.3 have the same public score on the current data. 11 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Anthropic logo

Anthropic

63.5/100

Supported · Public rank #38

90% interval 59.5–67.6

Model B
Z.AI logo

Z.AI

63.5/100

Supported · Public rank #39

90% interval 59.5–67.5

API price per 1M tokens

Claude Haiku 5.5: $0.10 input / $0.50 output

GLM-5.3: No comparable API price

Context window

Claude Haiku 5.5: 1M

GLM-5.3: 1M

Released

Claude Haiku 5.5: October 7, 2026

GLM-5.3: August 14, 2026

Shared results
11
Claude Haiku 5.5 only
16
GLM-5.3 only
29
Like-for-like categories
6 / 8
Supported: Claude Haiku 5.5 and GLM-5.3How the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Coding work

    Code generation, repair, and software-engineering tasks

    Claude Haiku 5.5

    Claude Haiku 5.5 has the higher public coding point estimate, 67.9 to 63.2, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
  • Agentic work

    Tool use, computer use, and multi-step task completion

    Claude Haiku 5.5

    Claude Haiku 5.5 has the higher public agentic point estimate, 68.3 to 66.1, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
Show secondary and unsupported calls
  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented
  • Chat turn cost

    1K fresh input + 500 output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates
  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates
  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

67.9Claude Haiku 5.563.2GLM-5.3

Like-for-like · BenchAlign v6.0

Claude Haiku 5.5 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

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

1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

  • FrontierMath v2 (Tier 4)Math

    Normalized gap 17.1
    Claude Haiku 5.5:46.341%
    GLM-5.3:29.268%
  • FrontierMath v2 (Tiers 1-3)Math

    Normalized gap 6.3
    Claude Haiku 5.5:75.088%
    GLM-5.3:68.772%
Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Like-for-like
Claude Haiku 5.5
68.3
Supported · #25/182
GLM-5.3
66.1
Supported · #30/182
Basis
BenchAlign v6.0 lane · 9 vs 18 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Coding

Like-for-like
Claude Haiku 5.5
67.9
Supported · #28/180
GLM-5.3
63.2
Supported · #42/180
Basis
BenchAlign v6.0 lane · 7 vs 17 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Reasoning

Like-for-like
Claude Haiku 5.5
62.6
Supported · #38/161
GLM-5.3
60.8
Supported · #45/161
Basis
BenchAlign v6.0 lane · 4 vs 0 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Knowledge

Like-for-like
Claude Haiku 5.5
50.2
Supported · #84/158
GLM-5.3
60.3
Supported · #43/158
Basis
BenchAlign v6.0 lane · 1 vs 2 public rows
Reading
GLM-5.3 leads · intervals overlap

Instruction following

Like-for-like
Claude Haiku 5.5
58.3
Supported · #37/143
GLM-5.3
60.0
Supported · #35/143
Basis
BenchAlign v6.0 lane · 0 vs 1 public rows
Reading
GLM-5.3 leads · intervals overlap

Math

Like-for-like
Claude Haiku 5.5
62.1
Supported · #29/125
GLM-5.3
59.7
Supported · #32/125
Basis
BenchAlign v6.0 lane · 2 vs 2 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Multimodal

Directional only
Claude Haiku 5.5
63.9
Supported · #39/119
GLM-5.3
63.8
Estimated · #47/119
Basis
BenchAlign v6.0 lane · 4 vs 0 public rows
Reading
Directional only

Multilingual

Not comparable
Claude Haiku 5.5
56.1
Estimated · #36/88
GLM-5.3
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Claude Haiku 5.5
$0.00035
Fits in one request
GLM-5.3
Self-hosted; infrastructure cost varies
Fits in one request

GLM-5.3 has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Claude Haiku 5.5
$0.0065
Fits in one request
GLM-5.3
Self-hosted; infrastructure cost varies
Fits in one request

GLM-5.3 has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Claude Haiku 5.5
$0.009
Fits in one request
GLM-5.3
Self-hosted; infrastructure cost varies
Fits in one request
Cached-input rate unavailable

GLM-5.3 has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 21, 2026.

Claude Haiku 5.5

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • Claude Haiku 5.5 is on the efficiency frontier: no cheaper model scores at least as high.
  • GLM-5.3 has no public API price, so it is not plotted.

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See Claude Haiku 5.5 on the full price vs performance chart

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Claude Haiku 5.5

$0.01 per 1M cached input tokens

Claude API pricing

GLM-5.3

No comparable hosted API rate

Z.AI GLM-5.3 model card

Reasoning profile

Claude Haiku 5.5

Reasoning

GLM-5.3

Reasoning

Weight access

Claude Haiku 5.5

Proprietary

GLM-5.3

Open Weight

License

Claude Haiku 5.5

Proprietary

GLM-5.3

Open Weight

Release date

Claude Haiku 5.5

2026-10-07

GLM-5.3

2026-08-14

If you already use one of these models

Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
Claude Haiku 5.5 and GLM-5.3 have the same public score on the current data.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Claude Haiku 5.5 or GLM-5.3?

Claude Haiku 5.5 and GLM-5.3 have the same public score on the current data. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Claude Haiku 5.5 or GLM-5.3?

Claude Haiku 5.5 has the higher public coding point estimate, 67.9 to 63.2, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which is better for agentic tasks, Claude Haiku 5.5 or GLM-5.3?

Claude Haiku 5.5 has the higher public agentic tasks point estimate, 68.3 to 66.1, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which costs less, Claude Haiku 5.5 or GLM-5.3?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

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

Both models list the same context window, 1M.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Claude Haiku 5.5
API / mo$450
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
GLM-5.3
API / mo (DeepInfra)$2,297
Self-host / mo$27,962
Break-evenNot reached at 70% load
Model the full break-even

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence56 rows

Agentic

  • Claude Haiku 5.558.62%
    GLM-5.355.04%

    Claude Haiku 5.5 leads this result

  • Terminal-Bench 4.1

    Shared source
    Claude Haiku 5.540.00%
    GLM-5.341.20%

    GLM-5.3 leads this result

  • Agents' Last Exam (Linux)

    Claude Haiku 5.557.0%
    Source
    GLM-5.3—

    Not directly comparable

  • Terminal-Bench 4.0

    Claude Haiku 5.539.20%
    Source
    GLM-5.3—

    Not directly comparable

  • HLE w/ tools

    Claude Haiku 5.557.4%
    Source
    GLM-5.362.5%
    Source

    GLM-5.3 leads this result

  • MazeBench

    Claude Haiku 5.51%
    Source
    GLM-5.30%
    Source

    Claude Haiku 5.5 leads this result

  • Hermes Index

    Shared source
    Claude Haiku 5.537.0%
    GLM-5.339.2%

    GLM-5.3 leads this result

  • Hermes Bench

    Shared source
    Claude Haiku 5.571.0%
    GLM-5.371.8%

    GLM-5.3 leads this result

  • OSWorld 2.1 Offline

    Claude Haiku 5.572.4%
    Source
    GLM-5.3—

    Not directly comparable

  • Finch

    Claude Haiku 5.5—
    GLM-5.365.1%
    Source

    Not directly comparable

  • b3 Agent Security

    Claude Haiku 5.5—
    GLM-5.393.0%
    Source

    Not directly comparable

  • Cyber Misuse Refusal

    Claude Haiku 5.5—
    GLM-5.387.0%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Haiku 5.5—
    GLM-5.388.2%
    Source

    Not directly comparable

  • terminalBench3

    Claude Haiku 5.5—
    GLM-5.328.3%
    Source

    Not directly comparable

  • CyberGym

    Claude Haiku 5.5—
    GLM-5.384.5%
    Source

    Not directly comparable

  • ExploitGym

    Claude Haiku 5.5—
    GLM-5.315.0%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Claude Haiku 5.5—
    GLM-5.373.0%
    Source

    Not directly comparable

  • AutomationBench

    Claude Haiku 5.5—
    GLM-5.348.2%
    Source

    Not directly comparable

  • Agents' Last Exam

    Claude Haiku 5.5—
    GLM-5.328.5%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Haiku 5.5—
    GLM-5.371.5%
    Source

    Not directly comparable

  • CWE-bench

    Claude Haiku 5.5—
    GLM-5.342.0%
    Source

    Not directly comparable

Coding

  • FrontierCode 1.1 Main

    Claude Haiku 5.546.4%
    Source
    GLM-5.3—

    Not directly comparable

  • Bug Hunt Bench

    Shared source
    Claude Haiku 5.521.5 fixes
    GLM-5.319.0 fixes

    Claude Haiku 5.5 leads this result

  • FrontierSWE v2

    Shared source
    Claude Haiku 5.543.8%
    GLM-5.330.2%

    Claude Haiku 5.5 leads this result

  • FrontierCode 2.0

    Claude Haiku 5.528.9%
    Source
    GLM-5.3—

    Not directly comparable

  • CursorBench 4.0

    Shared source
    Claude Haiku 5.548.4%
    GLM-5.342.6%

    Claude Haiku 5.5 leads this result

  • VulcanBench Frontier v4

    Claude Haiku 5.592.2%
    Source
    GLM-5.3—

    Not directly comparable

  • CursorBench 4.1

    Claude Haiku 5.548.4%
    Source
    GLM-5.3—

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Haiku 5.5—
    GLM-5.388.2%
    Source

    Not directly comparable

  • terminalBench3

    Claude Haiku 5.5—
    GLM-5.328.3%
    Source

    Not directly comparable

  • DeepSWE

    Claude Haiku 5.5—
    GLM-5.366.9%
    Source

    Not directly comparable

  • NL2Repo

    Claude Haiku 5.5—
    GLM-5.358%
    Source

    Not directly comparable

  • ProgramBench

    Claude Haiku 5.5—
    GLM-5.319.0%
    Source

    Not directly comparable

  • FrontierSWE

    Claude Haiku 5.5—
    GLM-5.378.1%
    Source

    Not directly comparable

  • sweMarathon

    Claude Haiku 5.5—
    GLM-5.342.5%
    Source

    Not directly comparable

  • PostTrainBench (lab runs)

    Claude Haiku 5.5—
    GLM-5.339.8%
    Source

    Not directly comparable

  • VulcanBench v3

    Claude Haiku 5.5—
    GLM-5.378.3%
    Source

    Not directly comparable

  • OpenHarmony Bench v1.0

    Claude Haiku 5.5—
    GLM-5.360.8%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Claude Haiku 5.5—
    GLM-5.380.5%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    Claude Haiku 5.5—
    GLM-5.395.4%
    Source

    Not directly comparable

  • PostTrainBench

    Claude Haiku 5.5—
    GLM-5.334.5%
    Source

    Not directly comparable

  • OpenHarmony Bench v1.2

    Claude Haiku 5.5—
    GLM-5.360.65%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-1

    Claude Haiku 5.589.00%
    Source
    GLM-5.3—

    Not directly comparable

  • ARC-AGI-2

    Claude Haiku 5.561.3%
    Source
    GLM-5.3—

    Not directly comparable

  • ARC-AGI-3

    Claude Haiku 5.50.5%
    Source
    GLM-5.3—

    Not directly comparable

  • ARC-AGI-3 Provider Adapter

    Claude Haiku 5.52.82%
    Source
    GLM-5.3—

    Not directly comparable

Multimodal

  • ParseBench-2

    Claude Haiku 5.571.24%
    Source
    GLM-5.3—

    Not directly comparable

  • PerceptionBench (tools)

    Claude Haiku 5.578.6%
    Source
    GLM-5.3—

    Not directly comparable

  • ParseBench-1

    Claude Haiku 5.556.06%
    Source
    GLM-5.3—

    Not directly comparable

  • Chartography (no tools)

    Claude Haiku 5.546.4%
    Source
    GLM-5.3—

    Not directly comparable

Knowledge

  • HLE w/o tools

    Claude Haiku 5.545.9%
    Source
    GLM-5.3—

    Not directly comparable

  • GPQA Diamond (Vals)

    Claude Haiku 5.5—
    GLM-5.388.1%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    Claude Haiku 5.5—
    GLM-5.386.8%
    Source

    Not directly comparable

Instruction following

  • Gray Swan IPI (15 attempts)

    Claude Haiku 5.5—
    GLM-5.331.5%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Claude Haiku 5.575.088%
    GLM-5.368.772%

    Claude Haiku 5.5 leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    Claude Haiku 5.546.341%
    GLM-5.329.268%

    Claude Haiku 5.5 leads this result

56 public results · 11 shared

Watch Claude Haiku 5.5 vs GLM-5.3

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 7,000+ subscribers.

Last updated November 21, 2026