Exaone 4.0 32B vs GLM-5

Updated September 29, 2026. Rank says GLM-5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Decision reading

GLM-5 has the higher public score, 54.26 versus 31.35, and the 90% score intervals do not overlap. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A

Exaone 4.0 32B

LG AI Research

31.35/100

Estimated · Public rank #162

90% interval 19.8–42.9

Model B

GLM-5

Z.AI

54.26/100

Supported · Public rank #67

90% interval 44.5–64.0

Shared results: 1
Exaone 4.0 32B only: 1
GLM-5 only: 35
Like-for-like categories: 0 / 8

Estimated: Exaone 4.0 32B · Supported: GLM-5How 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.

Long documents
Prompts that approach the documented context limit
GLM-5
GLM-5 has the larger documented context window.
Confidence: documented

Show secondary and unsupported calls

Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Exaone 4.0 32B is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Exaone 4.0 32B is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limited
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
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Exaone 4.0 32B does not fit this workload in one request. GLM-5 does not fit this workload in one request. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate. Exaone 4.0 32B has no comparable published API token rate.
Confidence: rate-fallback
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.

Pick the job you would use them for

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

—Exaone 4.0 32B39.2GLM-5

Not comparable · BenchAlign v5.7

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

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

Open the coding leaderboard Shortlist models for this job

Same basis rules as the category table below

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.

MMLU-ProKnowledge
Normalized gap 3.9
Exaone 4.0 32B:81.8%
GLM-5:85.7%
Exaone 4.0 32B source GLM-5 source

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 v5.7 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Knowledge

Directional only

Exaone 4.0 32B: 29.3; Supported · #147/169
GLM-5: 47.1; Estimated · #73/169
Basis: BenchAlign v5.7 lane · 1 vs 6 public rows
Reading: Directional only

Agentic

Not comparable

Exaone 4.0 32B: Not ranked
GLM-5: 37.6; Estimated · #58/117
Basis: BenchAlign v5.7 lane · 0 vs 11 public rows
Reading: Not comparable

Coding

Not comparable

Exaone 4.0 32B: Not ranked
GLM-5: 39.2; Estimated · #64/143
Basis: BenchAlign v5.7 lane · 0 vs 6 public rows
Reading: Not comparable

Reasoning

Not comparable

Exaone 4.0 32B: Not ranked
GLM-5: 53.3; Unranked · 4 rankable rows
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Not comparable

Multimodal

Not comparable

Exaone 4.0 32B: Not ranked
GLM-5: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Multilingual

Not comparable

Exaone 4.0 32B: Not ranked
GLM-5: 48.7; #6/12
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Not comparable

Instruction following

Not comparable

Exaone 4.0 32B: 36.5; Unranked · 1 rankable row
GLM-5: 87.2; #32/124
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Math

Not comparable

Exaone 4.0 32B: Not ranked
GLM-5: 56.5; #7/7
Basis: Provisional lane · 0 vs 4 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for Exaone 4.0 32B and GLM-5
Category	Exaone 4.0 32B	GLM-5	Basis	Reading
Knowledge	29.3Supported · #147/169	47.1Estimated · #73/169	Directional onlyBenchAlign v5.7 lane · 1 vs 6 public rows	Directional only
Agentic	Not ranked	37.6Estimated · #58/117	Not comparableBenchAlign v5.7 lane · 0 vs 11 public rows	Not comparable
Coding	Not ranked	39.2Estimated · #64/143	Not comparableBenchAlign v5.7 lane · 0 vs 6 public rows	Not comparable
Reasoning	Not ranked	53.3Unranked · 4 rankable rows	Not comparableProvisional lane · 0 vs 1 weighted rows	Not comparable
Multimodal	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Multilingual	Not ranked	48.7#6/12	Not comparableProvisional lane · 0 vs 1 weighted rows	Not comparable
Instruction following	36.5Unranked · 1 rankable row	87.2#32/124	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Math	Not ranked	56.5#7/7	Not comparableProvisional lane · 0 vs 4 weighted rows	Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. 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

Exaone 4.0 32B: API rate not published; Fits in one request
GLM-5: $0.0026; Fits in one request

Exaone 4.0 32B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Exaone 4.0 32B: API rate not published; Fits in one request
GLM-5: $0.0596; Fits in one request

Exaone 4.0 32B has no comparable published API token rate.

Cache-heavy agent loop

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

Exaone 4.0 32B: API rate not published; Does not fit in one request; Cached-input rate unavailable
GLM-5: $0.252; Does not fit in one request; Cached input priced at the published list-input rate

Exaone 4.0 32B does not fit this workload in one request. GLM-5 does not fit this workload in one request. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate. Exaone 4.0 32B has no comparable published API token rate.

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

Specification differences

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

SpecificationExaone 4.0 32BGLM-5

Context window

Maximum documented context; output-token limits may be lower.

Exaone 4.0 32B

128K

GLM-5

200K

API model ID

Exaone 4.0 32B

Not sourced

GLM-5

Not sourced

Cached-input rate

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

Exaone 4.0 32B

No comparable hosted API rate

GLM-5

Not published

Documented inputs

Exaone 4.0 32B

Not sourced

GLM-5

Not sourced

Documented outputs

Exaone 4.0 32B

Not sourced

GLM-5

Not sourced

Provider availability

Exaone 4.0 32B

Not sourced

GLM-5

Not sourced

Reasoning profile

Exaone 4.0 32B

Reasoning

GLM-5

Non-Reasoning

Weight access

Exaone 4.0 32B

Open Weight

GLM-5

Open Weight

License

Exaone 4.0 32B

Open Weight

GLM-5

Open Weight

Release date

Exaone 4.0 32B

Not sourced

GLM-5

2026-03-01

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: GLM-5 has the higher public score, 54.26 versus 31.35, and the 90% score intervals do not overlap.
Workload cost: A complete comparable API-rate estimate is not available for both models.
Context tradeoff: GLM-5 has the larger documented window (200K).

Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Exaone 4.0 32B or GLM-5?

GLM-5 has the higher public score, 54.26 versus 31.35, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, Exaone 4.0 32B or GLM-5?

Exaone 4.0 32B is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Exaone 4.0 32B or GLM-5?

Exaone 4.0 32B is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Exaone 4.0 32B or GLM-5?

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, Exaone 4.0 32B or GLM-5?

GLM-5 has the larger documented context window: 200K, compared with 128K.

Benchmark evidence

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

Browse raw public benchmark evidence37 rows

Agentic

Terminal-Bench 2.0
Exaone 4.0 32B—
GLM-556.2%
Source
Not directly comparable
Claw-Eval
Exaone 4.0 32B—
GLM-557.7%
Source
Not directly comparable
QwenClawBench
Exaone 4.0 32B—
GLM-554.1%
Source
Not directly comparable
τ³-bench results
Exaone 4.0 32B—
GLM-565.6%
Source
Not directly comparable
DeepPlanning
Exaone 4.0 32B—
GLM-514.6%
Source
Not directly comparable
Toolathlon
Exaone 4.0 32B—
GLM-538%
Source
Not directly comparable
MCP Atlas
Exaone 4.0 32B—
GLM-531.1%
Source
Not directly comparable
MCP-Tasks
Exaone 4.0 32B—
GLM-560.8%
Source
Not directly comparable
WideResearch
Exaone 4.0 32B—
GLM-569.8%
Source
Not directly comparable
CyberGym
Exaone 4.0 32B—
GLM-543.2%
Source
Not directly comparable
Gert Labs
Exaone 4.0 32B—
GLM-550.99%
Source
Not directly comparable

Coding

SWE-bench Verified
Exaone 4.0 32B—
GLM-577.8%
Source
Not directly comparable
SWE-bench Verified*
Exaone 4.0 32B—
GLM-572.8%
Source
Not directly comparable
SWE-bench Pro
Exaone 4.0 32B—
GLM-555.1%
Source
Not directly comparable
SWE Multilingual
Exaone 4.0 32B—
GLM-573.3%
Source
Not directly comparable
SWE-Rebench
Exaone 4.0 32B—
GLM-562.8%
Source
Not directly comparable
React Native Evals
Exaone 4.0 32B—
GLM-574.8%
Source
Not directly comparable

Reasoning

LongBench v2
Exaone 4.0 32B—
GLM-560.8%
Source
Not directly comparable
AI-Needle
Exaone 4.0 32B—
GLM-563.3%
Source
Not directly comparable

Knowledge

MMLU-Pro
Exaone 4.0 32B81.8%
Source
GLM-585.7%
Source
GLM-5 leads this result
GPQA
Exaone 4.0 32B—
GLM-586%
Source
Not directly comparable
GPQA-D
Exaone 4.0 32B—
GLM-586.0%
Source
Not directly comparable
SuperGPQA
Exaone 4.0 32B—
GLM-566.8%
Source
Not directly comparable
MMLU-Pro (Arcee)
Exaone 4.0 32B—
GLM-585.8%
Source
Not directly comparable
HLE
Exaone 4.0 32B—
GLM-550.4%
Source
Not directly comparable

Multilingual

MMLU-ProX
Exaone 4.0 32B—
GLM-583.1%
Source
Not directly comparable
NOVA-63
Exaone 4.0 32B—
GLM-555.1%
Source
Not directly comparable

Instruction following

IFEval
Exaone 4.0 32B—
GLM-592.6%
Source
Not directly comparable

Math

AIME 2025
Exaone 4.0 32B85.3%
Source
GLM-5—
Not directly comparable
AIME26
Exaone 4.0 32B—
GLM-595.8%
Source
Not directly comparable
AIME25 (Arcee)
Exaone 4.0 32B—
GLM-593.3%
Source
Not directly comparable
HMMT Feb 2025
Exaone 4.0 32B—
GLM-597.5%
Source
Not directly comparable
HMMT Nov 2025
Exaone 4.0 32B—
GLM-596.9%
Source
Not directly comparable
HMMT Feb 2026
Exaone 4.0 32B—
GLM-586.4%
Source
Not directly comparable
MMAnswerBench
Exaone 4.0 32B—
GLM-582.5%
Source
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Exaone 4.0 32B—
GLM-516.434%
Source
Not directly comparable
FrontierMath v2 (Tier 4)
Exaone 4.0 32B—
GLM-52.100%
Source
Not directly comparable

37 public results · 1 shared

Related comparisons

Compare API pricing Read the methodology Open the model selector

Watch Exaone 4.0 32B vs GLM-5

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

Read a sample issue

Join 2,000+ readers.

Last updated September 29, 2026

Exaone 4.0 32B vs GLM-5

Decision reading

Which one for your work

Long documents

Coding work

Agentic work

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

Which one for a specific job

What is actually comparable

Shape of the matched evidence

Category results, on a stated basis

Knowledge

Agentic

Coding

Reasoning

Multimodal

Multilingual

Instruction following

Math

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

If you already use one of these models

Questions

Which is better, Exaone 4.0 32B or GLM-5?

Which is better for coding, Exaone 4.0 32B or GLM-5?

Which is better for agentic tasks, Exaone 4.0 32B or GLM-5?

Which costs less, Exaone 4.0 32B or GLM-5?

Which has the larger context window, Exaone 4.0 32B or GLM-5?

Benchmark evidence

Agentic

Coding

Reasoning

Knowledge

Multilingual

Instruction following

Math

Related comparisons

Watch Exaone 4.0 32B vs GLM-5