Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes
BenchLM
Z.AI logo
Model A
GLM-5.2

Z.AI

68.12/100

Supported · Public rank #28

90% interval 61.6–74.6

GLM-5.2 vs Granite 4.2 3B

Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

IBM logo
Model B
Granite 4.2 3B

IBM

—

Evidence status unavailable

90% interval unavailable

Decision reading

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.

1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Share or export

Share on XLinkedInSocial cardCSVJSON

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-5.2

    GLM-5.2 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

    Granite 4.2 3B 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

    Granite 4.2 3B 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. Granite 4.2 3B does not fit this workload in one request. GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate. Granite 4.2 3B 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

What is actually comparable

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

Shared results
1
GLM-5.2 only
24
Granite 4.2 3B only
8
Like-for-like categories
0 / 8

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign 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.

Agentic

Not comparable
GLM-5.2
58.5
Supported · #28/152
Granite 4.2 3B
Not ranked
Basis
BenchAlign lane · 6 vs 2 public rows
Reading
Not comparable

Coding

Not comparable
GLM-5.2
61.0
Supported · #19/151
Granite 4.2 3B
Not ranked
Basis
BenchAlign lane · 8 vs 2 public rows
Reading
Not comparable

Reasoning

Not comparable
GLM-5.2
74.8
Unranked · 2 rankable rows
Granite 4.2 3B
37.7
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Knowledge

Not comparable
GLM-5.2
60.7
Supported · #35/183
Granite 4.2 3B
Not ranked
Basis
BenchAlign lane · 6 vs 2 public rows
Reading
Not comparable

Math

Not comparable
GLM-5.2
80.7
Unranked · 4 rankable rows
Granite 4.2 3B
Not ranked
Basis
Provisional lane · 2 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
GLM-5.2
Not ranked
Granite 4.2 3B
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
GLM-5.2
Not ranked
Granite 4.2 3B
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
GLM-5.2
89.8
#22/123
Granite 4.2 3B
Not ranked
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

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.

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

GLM-5.2
$0.0036
Fits in one request
Granite 4.2 3B
Self-hosted; infrastructure cost varies
Fits in one request

Granite 4.2 3B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

GLM-5.2
$0.0832
Fits in one request
Granite 4.2 3B
Self-hosted; infrastructure cost varies
Fits in one request

Granite 4.2 3B has no comparable published API token rate.

Cache-heavy agent loop

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

GLM-5.2
$0.352
Fits in one request
Cached input priced at the published list-input rate
Granite 4.2 3B
Self-hosted; infrastructure cost varies
Does not fit in one request
Cached-input rate unavailable

Granite 4.2 3B does not fit this workload in one request. GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate. Granite 4.2 3B has no comparable published API token rate.

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.

GLM-5.2

Not published

Granite 4.2 3B

No comparable hosted API rate

IBM Granite 4.2 3B model card

Documented inputs

GLM-5.2

Not sourced

Granite 4.2 3B

Not sourced

Documented outputs

GLM-5.2

Not sourced

Granite 4.2 3B

Not sourced

Provider availability

GLM-5.2

Not sourced

Granite 4.2 3B

Not sourced

Reasoning profile

GLM-5.2

Reasoning

Granite 4.2 3B

Reasoning

Weight access

GLM-5.2

Open Weight

Granite 4.2 3B

Open Weight

License

GLM-5.2

Open Weight

Granite 4.2 3B

Open Weight

Release date

GLM-5.2

2026-06-16

Granite 4.2 3B

2026-08-25

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
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
GLM-5.2 has the larger documented window (1M).

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

Benchmark evidence

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

Browse raw public benchmark evidence33 rows

Agentic

  • Terminal-Bench 3.0

    GLM-5.24.6%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • Terminal-Bench 2.0

    GLM-5.281%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • MCP Atlas

    GLM-5.276.8%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • Toolathlon

    GLM-5.248.2%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • ResearchClawBench

    GLM-5.220.7%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    GLM-5.267.8%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • τ³-bench results

    GLM-5.2—
    Granite 4.2 3B45.8%
    Source

    Not directly comparable

  • BFCL v4

    GLM-5.2—
    Granite 4.2 3B52.4%
    Source

    Not directly comparable

Coding

  • SWE-bench Pro

    GLM-5.262.1%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • NL2Repo

    GLM-5.248.9%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • Terminal-Bench 2.0

    GLM-5.281.0%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • ProgramBench

    GLM-5.263.7%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • cursorBench32

    GLM-5.255.0%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • OpenHarmony Bench

    GLM-5.258.4%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • LiveCodeBench (Vals)

    GLM-5.269.5%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • SWE-bench (Vals)

    GLM-5.282.8%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • LiveCodeBench v6

    GLM-5.2—
    Granite 4.2 3B69.7%
    Source

    Not directly comparable

  • SciCode

    GLM-5.2—
    Granite 4.2 3B24.1%
    Source

    Not directly comparable

Reasoning

  • CritPt

    GLM-5.220.9%
    Source
    Granite 4.2 3B—

    Not directly comparable

Knowledge

  • GPQA

    GLM-5.291.2%
    Source
    Granite 4.2 3B54.8%
    Source

    GLM-5.2 leads this result

  • GPQA-D

    GLM-5.291.2%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • HLE

    GLM-5.254.7%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • HLE w/o tools

    GLM-5.240.5%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • GPQA Diamond (Vals)

    GLM-5.285.6%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • MMLU-Pro (Vals)

    GLM-5.286.7%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • MMLU-Pro

    GLM-5.2—
    Granite 4.2 3B67.8%
    Source

    Not directly comparable

Math

  • AIME26

    GLM-5.299.2%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • HMMT Nov 2025

    GLM-5.294.4%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • HMMT Feb 2026

    GLM-5.292.5%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • MMAnswerBench

    GLM-5.291.0%
    Source
    Granite 4.2 3B—

    Not directly comparable

  • AIME 2025

    GLM-5.2—
    Granite 4.2 3B78.3%
    Source

    Not directly comparable

  • HMMT Feb 2025

    GLM-5.2—
    Granite 4.2 3B66.7%
    Source

    Not directly comparable

Instruction following

  • IFBench

    GLM-5.2—
    Granite 4.2 3B74.3%
    Source

    Not directly comparable

Frequently asked questions

Which is better, GLM-5.2 or Granite 4.2 3B?

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, GLM-5.2 or Granite 4.2 3B?

Granite 4.2 3B is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, GLM-5.2 or Granite 4.2 3B?

Granite 4.2 3B is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, GLM-5.2 or Granite 4.2 3B?

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, GLM-5.2 or Granite 4.2 3B?

GLM-5.2 has the larger documented context window: 1M, compared with 128K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 10, 2026

Watch GLM-5.2 vs Granite 4.2 3B

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

Read a sample issue

Join 2,000+ readers.