Skip to main content
BenchLM
Advertise

Model comparison

GLM-5 vs ZAYA1-8B

Updated August 5, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

GLM-5

Z.AI

65.3/100

Supported · Public rank #32

90% interval 54.5–76.1

ZAYA1-8B

Zyphra

31.6/100

Estimated · Public rank #201

90% interval 21.7–41.5

GLM-5 has the higher public score, 65.33 versus 31.58, and the 90% score intervals do not overlap.

6 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

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

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    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. GLM-5 does not fit this workload in one request. ZAYA1-8B does not fit this workload in one request. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate. ZAYA1-8B 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
6
GLM-5 only
30
ZAYA1-8B only
5
Like-for-like categories
0 / 8

3 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Knowledge

Directional only
GLM-5
66.4
ZAYA1-8B
73.6
Weighted basis
4 vs 2 rows
Reading
Directional only

Math

Directional only
GLM-5
56.3
ZAYA1-8B
80.4
Weighted basis
4 vs 2 rows
Reading
Directional only

Instruction following

Directional only
GLM-5
92.6
ZAYA1-8B
64.1
Weighted basis
1 vs 2 rows
Reading
Directional only

Agentic

Not comparable
GLM-5
56.2
ZAYA1-8B
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Coding

Not comparable
GLM-5
66.3
ZAYA1-8B
Not measured
Weighted basis
3 vs 0 rows
Reading
Not comparable

Reasoning

Not comparable
GLM-5
60.8
ZAYA1-8B
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
GLM-5
83.1
ZAYA1-8B
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
GLM-5
Not measured
ZAYA1-8B
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

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
$0.0026
Fits in one request
ZAYA1-8B
Self-hosted; infrastructure cost varies
Fits in one request

ZAYA1-8B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

GLM-5
$0.0596
Fits in one request
ZAYA1-8B
Self-hosted; infrastructure cost varies
Fits in one request

ZAYA1-8B has no comparable published API token rate.

Cache-heavy agent loop

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

GLM-5
$0.252
Does not fit in one request
Cached input priced at the published list-input rate
ZAYA1-8B
Self-hosted; infrastructure cost varies
Does not fit in one request
Cached-input rate unavailable

GLM-5 does not fit this workload in one request. ZAYA1-8B does not fit this workload in one request. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate. ZAYA1-8B 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.

Context window

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

GLM-5

200K

ZAYA1-8B

131K

API model ID

GLM-5

Not sourced

ZAYA1-8B

Not sourced

Cached-input rate

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

GLM-5

Not published

ZAYA1-8B

No comparable hosted API rate

Documented inputs

GLM-5

Not sourced

ZAYA1-8B

Not sourced

Documented outputs

GLM-5

Not sourced

ZAYA1-8B

Not sourced

Provider availability

GLM-5

Not sourced

ZAYA1-8B

Not sourced

Reasoning profile

GLM-5

Non-Reasoning

ZAYA1-8B

Reasoning

Weight access

GLM-5

Open Weight

ZAYA1-8B

Open Weight

License

GLM-5

Open Weight

ZAYA1-8B

Open Weight

Release date

GLM-5

2026-03-01

ZAYA1-8B

2026-05-05

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, 65.33 versus 31.58, 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.

Benchmark evidence

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

Browse raw public benchmark evidence41 rows

Agentic

  • Terminal-Bench 2.0

    GLM-556.2%
    Source
    ZAYA1-8B—

    Not directly comparable

  • Claw-Eval

    GLM-557.7%
    Source
    ZAYA1-8B—

    Not directly comparable

  • QwenClawBench

    GLM-554.1%
    Source
    ZAYA1-8B—

    Not directly comparable

  • τ³-bench results

    GLM-565.6%
    Source
    ZAYA1-8B—

    Not directly comparable

  • DeepPlanning

    GLM-514.6%
    Source
    ZAYA1-8B—

    Not directly comparable

  • Toolathlon

    GLM-538%
    Source
    ZAYA1-8B—

    Not directly comparable

  • MCP Atlas

    GLM-531.1%
    Source
    ZAYA1-8B—

    Not directly comparable

  • MCP-Tasks

    GLM-560.8%
    Source
    ZAYA1-8B—

    Not directly comparable

  • WideResearch

    GLM-569.8%
    Source
    ZAYA1-8B—

    Not directly comparable

  • CyberGym

    GLM-543.2%
    Source
    ZAYA1-8B—

    Not directly comparable

  • Gert Labs

    GLM-550.99%
    Source
    ZAYA1-8B—

    Not directly comparable

  • BFCL v4

    GLM-5—
    ZAYA1-8B39.2%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    GLM-577.8%
    Source
    ZAYA1-8B—

    Not directly comparable

  • SWE-bench Verified*

    GLM-572.8%
    Source
    ZAYA1-8B—

    Not directly comparable

  • SWE-bench Pro

    GLM-555.1%
    Source
    ZAYA1-8B—

    Not directly comparable

  • SWE Multilingual

    GLM-573.3%
    Source
    ZAYA1-8B—

    Not directly comparable

  • SWE-Rebench

    GLM-562.8%
    Source
    ZAYA1-8B—

    Not directly comparable

  • React Native Evals

    GLM-574.8%
    Source
    ZAYA1-8B—

    Not directly comparable

  • LiveCodeBench v6

    GLM-5—
    ZAYA1-8B65.8%
    Source

    Not directly comparable

Reasoning

  • LongBench v2

    GLM-560.8%
    Source
    ZAYA1-8B—

    Not directly comparable

  • AI-Needle

    GLM-563.3%
    Source
    ZAYA1-8B—

    Not directly comparable

Knowledge

  • GPQA

    GLM-586%
    Source
    ZAYA1-8B71%
    Source

    GLM-5 leads this result

  • GPQA-D

    GLM-586.0%
    Source
    ZAYA1-8B71.0%
    Source

    GLM-5 leads this result

  • SuperGPQA

    GLM-566.8%
    Source
    ZAYA1-8B—

    Not directly comparable

  • MMLU-Pro

    GLM-585.7%
    Source
    ZAYA1-8B74.2%
    Source

    GLM-5 leads this result

  • MMLU-Pro (Arcee)

    GLM-585.8%
    Source
    ZAYA1-8B—

    Not directly comparable

  • HLE

    GLM-550.4%
    Source
    ZAYA1-8B—

    Not directly comparable

Math

  • AIME26

    GLM-595.8%
    Source
    ZAYA1-8B89.1%
    Source

    GLM-5 leads this result

  • AIME25 (Arcee)

    GLM-593.3%
    Source
    ZAYA1-8B—

    Not directly comparable

  • HMMT Feb 2025

    GLM-597.5%
    Source
    ZAYA1-8B—

    Not directly comparable

  • HMMT Nov 2025

    GLM-596.9%
    Source
    ZAYA1-8B—

    Not directly comparable

  • HMMT Feb 2026

    GLM-586.4%
    Source
    ZAYA1-8B71.6%
    Source

    GLM-5 leads this result

  • MMAnswerBench

    GLM-582.5%
    Source
    ZAYA1-8B—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    GLM-516.434%
    Source
    ZAYA1-8B—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    GLM-52.100%
    Source
    ZAYA1-8B—

    Not directly comparable

  • IMOAnswerBench

    GLM-5—
    ZAYA1-8B59.3%
    Source

    Not directly comparable

  • Apex

    GLM-5—
    ZAYA1-8B32.2%
    Source

    Not directly comparable

Multilingual

  • MMLU-ProX

    GLM-583.1%
    Source
    ZAYA1-8B—

    Not directly comparable

  • NOVA-63

    GLM-555.1%
    Source
    ZAYA1-8B—

    Not directly comparable

Instruction following

  • IFEval

    GLM-592.6%
    Source
    ZAYA1-8B85.6%
    Source

    GLM-5 leads this result

  • IFBench

    GLM-5—
    ZAYA1-8B52.6%
    Source

    Not directly comparable

Frequently asked questions

Which is better, GLM-5 or ZAYA1-8B?

GLM-5 has the higher public score, 65.33 versus 31.58, 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, GLM-5 or ZAYA1-8B?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

Which is better for agentic tasks, GLM-5 or ZAYA1-8B?

The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.

Which costs less, GLM-5 or ZAYA1-8B?

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 or ZAYA1-8B?

GLM-5 has the larger documented context window: 200K, compared with 131K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 5, 2026

Watch GLM-5 vs ZAYA1-8B

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

Read a sample issue

Join 2,000+ readers.