Skip to main content
BenchLM
Data

GLM-5.2 vs Beam 1.0 501B-A23B

Updated November 19, 2026. Rank says GLM-5.2 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

GLM-5.2 has the higher public point estimate, 59.2 versus 47.3. Their conditional score ranges overlap. These ranges do not establish rank confidence. 9 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Z.AI logo

Z.AI

59.2/100

Supported · Public rank #64

90% interval 55.2–63.3

Model B

Reflection AI

47.3/100

Supported · Public rank #104

Conditional range 34.7–59.8

API price per 1M tokens

GLM-5.2: $1.40 input / $4.40 output

Beam 1.0 501B-A23B: No comparable API price

Context window

GLM-5.2: 1M

Beam 1.0 501B-A23B: 1M

Released

GLM-5.2: June 16, 2026

Beam 1.0 501B-A23B: October 16, 2026

Shared results
9
GLM-5.2 only
23
Beam 1.0 501B-A23B only
12
Like-for-like categories
1 / 8
Supported: GLM-5.2 and Beam 1.0 501B-A23B. Conditional ranges do not establish rank confidence.How 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.

  • Agentic work

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

    GLM-5.2

    GLM-5.2 has the higher public agentic point estimate, 61.9 to 55.2, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
Show secondary and unsupported calls
  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Beam 1.0 501B-A23B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited
  • 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: 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.

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

61.0GLM-5.239.2Beam 1.0 501B-A23B

Directional only · BenchAlign v6.0

GLM-5.2 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.

2 categories rest 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.

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
GLM-5.2
61.9
Supported · #51/177
Beam 1.0 501B-A23B
55.2
Supported · #76/177
Basis
BenchAlign v6.0 lane · 8 vs 7 public rows
Reading
GLM-5.2 leads · intervals overlap

Coding

Directional only
GLM-5.2
61.0
Supported · #47/177
Beam 1.0 501B-A23B
39.2
Estimated · #139/177
Basis
BenchAlign v6.0 lane · 11 vs 8 public rows
Reading
Directional only

Instruction following

Directional only
GLM-5.2
55.1
Supported · #49/142
Beam 1.0 501B-A23B
44.8
Estimated · #95/142
Basis
BenchAlign v6.0 lane · 0 vs 1 public rows
Reading
Directional only

Reasoning

Not comparable
GLM-5.2
52.5
Supported · #67/160
Beam 1.0 501B-A23B
Not ranked
Basis
BenchAlign v6.0 lane · 1 vs 2 public rows
Reading
Not comparable

Multimodal

Not comparable
GLM-5.2
60.1
Estimated · #53/115
Beam 1.0 501B-A23B
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Knowledge

Not comparable
GLM-5.2
55.9
Estimated · #60/156
Beam 1.0 501B-A23B
Not ranked
Basis
BenchAlign v6.0 lane · 6 vs 2 public rows
Reading
Not comparable

Multilingual

Not comparable
GLM-5.2
Not ranked
Beam 1.0 501B-A23B
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Math

Not comparable
GLM-5.2
57.3
Supported · #43/124
Beam 1.0 501B-A23B
Not ranked
Basis
BenchAlign v6.0 lane · 6 vs 1 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

GLM-5.2
$0.0036
Fits in one request
Beam 1.0 501B-A23B
API rate not published
Fits in one request

Beam 1.0 501B-A23B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

GLM-5.2
$0.0832
Fits in one request
Beam 1.0 501B-A23B
API rate not published
Fits in one request

Beam 1.0 501B-A23B 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
Beam 1.0 501B-A23B
API rate not published
Fits in one request
Cached-input rate unavailable

GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate. Beam 1.0 501B-A23B 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 18, 2026.

GLM-5.2

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • 12 cheaper models score at least as high as GLM-5.2. The nearest is Muse Spark 1.2 (score 59.9, $4.25 per 1M output tokens).
  • Beam 1.0 501B-A23B 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 GLM-5.2 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.

GLM-5.2

Not published

Beam 1.0 501B-A23B

No comparable hosted API rate

Reflection launch post

Provider availability

GLM-5.2

Not sourced

Beam 1.0 501B-A23B

Open Weights · Hugging Face, self-hosted inference, Reflection API public beta, partner endpoints

Reflection Beam 1.0 BF16 model card

Reasoning profile

GLM-5.2

Reasoning

Beam 1.0 501B-A23B

Reasoning

Weight access

GLM-5.2

Open Weight

Beam 1.0 501B-A23B

Open Weight

License

GLM-5.2

Open Weight

Beam 1.0 501B-A23B

Open Weight

Release date

GLM-5.2

2026-06-16

Beam 1.0 501B-A23B

2026-10-16

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-5.2 has the higher public point estimate, 59.2 versus 47.3. Their conditional score ranges overlap. These ranges do not establish rank confidence.
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, GLM-5.2 or Beam 1.0 501B-A23B?

GLM-5.2 has the higher public point estimate, 59.2 versus 47.3. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, GLM-5.2 or Beam 1.0 501B-A23B?

GLM-5.2 scores higher for coding on the public lane, 61 to 39.2. Beam 1.0 501B-A23B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, GLM-5.2 or Beam 1.0 501B-A23B?

GLM-5.2 has the higher public agentic tasks point estimate, 61.9 to 55.2, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which costs less, GLM-5.2 or Beam 1.0 501B-A23B?

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 Beam 1.0 501B-A23B?

Both models list the same context window, 1M.

Self-host vs API cost

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

GLM-5.2
API / mo$4,350
Self-host / mo$27,962
Break-evenNot reached at 70% load
Beam 1.0 501B-A23B
API / mo (Nebius Token Factory)$938
Self-host / mo$7,008
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 evidence44 rows

Agentic

  • Terminal-Bench 3.0

    GLM-5.24.6%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • Terminal-Bench 2.1

    GLM-5.281.0%
    Source
    Beam 1.0 501B-A23B80.1%
    Source

    GLM-5.2 leads this result

  • MCP Atlas

    GLM-5.276.8%
    Source
    Beam 1.0 501B-A23B80.8%
    Source

    Beam 1.0 501B-A23B leads this result

  • Toolathlon

    GLM-5.248.2%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • ResearchClawBench

    GLM-5.220.7%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    GLM-5.267.8%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • HLE w/ tools

    GLM-5.254.7%
    Source
    Beam 1.0 501B-A23B51.1%
    Source

    GLM-5.2 leads this result

  • MazeBench

    GLM-5.20%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • Terminal-Bench 4.1

    GLM-5.2—
    Beam 1.0 501B-A23B6.40%
    Source

    Not directly comparable

  • τ³-bench results

    GLM-5.2—
    Beam 1.0 501B-A23B36.1%
    Source

    Not directly comparable

  • BrowseComp

    GLM-5.2—
    Beam 1.0 501B-A23B76.8%
    Source

    Not directly comparable

  • DeepSearchQA

    GLM-5.2—
    Beam 1.0 501B-A23B80.5%
    Source

    Not directly comparable

Coding

  • SWE-bench Pro

    GLM-5.262.1%
    Source
    Beam 1.0 501B-A23B66.1%
    Source

    Beam 1.0 501B-A23B leads this result

  • NL2Repo

    GLM-5.248.9%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • Terminal-Bench 2.1

    GLM-5.281.0%
    Source
    Beam 1.0 501B-A23B80.1%
    Source

    GLM-5.2 leads this result

  • ProgramBench

    GLM-5.263.7%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • CursorBench 3.2

    GLM-5.255.0%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • OpenHarmony Bench v1.0

    GLM-5.258.4%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • LiveCodeBench (Vals)

    GLM-5.269.5%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • SWE-bench (Vals)

    GLM-5.282.8%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • PostTrainBench v1.1

    GLM-5.231.7%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • PostTrainBench

    GLM-5.230.4%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • PostTrainBench v1

    GLM-5.234.3%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • DeepSWE

    GLM-5.2—
    Beam 1.0 501B-A23B43.3%
    Source

    Not directly comparable

  • SWE-Atlas Codebase QnA

    GLM-5.2—
    Beam 1.0 501B-A23B31.8%
    Source

    Not directly comparable

  • SWE Multilingual

    GLM-5.2—
    Beam 1.0 501B-A23B78.3%
    Source

    Not directly comparable

  • SWE-bench Verified

    GLM-5.2—
    Beam 1.0 501B-A23B81.6%
    Source

    Not directly comparable

  • SciCode

    GLM-5.2—
    Beam 1.0 501B-A23B49.2%
    Source

    Not directly comparable

  • VulcanBench Frontier v4

    GLM-5.2—
    Beam 1.0 501B-A23B64.7%
    Source

    Not directly comparable

Reasoning

  • CritPt

    GLM-5.220.9%
    Source
    Beam 1.0 501B-A23B16.3%
    Source

    GLM-5.2 leads this result

  • LongBench v2

    GLM-5.2—
    Beam 1.0 501B-A23B67.5%
    Source

    Not directly comparable

Knowledge

  • GPQA

    GLM-5.291.2%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • GPQA-D

    GLM-5.291.2%
    Source
    Beam 1.0 501B-A23B90.6%
    Source

    GLM-5.2 leads this result

  • HLE

    GLM-5.240.5%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • HLE w/o tools

    GLM-5.240.5%
    Source
    Beam 1.0 501B-A23B36%
    Source

    GLM-5.2 leads this result

  • GPQA Diamond (Vals)

    GLM-5.285.6%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • MMLU-Pro (Vals)

    GLM-5.286.7%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

Instruction following

  • IFBench

    GLM-5.2—
    Beam 1.0 501B-A23B79.6%
    Source

    Not directly comparable

Math

  • AIME26

    GLM-5.299.2%
    Source
    Beam 1.0 501B-A23B97.7%
    Source

    GLM-5.2 leads this result

  • HMMT Nov 2025

    GLM-5.294.4%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • HMMT Feb 2026

    GLM-5.292.5%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • MMAnswerBench

    GLM-5.291.0%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    GLM-5.259.206%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    GLM-5.229.268%
    Source
    Beam 1.0 501B-A23B—

    Not directly comparable

44 public results · 9 shared

Watch GLM-5.2 vs Beam 1.0 501B-A23B

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 19, 2026