Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

See the free Radar Brief
BenchLM
Anthropic logo
Model A
Claude 4 Sonnet

Anthropic

41.9/100

Supported · Public rank #197

90% interval 38.5–45.3

Claude 4 Sonnet vs GLM-5

Updated September 3, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Z.AI logo
Model B
GLM-5

Z.AI

65.68/100

Supported · Public rank #43

90% interval 53.6–77.8

Decision reading

GLM-5 has the higher public score, 65.68 versus 41.9, and the 90% score intervals do not overlap.

2 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.

  • Chat turn cost

    1K fresh input + 500 output tokens

    GLM-5

    GLM-5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    GLM-5

    GLM-5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.

    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

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

  • 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. Claude 4 Sonnet does not fit this workload in one request. GLM-5 does not fit this workload in one request. Claude 4 Sonnet has no published cached-input rate, so cached tokens use its listed input rate. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

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
2
Claude 4 Sonnet only
1
GLM-5 only
34
Like-for-like categories
0 / 8

1 category uses 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.

Coding

Directional only
Claude 4 Sonnet
72.7
GLM-5
66.3
Weighted basis
1 vs 3 rows
Reading
Directional only

Agentic

Not comparable
Claude 4 Sonnet
Not measured
GLM-5
56.2
Weighted basis
0 vs 1 rows
Reading
Not comparable

Reasoning

Not comparable
Claude 4 Sonnet
Not measured
GLM-5
60.8
Weighted basis
0 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
Claude 4 Sonnet
Not measured
GLM-5
66.4
Weighted basis
0 vs 4 rows
Reading
Not comparable

Math

Not comparable
Claude 4 Sonnet
Not measured
GLM-5
56.3
Weighted basis
0 vs 4 rows
Reading
Not comparable

Multilingual

Not comparable
Claude 4 Sonnet
Not measured
GLM-5
83.1
Weighted basis
0 vs 1 rows
Reading
Not comparable

Multimodal

Not comparable
Claude 4 Sonnet
Not measured
GLM-5
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Claude 4 Sonnet
Not measured
GLM-5
92.6
Weighted basis
0 vs 1 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

Claude 4 Sonnet
$0.0105
Fits in one request
GLM-5
$0.0026
Fits in one request

GLM-5 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude 4 Sonnet
$0.195
Fits in one request
GLM-5
$0.0596
Fits in one request

GLM-5 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Claude 4 Sonnet
$0.81
Does not fit in one request
Cached input priced at the published list-input rate
GLM-5
$0.252
Does not fit in one request
Cached input priced at the published list-input rate

Claude 4 Sonnet does not fit this workload in one request. GLM-5 does not fit this workload in one request. Claude 4 Sonnet has no published cached-input rate, so cached tokens use its listed input rate. GLM-5 has no published cached-input rate, so cached tokens use its listed input 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.

Claude 4 Sonnet

200K

GLM-5

200K

API model ID

Claude 4 Sonnet

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.

Claude 4 Sonnet

Not published

GLM-5

Not published

Documented inputs

Claude 4 Sonnet

Not sourced

GLM-5

Not sourced

Documented outputs

Claude 4 Sonnet

Not sourced

GLM-5

Not sourced

Provider availability

Claude 4 Sonnet

Not sourced

GLM-5

Not sourced

Reasoning profile

Claude 4 Sonnet

Non-Reasoning

GLM-5

Non-Reasoning

Weight access

Claude 4 Sonnet

Proprietary

GLM-5

Open Weight

License

Claude 4 Sonnet

Proprietary

GLM-5

Open Weight

Release date

Claude 4 Sonnet

2025-05-01

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, 65.68 versus 41.9, and the 90% score intervals do not overlap.
Workload cost
Repository review: $0.195 vs $0.0596. Cache-heavy agent loop: $0.81 vs $0.252.
Context tradeoff
Both models list 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 evidence37 rows

Agentic

  • Gert Labs

    Shared source
    Claude 4 Sonnet39.66%
    GLM-550.99%

    GLM-5 leads this result

  • JobBench

    Claude 4 Sonnet18.4%
    Source
    GLM-5—

    Not directly comparable

  • Terminal-Bench 2.0

    Claude 4 Sonnet—
    GLM-556.2%
    Source

    Not directly comparable

  • Claw-Eval

    Claude 4 Sonnet—
    GLM-557.7%
    Source

    Not directly comparable

  • QwenClawBench

    Claude 4 Sonnet—
    GLM-554.1%
    Source

    Not directly comparable

  • τ³-bench results

    Claude 4 Sonnet—
    GLM-565.6%
    Source

    Not directly comparable

  • DeepPlanning

    Claude 4 Sonnet—
    GLM-514.6%
    Source

    Not directly comparable

  • Toolathlon

    Claude 4 Sonnet—
    GLM-538%
    Source

    Not directly comparable

  • MCP Atlas

    Claude 4 Sonnet—
    GLM-531.1%
    Source

    Not directly comparable

  • MCP-Tasks

    Claude 4 Sonnet—
    GLM-560.8%
    Source

    Not directly comparable

  • WideResearch

    Claude 4 Sonnet—
    GLM-569.8%
    Source

    Not directly comparable

  • CyberGym

    Claude 4 Sonnet—
    GLM-543.2%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Claude 4 Sonnet72.7%
    Source
    GLM-577.8%
    Source

    GLM-5 leads this result

  • SWE-bench Verified*

    Claude 4 Sonnet—
    GLM-572.8%
    Source

    Not directly comparable

  • SWE-bench Pro

    Claude 4 Sonnet—
    GLM-555.1%
    Source

    Not directly comparable

  • SWE Multilingual

    Claude 4 Sonnet—
    GLM-573.3%
    Source

    Not directly comparable

  • SWE-Rebench

    Claude 4 Sonnet—
    GLM-562.8%
    Source

    Not directly comparable

  • React Native Evals

    Claude 4 Sonnet—
    GLM-574.8%
    Source

    Not directly comparable

Reasoning

  • LongBench v2

    Claude 4 Sonnet—
    GLM-560.8%
    Source

    Not directly comparable

  • AI-Needle

    Claude 4 Sonnet—
    GLM-563.3%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Claude 4 Sonnet—
    GLM-586%
    Source

    Not directly comparable

  • GPQA-D

    Claude 4 Sonnet—
    GLM-586.0%
    Source

    Not directly comparable

  • SuperGPQA

    Claude 4 Sonnet—
    GLM-566.8%
    Source

    Not directly comparable

  • MMLU-Pro

    Claude 4 Sonnet—
    GLM-585.7%
    Source

    Not directly comparable

  • MMLU-Pro (Arcee)

    Claude 4 Sonnet—
    GLM-585.8%
    Source

    Not directly comparable

  • HLE

    Claude 4 Sonnet—
    GLM-550.4%
    Source

    Not directly comparable

Math

  • AIME26

    Claude 4 Sonnet—
    GLM-595.8%
    Source

    Not directly comparable

  • AIME25 (Arcee)

    Claude 4 Sonnet—
    GLM-593.3%
    Source

    Not directly comparable

  • HMMT Feb 2025

    Claude 4 Sonnet—
    GLM-597.5%
    Source

    Not directly comparable

  • HMMT Nov 2025

    Claude 4 Sonnet—
    GLM-596.9%
    Source

    Not directly comparable

  • HMMT Feb 2026

    Claude 4 Sonnet—
    GLM-586.4%
    Source

    Not directly comparable

  • MMAnswerBench

    Claude 4 Sonnet—
    GLM-582.5%
    Source

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Claude 4 Sonnet—
    GLM-516.434%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Claude 4 Sonnet—
    GLM-52.100%
    Source

    Not directly comparable

Multilingual

  • MMLU-ProX

    Claude 4 Sonnet—
    GLM-583.1%
    Source

    Not directly comparable

  • NOVA-63

    Claude 4 Sonnet—
    GLM-555.1%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Claude 4 Sonnet—
    GLM-592.6%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Claude 4 Sonnet or GLM-5?

GLM-5 has the higher public score, 65.68 versus 41.9, 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, Claude 4 Sonnet or GLM-5?

The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Claude 4 Sonnet or GLM-5?

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, Claude 4 Sonnet or GLM-5?

For the stated presets, chat costs $0.0105 on Claude 4 Sonnet and $0.0026 on GLM-5; repository review costs $0.195 and $0.0596; the cache-heavy agent loop costs $0.81 and $0.252. Claude 4 Sonnet does not fit this workload in one request. GLM-5 does not fit this workload in one request. Claude 4 Sonnet has no published cached-input rate, so cached tokens use its listed input rate. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude 4 Sonnet or GLM-5?

Both models list the same context window, 200K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 3, 2026

Watch Claude 4 Sonnet 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.