Agentic
Directional only- GLM-4.7
- 45.7
- GLM-5
- 56.2
- Weighted basis
- 2 vs 1 rows
- Reading
- Directional only
GLM-4.7 vs GLM-5
Updated September 3, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
GLM-5 has the higher public score estimate, 65.68 versus 60.91, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
9 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.
No workload recommendation clears the current evidence threshold.
Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.
Show secondary and unsupported calls
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
The category averages use different weighted benchmark sets, so they are 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
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. GLM-4.7 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. GLM-4.7 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.
4 GLM-4.7 only
9 Shared
27 GLM-5 only
- Shared results
- 9
- GLM-4.7 only
- 4
- GLM-5 only
- 27
- Like-for-like categories
- 0 / 8
4 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.
Coding
Directional only- GLM-4.7
- 75.4
- GLM-5
- 66.3
- Weighted basis
- 3 vs 3 rows
- Reading
- Directional only
Knowledge
Directional only- GLM-4.7
- 51.8
- GLM-5
- 66.4
- Weighted basis
- 3 vs 4 rows
- Reading
- Directional only
Math
Directional only- GLM-4.7
- 1.8
- GLM-5
- 56.3
- Weighted basis
- 2 vs 4 rows
- Reading
- Directional only
Reasoning
Not comparable- GLM-4.7
- Not measured
- GLM-5
- 60.8
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-4.7
- Not measured
- GLM-5
- 83.1
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-4.7
- Not measured
- GLM-5
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- GLM-4.7
- Not measured
- GLM-5
- 92.6
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
| Category | GLM-4.7 | GLM-5 | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 45.7 | 56.2 | Directional only2 vs 1 rows | Directional only |
| Coding | 75.4 | 66.3 | Directional only3 vs 3 rows | Directional only |
| Knowledge | 51.8 | 66.4 | Directional only3 vs 4 rows | Directional only |
| Math | 1.8 | 56.3 | Directional only2 vs 4 rows | Directional only |
| Reasoning | Not measured | 60.8 | Not comparable0 vs 1 rows | Not comparable |
| Multilingual | Not measured | 83.1 | Not comparable0 vs 1 rows | Not comparable |
| Multimodal | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Instruction following | Not measured | 92.6 | Not comparable0 vs 1 rows | 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.
HLE
Knowledge
Terminal-Bench 2.0
Agentic
FrontierMath v2 (Tiers 1-3)
Math
SWE-Rebench
Coding
SWE-bench Verified
Coding
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-4.7
- Self-hosted; infrastructure cost varies
- Fits in one request
- GLM-5
- $0.0026
- Fits in one request
GLM-4.7 has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- GLM-4.7
- Self-hosted; infrastructure cost varies
- Fits in one request
- GLM-5
- $0.0596
- Fits in one request
GLM-4.7 has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GLM-4.7
- Self-hosted; infrastructure cost varies
- 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
GLM-4.7 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. GLM-4.7 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.
SpecificationGLM-4.7GLM-5
Context window
Maximum documented context; output-token limits may be lower.
GLM-4.7
200K
GLM-5
200K
API model ID
GLM-4.7
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.
GLM-4.7
No comparable hosted API rate
GLM-5
Not published
Documented inputs
GLM-4.7
Not sourced
GLM-5
Not sourced
Documented outputs
GLM-4.7
Not sourced
GLM-5
Not sourced
Provider availability
GLM-4.7
Not sourced
GLM-5
Not sourced
Reasoning profile
GLM-4.7
Reasoning
GLM-5
Non-Reasoning
Weight access
GLM-4.7
Open Weight
GLM-5
Open Weight
License
GLM-4.7
Open Weight
GLM-5
Open Weight
Release date
GLM-4.7
2025-10-01
GLM-5
2026-03-01
If you already use one of these models
- Deployment change
- Both entries list Z.AI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- GLM-5 has the higher public score estimate, 65.68 versus 60.91, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- 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 evidence40 rows
Agentic
Terminal-Bench 2.0
GLM-4.741%SourceGLM-556.2%SourceGLM-5 leads this result
BrowseComp
GLM-4.752%SourceGLM-5—Not directly comparable
VITA-Bench
GLM-4.715.5%SourceGLM-5—Not directly comparable
Gert Labs
Shared sourceGLM-4.739.95%GLM-550.99%GLM-5 leads this result
Claw-Eval
GLM-4.7—GLM-557.7%SourceNot directly comparable
QwenClawBench
GLM-4.7—GLM-554.1%SourceNot directly comparable
τ³-bench results
GLM-4.7—GLM-565.6%SourceNot directly comparable
DeepPlanning
GLM-4.7—GLM-514.6%SourceNot directly comparable
Toolathlon
GLM-4.7—GLM-538%SourceNot directly comparable
MCP Atlas
GLM-4.7—GLM-531.1%SourceNot directly comparable
MCP-Tasks
GLM-4.7—GLM-560.8%SourceNot directly comparable
WideResearch
GLM-4.7—GLM-569.8%SourceNot directly comparable
CyberGym
GLM-4.7—GLM-543.2%SourceNot directly comparable
Coding
SWE-bench Verified
GLM-4.773.8%SourceGLM-577.8%SourceGLM-5 leads this result
LiveCodeBench
GLM-4.784.9%SourceGLM-5—Not directly comparable
SWE-Rebench
GLM-4.758.7%SourceGLM-562.8%SourceGLM-5 leads this result
SWE-bench Verified*
GLM-4.7—GLM-572.8%SourceNot directly comparable
SWE-bench Pro
GLM-4.7—GLM-555.1%SourceNot directly comparable
SWE Multilingual
GLM-4.7—GLM-573.3%SourceNot directly comparable
React Native Evals
GLM-4.7—GLM-574.8%SourceNot directly comparable
Reasoning
Knowledge
GPQA
GLM-4.785.7%SourceGLM-586%SourceGLM-5 leads this result
MMLU-Pro
GLM-4.784.3%SourceGLM-585.7%SourceGLM-5 leads this result
HLE
GLM-4.724.8%SourceGLM-550.4%SourceGLM-5 leads this result
GPQA-D
GLM-4.7—GLM-586.0%SourceNot directly comparable
SuperGPQA
GLM-4.7—GLM-566.8%SourceNot directly comparable
MMLU-Pro (Arcee)
GLM-4.7—GLM-585.8%SourceNot directly comparable
Math
AIME 2025
GLM-4.795.7%SourceGLM-5—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared sourceGLM-4.72.439%GLM-516.434%GLM-5 leads this result
FrontierMath v2 (Tier 4)
Shared sourceGLM-4.70.000%GLM-52.100%GLM-5 leads this result
AIME26
GLM-4.7—GLM-595.8%SourceNot directly comparable
AIME25 (Arcee)
GLM-4.7—GLM-593.3%SourceNot directly comparable
HMMT Feb 2025
GLM-4.7—GLM-597.5%SourceNot directly comparable
HMMT Nov 2025
GLM-4.7—GLM-596.9%SourceNot directly comparable
HMMT Feb 2026
GLM-4.7—GLM-586.4%SourceNot directly comparable
MMAnswerBench
GLM-4.7—GLM-582.5%SourceNot directly comparable
Multilingual
Instruction following
IFEval
GLM-4.7—GLM-592.6%SourceNot directly comparable
Frequently asked questions
Which is better, GLM-4.7 or GLM-5?
GLM-5 has the higher public score estimate, 65.68 versus 60.91, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, GLM-4.7 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, GLM-4.7 or GLM-5?
The current agentic tasks 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 costs less, GLM-4.7 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, GLM-4.7 or GLM-5?
Both models list the same context window, 200K.
Related comparisons
Last updated September 3, 2026
Watch GLM-4.7 vs GLM-5
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.