Knowledge
Directional only- GLM-5
- 54.1
- Estimated · #57/183
- GLM-5-Turbo
- 53.9
- Estimated · #62/183
- Basis
- BenchAlign lane · 6 vs 0 public rows
- Reading
- Directional only
GLM-5 vs GLM-5-Turbo
Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload. This is a same-family comparison, so migration details appear when the source data supports them.
Decision reading
GLM-5-Turbo has the higher public score estimate, 61.64 versus 61.45, but the 90% score intervals overlap. Treat that as a lead, not a settled 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
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
GLM-5-Turbo 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
GLM-5-Turbo is not ranked on the public lane for agentic, so no winner is named for agentic.
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. GLM-5 does not fit this workload in one request. GLM-5-Turbo 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-5-Turbo 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.
35 GLM-5 only
1 Shared
- Shared results
- 1
- GLM-5 only
- 35
- GLM-5-Turbo only
- 0
- Like-for-like categories
- 0 / 8
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
Instruction following
Directional only- GLM-5
- 88.5
- #31/123
- GLM-5-Turbo
- 89.7
- #24/123
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Agentic
Not comparable- GLM-5
- 51.0
- Estimated · #45/152
- GLM-5-Turbo
- Not ranked
- Basis
- BenchAlign lane · 11 vs 1 public rows
- Reading
- Not comparable
Coding
Not comparable- GLM-5
- 56.1
- Estimated · #39/151
- GLM-5-Turbo
- Not ranked
- Basis
- BenchAlign lane · 6 vs 0 public rows
- Reading
- Not comparable
Reasoning
Not comparable- GLM-5
- 52.1
- Unranked · 4 rankable rows
- GLM-5-Turbo
- 70.3
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- GLM-5
- 56.9
- #7/7
- GLM-5-Turbo
- Not ranked
- Basis
- Provisional lane · 4 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-5
- 48.7
- #6/12
- GLM-5-Turbo
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-5
- Not ranked
- GLM-5-Turbo
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | GLM-5 | GLM-5-Turbo | Basis | Reading |
|---|---|---|---|---|
| Knowledge | 54.1Estimated · #57/183 | 53.9Estimated · #62/183 | Directional onlyBenchAlign lane · 6 vs 0 public rows | Directional only |
| Instruction following | 88.5#31/123 | 89.7#24/123 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Agentic | 51.0Estimated · #45/152 | Not ranked | Not comparableBenchAlign lane · 11 vs 1 public rows | Not comparable |
| Coding | 56.1Estimated · #39/151 | Not ranked | Not comparableBenchAlign lane · 6 vs 0 public rows | Not comparable |
| Reasoning | 52.1Unranked · 4 rankable rows | 70.3Unranked · 2 rankable rows | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Math | 56.9#7/7 | Not ranked | Not comparableProvisional lane · 4 vs 0 weighted rows | Not comparable |
| Multilingual | 48.7#6/12 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | 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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
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
- GLM-5-Turbo
- $0.0032
- 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
- GLM-5
- $0.0596
- Fits in one request
- GLM-5-Turbo
- $0.072
- 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
- GLM-5
- $0.252
- Does not fit in one request
- Cached input priced at the published list-input rate
- GLM-5-Turbo
- $0.304
- Does not fit in one request
- Cached input priced at the published list-input rate
GLM-5 does not fit this workload in one request. GLM-5-Turbo 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-5-Turbo 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.
SpecificationGLM-5GLM-5-Turbo
Context window
Maximum documented context; output-token limits may be lower.
GLM-5
200K
GLM-5-Turbo
200K
API model ID
GLM-5
Not sourced
GLM-5-Turbo
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
GLM-5-Turbo
Not published
Documented inputs
GLM-5
Not sourced
GLM-5-Turbo
Not sourced
Documented outputs
GLM-5
Not sourced
GLM-5-Turbo
Not sourced
Provider availability
GLM-5
Not sourced
GLM-5-Turbo
Not sourced
Reasoning profile
GLM-5
Non-Reasoning
GLM-5-Turbo
Reasoning
Weight access
GLM-5
Open Weight
GLM-5-Turbo
Proprietary
License
GLM-5
Open Weight
GLM-5-Turbo
Proprietary
Release date
GLM-5
2026-03-01
GLM-5-Turbo
2026-03-01
If you are choosing between sibling variants
- Deployment change
- Both entries list Z.AI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- GLM-5-Turbo has the higher public score estimate, 61.64 versus 61.45, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.0596 vs $0.072. Cache-heavy agent loop: $0.252 vs $0.304.
- 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 evidence36 rows
Agentic
Terminal-Bench 2.0
GLM-556.2%SourceGLM-5-Turbo—Not directly comparable
Claw-Eval
GLM-557.7%SourceGLM-5-Turbo55.8%SourceGLM-5 leads this result
QwenClawBench
GLM-554.1%SourceGLM-5-Turbo—Not directly comparable
τ³-bench results
GLM-565.6%SourceGLM-5-Turbo—Not directly comparable
DeepPlanning
GLM-514.6%SourceGLM-5-Turbo—Not directly comparable
Toolathlon
GLM-538%SourceGLM-5-Turbo—Not directly comparable
MCP Atlas
GLM-531.1%SourceGLM-5-Turbo—Not directly comparable
MCP-Tasks
GLM-560.8%SourceGLM-5-Turbo—Not directly comparable
WideResearch
GLM-569.8%SourceGLM-5-Turbo—Not directly comparable
CyberGym
GLM-543.2%SourceGLM-5-Turbo—Not directly comparable
Gert Labs
GLM-550.99%SourceGLM-5-Turbo—Not directly comparable
Coding
SWE-bench Verified
GLM-577.8%SourceGLM-5-Turbo—Not directly comparable
SWE-bench Verified*
GLM-572.8%SourceGLM-5-Turbo—Not directly comparable
SWE-bench Pro
GLM-555.1%SourceGLM-5-Turbo—Not directly comparable
SWE Multilingual
GLM-573.3%SourceGLM-5-Turbo—Not directly comparable
SWE-Rebench
GLM-562.8%SourceGLM-5-Turbo—Not directly comparable
React Native Evals
GLM-574.8%SourceGLM-5-Turbo—Not directly comparable
Reasoning
Knowledge
GPQA
GLM-586%SourceGLM-5-Turbo—Not directly comparable
GPQA-D
GLM-586.0%SourceGLM-5-Turbo—Not directly comparable
SuperGPQA
GLM-566.8%SourceGLM-5-Turbo—Not directly comparable
MMLU-Pro
GLM-585.7%SourceGLM-5-Turbo—Not directly comparable
MMLU-Pro (Arcee)
GLM-585.8%SourceGLM-5-Turbo—Not directly comparable
HLE
GLM-550.4%SourceGLM-5-Turbo—Not directly comparable
Math
AIME26
GLM-595.8%SourceGLM-5-Turbo—Not directly comparable
AIME25 (Arcee)
GLM-593.3%SourceGLM-5-Turbo—Not directly comparable
HMMT Feb 2025
GLM-597.5%SourceGLM-5-Turbo—Not directly comparable
HMMT Nov 2025
GLM-596.9%SourceGLM-5-Turbo—Not directly comparable
HMMT Feb 2026
GLM-586.4%SourceGLM-5-Turbo—Not directly comparable
MMAnswerBench
GLM-582.5%SourceGLM-5-Turbo—Not directly comparable
FrontierMath v2 (Tiers 1-3)
GLM-516.434%SourceGLM-5-Turbo—Not directly comparable
FrontierMath v2 (Tier 4)
GLM-52.100%SourceGLM-5-Turbo—Not directly comparable
Multilingual
Instruction following
IFEval
GLM-592.6%SourceGLM-5-Turbo—Not directly comparable
Frequently asked questions
Which is better, GLM-5 or GLM-5-Turbo?
GLM-5-Turbo has the higher public score estimate, 61.64 versus 61.45, 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-5 or GLM-5-Turbo?
GLM-5-Turbo is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, GLM-5 or GLM-5-Turbo?
GLM-5-Turbo is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, GLM-5 or GLM-5-Turbo?
For the stated presets, chat costs $0.0026 on GLM-5 and $0.0032 on GLM-5-Turbo; repository review costs $0.0596 and $0.072; the cache-heavy agent loop costs $0.252 and $0.304. GLM-5 does not fit this workload in one request. GLM-5-Turbo 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-5-Turbo has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GLM-5 or GLM-5-Turbo?
Both models list the same context window, 200K.
Related comparisons
Last updated September 10, 2026
Watch GLM-5 vs GLM-5-Turbo
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.