Coding
Like-for-like- GLM-5.1
- 56.5
- Supported · #38/152
- GLM-5.2
- 61.0
- Supported · #19/152
- Basis
- BenchAlign lane · 7 vs 8 public rows
- Reading
- GLM-5.2 leads · intervals overlap
GLM-5.1 vs GLM-5.2
Updated September 14, 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-5.2 has the higher public score estimate, 68.19 versus 63.3, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
17 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.
Coding work
Code generation, repair, and software-engineering tasks
GLM-5.2
GLM-5.2 leads on the public coding lane, 61 to 56.5, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Long documents
Prompts that approach the documented context limit
GLM-5.2
GLM-5.2 has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GLM-5.1 is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
No clear pick
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-5.1 does not fit this workload in one request. GLM-5.1 has no published cached-input rate, so cached tokens use its listed input rate. GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Repository review cost
50K fresh input + 3K output tokens
No clear pick
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.
9 GLM-5.1 only
17 Shared
8 GLM-5.2 only
- Shared results
- 17
- GLM-5.1 only
- 9
- GLM-5.2 only
- 8
- Like-for-like categories
- 2 / 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.
Knowledge
Like-for-like- GLM-5.1
- 54.8
- Supported · #54/183
- GLM-5.2
- 60.7
- Supported · #35/183
- Basis
- BenchAlign lane · 4 vs 6 public rows
- Reading
- GLM-5.2 leads · intervals overlap
Agentic
Directional only- GLM-5.1
- 54.3
- Estimated · #38/153
- GLM-5.2
- 58.5
- Supported · #29/153
- Basis
- BenchAlign lane · 9 vs 6 public rows
- Reading
- Directional only
Instruction following
Directional only- GLM-5.1
- 93.7
- #5/123
- GLM-5.2
- 89.8
- #22/123
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Reasoning
Not comparable- GLM-5.1
- 71.7
- Unranked · 2 rankable rows
- GLM-5.2
- 74.8
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- GLM-5.1
- 64.1
- #3/7
- GLM-5.2
- 80.7
- Unranked · 4 rankable rows
- Basis
- Provisional lane · 4 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-5.1
- Not ranked
- GLM-5.2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-5.1
- Not ranked
- GLM-5.2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | GLM-5.1 | GLM-5.2 | Basis | Reading |
|---|---|---|---|---|
| Coding | 56.5Supported · #38/152 | 61.0Supported · #19/152 | Like-for-likeBenchAlign lane · 7 vs 8 public rows | GLM-5.2 leads · intervals overlap |
| Knowledge | 54.8Supported · #54/183 | 60.7Supported · #35/183 | Like-for-likeBenchAlign lane · 4 vs 6 public rows | GLM-5.2 leads · intervals overlap |
| Agentic | 54.3Estimated · #38/153 | 58.5Supported · #29/153 | Directional onlyBenchAlign lane · 9 vs 6 public rows | Directional only |
| Instruction following | 93.7#5/123 | 89.8#22/123 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Reasoning | 71.7Unranked · 2 rankable rows | 74.8Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 64.1#3/7 | 80.7Unranked · 4 rankable rows | Not comparableProvisional lane · 4 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 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.
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.
Terminal-Bench 2.0
Agentic
LiveCodeBench (Vals)
Coding
HMMT Feb 2026
Math
AIME26
Math
SWE-bench Pro
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-5.1
- $0.0036
- Fits in one request
- GLM-5.2
- $0.0036
- Fits in one request
Modeled costs are equal
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GLM-5.1
- $0.0832
- Fits in one request
- GLM-5.2
- $0.0832
- Fits in one request
Modeled costs are equal
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GLM-5.1
- $0.352
- Does not fit in one request
- Cached input priced at the published list-input rate
- GLM-5.2
- $0.352
- Fits in one request
- Cached input priced at the published list-input rate
GLM-5.1 does not fit this workload in one request. GLM-5.1 has no published cached-input rate, so cached tokens use its listed input rate. GLM-5.2 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-5.1GLM-5.2
Context window
Maximum documented context; output-token limits may be lower.
GLM-5.1
203K
GLM-5.2
1M
API model ID
GLM-5.1
Not sourced
GLM-5.2
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GLM-5.1
Not published
GLM-5.2
Not published
Documented inputs
GLM-5.1
Not sourced
GLM-5.2
Not sourced
Documented outputs
GLM-5.1
Not sourced
GLM-5.2
Not sourced
Provider availability
GLM-5.1
Not sourced
GLM-5.2
Not sourced
Reasoning profile
GLM-5.1
Reasoning
GLM-5.2
Reasoning
Weight access
GLM-5.1
Open Weight
GLM-5.2
Open Weight
License
GLM-5.1
Open Weight
GLM-5.2
Open Weight
Release date
GLM-5.1
2026-04-07
GLM-5.2
2026-06-16
If you are considering the documented upgrade path
- Deployment change
- Both entries list Z.AI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- GLM-5.2 has the higher public score estimate, 68.19 versus 63.3, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.0832 vs $0.0832. Cache-heavy agent loop: $0.352 vs $0.352.
- Context tradeoff
- GLM-5.2 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
GLM-5.1
API / mo$4,350
Self-host / mo$18,221
Break-even264M/day
GLM-5.2
API / mo$4,350
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence34 rows
Agentic
Terminal-Bench 2.0
GLM-5.163.5%SourceGLM-5.281%SourceGLM-5.2 leads this result
BrowseComp
GLM-5.168%SourceGLM-5.2—Not directly comparable
τ³-bench results
GLM-5.170.6%SourceGLM-5.2—Not directly comparable
MCP Atlas
GLM-5.171.8%SourceGLM-5.276.8%SourceGLM-5.2 leads this result
CyberGym
GLM-5.168.7%SourceGLM-5.2—Not directly comparable
Claw-Eval
GLM-5.162.3%SourceGLM-5.2—Not directly comparable
Gert Labs
GLM-5.160.11%SourceGLM-5.2—Not directly comparable
ResearchClawBench
Shared sourceGLM-5.118.2%GLM-5.220.7%GLM-5.2 leads this result
Terminal-Bench 2.1 (Vals)
GLM-5.156.9%SourceGLM-5.267.8%SourceGLM-5.2 leads this result
Terminal-Bench 3.0
GLM-5.1—GLM-5.24.6%SourceNot directly comparable
Toolathlon
GLM-5.1—GLM-5.248.2%SourceNot directly comparable
Coding
SWE-bench Pro
GLM-5.158.4%SourceGLM-5.262.1%SourceGLM-5.2 leads this result
NL2Repo
GLM-5.142.7%SourceGLM-5.248.9%SourceGLM-5.2 leads this result
SWE-Rebench
GLM-5.162.7%SourceGLM-5.2—Not directly comparable
Vibe Code Bench
GLM-5.131.46%SourceGLM-5.2—Not directly comparable
OpenHarmony Bench
Shared sourceGLM-5.152.3%GLM-5.258.4%GLM-5.2 leads this result
LiveCodeBench (Vals)
GLM-5.181.4%SourceGLM-5.269.5%SourceGLM-5.1 leads this result
SWE-bench (Vals)
GLM-5.176.4%SourceGLM-5.282.8%SourceGLM-5.2 leads this result
Terminal-Bench 2.0
GLM-5.1—GLM-5.281.0%SourceNot directly comparable
ProgramBench
GLM-5.1—GLM-5.263.7%SourceNot directly comparable
cursorBench32
GLM-5.1—GLM-5.255.0%SourceNot directly comparable
Reasoning
CritPt
GLM-5.1—GLM-5.220.9%SourceNot directly comparable
Knowledge
GPQA-D
GLM-5.186.2%SourceGLM-5.291.2%SourceGLM-5.2 leads this result
HLE
GLM-5.152.3%SourceGLM-5.254.7%SourceGLM-5.2 leads this result
GPQA Diamond (Vals)
GLM-5.184.5%SourceGLM-5.285.6%SourceGLM-5.2 leads this result
MMLU-Pro (Vals)
GLM-5.186.9%SourceGLM-5.286.7%SourceGLM-5.1 leads this result
GPQA
GLM-5.1—GLM-5.291.2%SourceNot directly comparable
HLE w/o tools
GLM-5.1—GLM-5.240.5%SourceNot directly comparable
Math
AIME26
GLM-5.195.3%SourceGLM-5.299.2%SourceGLM-5.2 leads this result
HMMT Nov 2025
GLM-5.194.0%SourceGLM-5.294.4%SourceGLM-5.2 leads this result
HMMT Feb 2026
GLM-5.182.6%SourceGLM-5.292.5%SourceGLM-5.2 leads this result
MMAnswerBench
GLM-5.183.8%SourceGLM-5.291.0%SourceGLM-5.2 leads this result
FrontierMath v2 (Tiers 1-3)
GLM-5.133.448%SourceGLM-5.2—Not directly comparable
FrontierMath v2 (Tier 4)
GLM-5.112.500%SourceGLM-5.2—Not directly comparable
Frequently asked questions
Which is better, GLM-5.1 or GLM-5.2?
GLM-5.2 has the higher public score estimate, 68.19 versus 63.3, 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-5.1 or GLM-5.2?
GLM-5.2 leads the public coding lane, 61 to 56.5, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, GLM-5.1 or GLM-5.2?
GLM-5.2 scores higher for agentic tasks on the public lane, 58.5 to 54.3. GLM-5.1 is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, GLM-5.1 or GLM-5.2?
For the stated presets, chat costs $0.0036 on GLM-5.1 and $0.0036 on GLM-5.2; repository review costs $0.0832 and $0.0832; the cache-heavy agent loop costs $0.352 and $0.352. GLM-5.1 does not fit this workload in one request. GLM-5.1 has no published cached-input rate, so cached tokens use its listed input rate. GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GLM-5.1 or GLM-5.2?
GLM-5.2 has the larger documented context window: 1M, compared with 203K.
Related comparisons
Last updated September 14, 2026
Watch GLM-5.1 vs GLM-5.2
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.