Agentic
Directional only- GLM-5.2
- 58.5
- Supported · #29/153
- Hy3 Preview
- 47.9
- Estimated · #69/153
- Basis
- BenchAlign lane · 6 vs 2 public rows
- Reading
- Directional only
GLM-5.2 vs Hy3 Preview
Updated September 14, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
GLM-5.2 has the higher public score estimate, 68.19 versus 55.49, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
4 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.
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
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Hy3 Preview is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Hy3 Preview 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
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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
21 GLM-5.2 only
4 Shared
2 Hy3 Preview only
- Shared results
- 4
- GLM-5.2 only
- 21
- Hy3 Preview only
- 2
- Like-for-like categories
- 0 / 8
4 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.
Coding
Directional only- GLM-5.2
- 61.0
- Supported · #19/152
- Hy3 Preview
- 44.5
- Estimated · #93/152
- Basis
- BenchAlign lane · 8 vs 2 public rows
- Reading
- Directional only
Knowledge
Directional only- GLM-5.2
- 60.7
- Supported · #35/183
- Hy3 Preview
- 49.0
- Estimated · #88/183
- Basis
- BenchAlign lane · 6 vs 2 public rows
- Reading
- Directional only
Instruction following
Directional only- GLM-5.2
- 89.8
- #22/123
- Hy3 Preview
- 54.8
- #76/123
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Reasoning
Not comparable- GLM-5.2
- 74.8
- Unranked · 2 rankable rows
- Hy3 Preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- GLM-5.2
- 80.7
- Unranked · 4 rankable rows
- Hy3 Preview
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-5.2
- Not ranked
- Hy3 Preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-5.2
- Not ranked
- Hy3 Preview
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | GLM-5.2 | Hy3 Preview | Basis | Reading |
|---|---|---|---|---|
| Agentic | 58.5Supported · #29/153 | 47.9Estimated · #69/153 | Directional onlyBenchAlign lane · 6 vs 2 public rows | Directional only |
| Coding | 61.0Supported · #19/152 | 44.5Estimated · #93/152 | Directional onlyBenchAlign lane · 8 vs 2 public rows | Directional only |
| Knowledge | 60.7Supported · #35/183 | 49.0Estimated · #88/183 | Directional onlyBenchAlign lane · 6 vs 2 public rows | Directional only |
| Instruction following | 89.8#22/123 | 54.8#76/123 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Reasoning | 74.8Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 80.7Unranked · 4 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 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
GPQA
Knowledge
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
- Hy3 Preview
- Self-hosted; infrastructure cost varies
- Fits in one request
Hy3 Preview has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- GLM-5.2
- $0.0832
- Fits in one request
- Hy3 Preview
- Self-hosted; infrastructure cost varies
- Fits in one request
Hy3 Preview 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
- Hy3 Preview
- Self-hosted; infrastructure cost varies
- 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. Hy3 Preview 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-5.2Hy3 Preview
Context window
Maximum documented context; output-token limits may be lower.
GLM-5.2
1M
Hy3 Preview
256K
API model ID
GLM-5.2
Not sourced
Hy3 Preview
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GLM-5.2
Not published
Hy3 Preview
No comparable hosted API rate
Documented inputs
GLM-5.2
Not sourced
Hy3 Preview
Not sourced
Documented outputs
GLM-5.2
Not sourced
Hy3 Preview
Not sourced
Provider availability
GLM-5.2
Not sourced
Hy3 Preview
Not sourced
Reasoning profile
GLM-5.2
Reasoning
Hy3 Preview
Reasoning
Weight access
GLM-5.2
Open Weight
Hy3 Preview
Open Weight
License
GLM-5.2
Open Weight
Hy3 Preview
Open Weight
Release date
GLM-5.2
2026-06-16
Hy3 Preview
2026-04-23
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 score estimate, 68.19 versus 55.49, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- GLM-5.2 has the larger documented window (1M).
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 evidence27 rows
Agentic
Terminal-Bench 3.0
GLM-5.24.6%SourceHy3 Preview—Not directly comparable
Terminal-Bench 2.0
GLM-5.281%SourceHy3 Preview54.4%SourceGLM-5.2 leads this result
MCP Atlas
GLM-5.276.8%SourceHy3 Preview—Not directly comparable
Toolathlon
GLM-5.248.2%SourceHy3 Preview—Not directly comparable
ResearchClawBench
GLM-5.220.7%SourceHy3 Preview—Not directly comparable
Terminal-Bench 2.1 (Vals)
GLM-5.267.8%SourceHy3 Preview—Not directly comparable
Gert Labs
GLM-5.2—Hy3 Preview36.91%SourceNot directly comparable
Coding
SWE-bench Pro
GLM-5.262.1%SourceHy3 Preview—Not directly comparable
NL2Repo
GLM-5.248.9%SourceHy3 Preview—Not directly comparable
Terminal-Bench 2.0
GLM-5.281.0%SourceHy3 Preview54.4%SourceGLM-5.2 leads this result
ProgramBench
GLM-5.263.7%SourceHy3 Preview—Not directly comparable
cursorBench32
GLM-5.255.0%SourceHy3 Preview—Not directly comparable
OpenHarmony Bench
GLM-5.258.4%SourceHy3 Preview—Not directly comparable
LiveCodeBench (Vals)
GLM-5.269.5%SourceHy3 Preview—Not directly comparable
SWE-bench (Vals)
GLM-5.282.8%SourceHy3 Preview—Not directly comparable
SWE-bench Verified
GLM-5.2—Hy3 Preview74.4%SourceNot directly comparable
Reasoning
CritPt
GLM-5.220.9%SourceHy3 Preview—Not directly comparable
Knowledge
GPQA
GLM-5.291.2%SourceHy3 Preview87.2%SourceGLM-5.2 leads this result
GPQA-D
GLM-5.291.2%SourceHy3 Preview87.2%SourceGLM-5.2 leads this result
HLE
GLM-5.254.7%SourceHy3 Preview—Not directly comparable
HLE w/o tools
GLM-5.240.5%SourceHy3 Preview—Not directly comparable
GPQA Diamond (Vals)
GLM-5.285.6%SourceHy3 Preview—Not directly comparable
MMLU-Pro (Vals)
GLM-5.286.7%SourceHy3 Preview—Not directly comparable
Math
Frequently asked questions
Which is better, GLM-5.2 or Hy3 Preview?
GLM-5.2 has the higher public score estimate, 68.19 versus 55.49, 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-5.2 or Hy3 Preview?
GLM-5.2 scores higher for coding on the public lane, 61 to 44.5. Hy3 Preview 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 Hy3 Preview?
GLM-5.2 scores higher for agentic tasks on the public lane, 58.5 to 47.9. Hy3 Preview 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-5.2 or Hy3 Preview?
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 Hy3 Preview?
GLM-5.2 has the larger documented context window: 1M, compared with 256K.
Related comparisons
Last updated September 14, 2026
Watch GLM-5.2 vs Hy3 Preview
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.