Agentic
Like-for-like- GLM-5.2
- 58.5
- Supported · #29/153
- GPT-5.5
- 61.1
- Supported · #17/153
- Basis
- BenchAlign lane · 6 vs 14 public rows
- Reading
- GPT-5.5 leads · intervals overlap
GLM-5.2 vs GPT-5.5
Updated September 14, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
GPT-5.5 has the higher public score estimate, 72.14 versus 68.19, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
16 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
GPT-5.5
GPT-5.5 leads on the public coding lane, 67.6 to 61, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
GPT-5.5
GPT-5.5 leads on the public agentic lane, 61.1 to 58.5, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
GLM-5.2
GLM-5.2 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
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
GLM-5.2
GLM-5.2 has the lower estimated token cost for this stated workload. 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
GLM-5.2
GLM-5.2 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
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-5.2 only
16 Shared
23 GPT-5.5 only
- Shared results
- 16
- GLM-5.2 only
- 9
- GPT-5.5 only
- 23
- Like-for-like categories
- 3 / 8
1 category rests 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
Like-for-like- GLM-5.2
- 61.0
- Supported · #19/152
- GPT-5.5
- 67.6
- Supported · #7/152
- Basis
- BenchAlign lane · 8 vs 9 public rows
- Reading
- GPT-5.5 leads · intervals overlap
Knowledge
Like-for-like- GLM-5.2
- 60.7
- Supported · #35/183
- GPT-5.5
- 72.9
- Supported · #7/183
- Basis
- BenchAlign lane · 6 vs 6 public rows
- Reading
- GPT-5.5 leads · intervals overlap
Instruction following
Directional only- GLM-5.2
- 89.8
- #22/123
- GPT-5.5
- 93.2
- #7/123
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Reasoning
Not comparable- GLM-5.2
- 74.8
- Unranked · 2 rankable rows
- GPT-5.5
- 64.0
- #13/20
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Math
Not comparable- GLM-5.2
- 80.7
- Unranked · 4 rankable rows
- GPT-5.5
- 69.6
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 2 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-5.2
- Not ranked
- GPT-5.5
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-5.2
- Not ranked
- GPT-5.5
- 71.3
- #19/48
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
| Category | GLM-5.2 | GPT-5.5 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 58.5Supported · #29/153 | 61.1Supported · #17/153 | Like-for-likeBenchAlign lane · 6 vs 14 public rows | GPT-5.5 leads · intervals overlap |
| Coding | 61.0Supported · #19/152 | 67.6Supported · #7/152 | Like-for-likeBenchAlign lane · 8 vs 9 public rows | GPT-5.5 leads · intervals overlap |
| Knowledge | 60.7Supported · #35/183 | 72.9Supported · #7/183 | Like-for-likeBenchAlign lane · 6 vs 6 public rows | GPT-5.5 leads · intervals overlap |
| Instruction following | 89.8#22/123 | 93.2#7/123 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Reasoning | 74.8Unranked · 2 rankable rows | 64.0#13/20 | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Math | 80.7Unranked · 4 rankable rows | 69.6Unranked · 3 rankable rows | Not comparableProvisional lane · 2 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | 71.3#19/48 | Not comparableProvisional lane · 0 vs 2 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.
LiveCodeBench (Vals)
Coding
SWE-bench Pro
Coding
cursorBench32
Coding
HLE
Knowledge
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
- GPT-5.5
- $0.02
- Fits in one request
GLM-5.2 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GLM-5.2
- $0.0832
- Fits in one request
- GPT-5.5
- $0.34
- Fits in one request
GLM-5.2 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-5.2
- $0.352
- Fits in one request
- Cached input priced at the published list-input rate
- GPT-5.5
- $0.5
- Fits in one request
GLM-5.2 has the lower modeled cost
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-5.2GPT-5.5
Context window
Maximum documented context; output-token limits may be lower.
GLM-5.2
1M
GPT-5.5
API model ID
GLM-5.2
Not sourced
GPT-5.5
gpt-5.5
OpenAI pricingCached-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
GPT-5.5
$0.5 per 1M cached input tokens
OpenAI pricingDocumented inputs
GLM-5.2
Not sourced
GPT-5.5
Not sourced
Documented outputs
GLM-5.2
Not sourced
GPT-5.5
Not sourced
Provider availability
GLM-5.2
Not sourced
GPT-5.5
Not sourced
Reasoning profile
GLM-5.2
Reasoning
GPT-5.5
Reasoning
Weight access
GLM-5.2
Open Weight
GPT-5.5
Proprietary
License
GLM-5.2
Open Weight
GPT-5.5
Proprietary
Release date
GLM-5.2
2026-06-16
GPT-5.5
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
- GPT-5.5 has the higher public score estimate, 72.14 versus 68.19, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.0832 vs $0.34. Cache-heavy agent loop: $0.352 vs $0.5.
- Context tradeoff
- Both models list 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 evidence48 rows
Agentic
Terminal-Bench 3.0
GLM-5.24.6%SourceGPT-5.5—Not directly comparable
Terminal-Bench 2.0
GLM-5.281%SourceGPT-5.582%SourceGPT-5.5 leads this result
MCP Atlas
GLM-5.276.8%SourceGPT-5.575.3%SourceGLM-5.2 leads this result
Toolathlon
GLM-5.248.2%SourceGPT-5.555.6%SourceGPT-5.5 leads this result
ResearchClawBench
Shared sourceGLM-5.220.7%GPT-5.517.0%GLM-5.2 leads this result
Terminal-Bench 2.1 (Vals)
GLM-5.267.8%SourceGPT-5.576.4%SourceGPT-5.5 leads this result
CyberGym
GLM-5.2—GPT-5.581.8%SourceNot directly comparable
BrowseComp
GLM-5.2—GPT-5.584.4%SourceNot directly comparable
OSWorld-Verified
GLM-5.2—GPT-5.578.7%SourceNot directly comparable
τ²-bench results
GLM-5.2—GPT-5.598%SourceNot directly comparable
Gert Labs
GLM-5.2—GPT-5.572.93%SourceNot directly comparable
OSWorld 2.0
GLM-5.2—GPT-5.513.0%SourceNot directly comparable
JobBench
GLM-5.2—GPT-5.542.7%SourceNot directly comparable
ExploitGym
GLM-5.2—GPT-5.513.4%SourceNot directly comparable
ApprenticeBench
GLM-5.2—GPT-5.520%SourceNot directly comparable
Coding
SWE-bench Pro
GLM-5.262.1%SourceGPT-5.558.6%SourceGLM-5.2 leads this result
NL2Repo
GLM-5.248.9%SourceGPT-5.5—Not directly comparable
Terminal-Bench 2.0
GLM-5.281.0%SourceGPT-5.582.0%SourceGPT-5.5 leads this result
ProgramBench
GLM-5.263.7%SourceGPT-5.5—Not directly comparable
cursorBench32
Shared sourceGLM-5.255.0%GPT-5.558.4%GPT-5.5 leads this result
OpenHarmony Bench
GLM-5.258.4%SourceGPT-5.5—Not directly comparable
LiveCodeBench (Vals)
GLM-5.269.5%SourceGPT-5.585.3%SourceGPT-5.5 leads this result
SWE-bench (Vals)
GLM-5.282.8%SourceGPT-5.582.6%SourceGLM-5.2 leads this result
Vibe Code Bench
GLM-5.2—GPT-5.569.85%SourceNot directly comparable
React Native Evals
GLM-5.2—GPT-5.584.7%SourceNot directly comparable
cursorBench31
GLM-5.2—GPT-5.559.2%SourceNot directly comparable
FrontierCode 1.1 Main
GLM-5.2—GPT-5.543.0%SourceNot directly comparable
Reasoning
CritPt
GLM-5.220.9%SourceGPT-5.5—Not directly comparable
MRCR v2 64K-128K
GLM-5.2—GPT-5.583.1%SourceNot directly comparable
MRCR v2 128K-256K
GLM-5.2—GPT-5.587.5%SourceNot directly comparable
ARC-AGI-2
GLM-5.2—GPT-5.585%SourceNot directly comparable
ARC-AGI-3
GLM-5.2—GPT-5.50.4%SourceNot directly comparable
Knowledge
GPQA
GLM-5.291.2%SourceGPT-5.593.6%SourceGPT-5.5 leads this result
GPQA-D
GLM-5.291.2%SourceGPT-5.593.6%SourceGPT-5.5 leads this result
HLE
GLM-5.254.7%SourceGPT-5.552.2%SourceGLM-5.2 leads this result
HLE w/o tools
GLM-5.240.5%SourceGPT-5.541.4%SourceGPT-5.5 leads this result
GPQA Diamond (Vals)
GLM-5.285.6%SourceGPT-5.593.2%SourceGPT-5.5 leads this result
MMLU-Pro (Vals)
GLM-5.286.7%SourceGPT-5.588.1%SourceGPT-5.5 leads this result
Math
AIME26
GLM-5.299.2%SourceGPT-5.5—Not directly comparable
HMMT Nov 2025
GLM-5.294.4%SourceGPT-5.5—Not directly comparable
HMMT Feb 2026
GLM-5.292.5%SourceGPT-5.5—Not directly comparable
MMAnswerBench
GLM-5.291.0%SourceGPT-5.5—Not directly comparable
FrontierMath (legacy)
GLM-5.2—GPT-5.551.7%SourceNot directly comparable
FrontierMath v2 (Tiers 1-3)
GLM-5.2—GPT-5.551.700%SourceNot directly comparable
FrontierMath v2 (Tier 4)
GLM-5.2—GPT-5.535.400%SourceNot directly comparable
Multimodal
Frequently asked questions
Which is better, GLM-5.2 or GPT-5.5?
GPT-5.5 has the higher public score estimate, 72.14 versus 68.19, 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 GPT-5.5?
GPT-5.5 leads the public coding lane, 67.6 to 61, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, GLM-5.2 or GPT-5.5?
GPT-5.5 leads the public agentic tasks lane, 61.1 to 58.5, with Supported evidence for both models, although the 90% intervals overlap.
Which costs less, GLM-5.2 or GPT-5.5?
For the stated presets, chat costs $0.0036 on GLM-5.2 and $0.02 on GPT-5.5; repository review costs $0.0832 and $0.34; the cache-heavy agent loop costs $0.352 and $0.5. GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GLM-5.2 or GPT-5.5?
Both models list the same context window, 1M.
Related comparisons
Last updated September 14, 2026
Watch GLM-5.2 vs GPT-5.5
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.