Agentic
Like-for-like- GLM-5.2
- 58.5
- Supported · #29/153
- Grok 4.20
- 26.7
- Supported · #146/153
- Basis
- BenchAlign lane · 6 vs 4 public rows
- Reading
- GLM-5.2 leads
GLM-5.2 vs Grok 4.20
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 67.21, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
9 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 28.3, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: stronger
Agentic work
Tool use, computer use, and multi-step task completion
GLM-5.2
GLM-5.2 leads on the public agentic lane, 58.5 to 26.7, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: stronger
Long documents
Prompts that approach the documented context limit
Grok 4.20
Grok 4.20 has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
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
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. Grok 4.20 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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
16 GLM-5.2 only
9 Shared
14 Grok 4.20 only
- Shared results
- 9
- GLM-5.2 only
- 16
- Grok 4.20 only
- 14
- Like-for-like categories
- 3 / 8
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
- Grok 4.20
- 28.3
- Supported · #142/152
- Basis
- BenchAlign lane · 8 vs 6 public rows
- Reading
- GLM-5.2 leads
Knowledge
Like-for-like- GLM-5.2
- 60.7
- Supported · #35/183
- Grok 4.20
- 49.3
- Supported · #85/183
- Basis
- BenchAlign lane · 6 vs 6 public rows
- Reading
- GLM-5.2 leads · intervals overlap
Reasoning
Not comparable- GLM-5.2
- 74.8
- Unranked · 2 rankable rows
- Grok 4.20
- 34.2
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Math
Not comparable- GLM-5.2
- 80.7
- Unranked · 4 rankable rows
- Grok 4.20
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-5.2
- Not ranked
- Grok 4.20
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-5.2
- Not ranked
- Grok 4.20
- 34.6
- #43/48
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- GLM-5.2
- 89.8
- #22/123
- Grok 4.20
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | GLM-5.2 | Grok 4.20 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 58.5Supported · #29/153 | 26.7Supported · #146/153 | Like-for-likeBenchAlign lane · 6 vs 4 public rows | GLM-5.2 leads |
| Coding | 61.0Supported · #19/152 | 28.3Supported · #142/152 | Like-for-likeBenchAlign lane · 8 vs 6 public rows | GLM-5.2 leads |
| Knowledge | 60.7Supported · #35/183 | 49.3Supported · #85/183 | Like-for-likeBenchAlign lane · 6 vs 6 public rows | GLM-5.2 leads · intervals overlap |
| Reasoning | 74.8Unranked · 2 rankable rows | 34.2Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 2 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 | 34.6#43/48 | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Instruction following | 89.8#22/123 | 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
SWE-bench Pro
Coding
HLE w/o tools
Knowledge
MMLU-Pro (Vals)
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
- Grok 4.20
- $0.005
- 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
- Grok 4.20
- $0.118
- 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
- Grok 4.20
- $0.5
- Fits in one request
- Cached input priced at the published list-input rate
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. Grok 4.20 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-5.2Grok 4.20
Context window
Maximum documented context; output-token limits may be lower.
GLM-5.2
1M
Grok 4.20
2M
API model ID
GLM-5.2
Not sourced
Grok 4.20
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
Grok 4.20
Not published
Documented inputs
GLM-5.2
Not sourced
Grok 4.20
Not sourced
Documented outputs
GLM-5.2
Not sourced
Grok 4.20
Not sourced
Provider availability
GLM-5.2
Not sourced
Grok 4.20
Not sourced
Reasoning profile
GLM-5.2
Reasoning
Grok 4.20
Reasoning
Weight access
GLM-5.2
Open Weight
Grok 4.20
Proprietary
License
GLM-5.2
Open Weight
Grok 4.20
Proprietary
Release date
GLM-5.2
2026-06-16
Grok 4.20
2026-03-10
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 67.21, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.0832 vs $0.118. Cache-heavy agent loop: $0.352 vs $0.5.
- Context tradeoff
- Grok 4.20 has the larger documented window (2M).
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 evidence39 rows
Agentic
Terminal-Bench 3.0
GLM-5.24.6%SourceGrok 4.20—Not directly comparable
Terminal-Bench 2.0
GLM-5.281%SourceGrok 4.2047.1%SourceGLM-5.2 leads this result
MCP Atlas
GLM-5.276.8%SourceGrok 4.20—Not directly comparable
Toolathlon
GLM-5.248.2%SourceGrok 4.20—Not directly comparable
ResearchClawBench
GLM-5.220.7%SourceGrok 4.20—Not directly comparable
Terminal-Bench 2.1 (Vals)
GLM-5.267.8%SourceGrok 4.2044.2%SourceGLM-5.2 leads this result
DeepSearchQA
GLM-5.2—Grok 4.2062.8%SourceNot directly comparable
Gert Labs
GLM-5.2—Grok 4.2038.36%SourceNot directly comparable
Coding
SWE-bench Pro
GLM-5.262.1%SourceGrok 4.2051.8%SourceGLM-5.2 leads this result
NL2Repo
GLM-5.248.9%SourceGrok 4.20—Not directly comparable
Terminal-Bench 2.0
GLM-5.281.0%SourceGrok 4.20—Not directly comparable
ProgramBench
GLM-5.263.7%SourceGrok 4.20—Not directly comparable
cursorBench32
GLM-5.255.0%SourceGrok 4.20—Not directly comparable
OpenHarmony Bench
GLM-5.258.4%SourceGrok 4.20—Not directly comparable
LiveCodeBench (Vals)
GLM-5.269.5%SourceGrok 4.2084.3%SourceGrok 4.20 leads this result
SWE-bench (Vals)
GLM-5.282.8%SourceGrok 4.2072.2%SourceGLM-5.2 leads this result
LiveCodeBench Pro
GLM-5.2—Grok 4.2074.2%SourceNot directly comparable
SWE-bench Verified
GLM-5.2—Grok 4.2076.7%SourceNot directly comparable
Vibe Code Bench
GLM-5.2—Grok 4.204.06%SourceNot directly comparable
Reasoning
Knowledge
GPQA
GLM-5.291.2%SourceGrok 4.20—Not directly comparable
GPQA-D
GLM-5.291.2%SourceGrok 4.2088.5%SourceGLM-5.2 leads this result
HLE
GLM-5.254.7%SourceGrok 4.20—Not directly comparable
HLE w/o tools
GLM-5.240.5%SourceGrok 4.2031.6%SourceGLM-5.2 leads this result
GPQA Diamond (Vals)
GLM-5.285.6%SourceGrok 4.2088.6%SourceGrok 4.20 leads this result
MMLU-Pro (Vals)
GLM-5.286.7%SourceGrok 4.2086.3%SourceGLM-5.2 leads this result
HealthBench Hard
GLM-5.2—Grok 4.2020.3%SourceNot directly comparable
MedXpertQA (Text)
GLM-5.2—Grok 4.2050.2%SourceNot directly comparable
Math
Multimodal
MMMU-Pro
GLM-5.2—Grok 4.2075.2%SourceNot directly comparable
CharXiv
GLM-5.2—Grok 4.2060.9%SourceNot directly comparable
ERQA
GLM-5.2—Grok 4.2054.1%SourceNot directly comparable
SimpleVQA
GLM-5.2—Grok 4.2057.4%SourceNot directly comparable
MedXpertQA (MM)
GLM-5.2—Grok 4.2065.8%SourceNot directly comparable
Frequently asked questions
Which is better, GLM-5.2 or Grok 4.20?
GLM-5.2 has the higher public score estimate, 68.19 versus 67.21, 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 Grok 4.20?
GLM-5.2 leads the public coding lane, 61 to 28.3, with Supported evidence for both models and non-overlapping 90% intervals.
Which is better for agentic tasks, GLM-5.2 or Grok 4.20?
GLM-5.2 leads the public agentic tasks lane, 58.5 to 26.7, with Supported evidence for both models and non-overlapping 90% intervals.
Which costs less, GLM-5.2 or Grok 4.20?
For the stated presets, chat costs $0.0036 on GLM-5.2 and $0.005 on Grok 4.20; repository review costs $0.0832 and $0.118; 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. Grok 4.20 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GLM-5.2 or Grok 4.20?
Grok 4.20 has the larger documented context window: 2M, compared with 1M.
Related comparisons
Last updated September 14, 2026
Watch GLM-5.2 vs Grok 4.20
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.