Knowledge
Like-for-like- GLM-5.2
- 59.6
- Kimi K3
- 61.0
- Weighted basis
- 2 vs 2 rows
- Reading
- Kimi K3 leads
GLM-5.2 vs Kimi K3
Updated August 19, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Kimi K3 has the higher public score estimate, 80.53 versus 63.36, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
9 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
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
Kimi K3
Kimi K3 has the larger documented context window.
Confidence: documented
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
Kimi K3
Kimi K3 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
Show secondary and unsupported calls
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
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
11 GLM-5.2 only
9 Shared
31 Kimi K3 only
- Shared results
- 9
- GLM-5.2 only
- 11
- Kimi K3 only
- 31
- Like-for-like categories
- 1 / 8
1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Agentic
Directional only- GLM-5.2
- 81.0
- Kimi K3
- 89.5
- Weighted basis
- 1 vs 2 rows
- Reading
- Directional only
Coding
Not comparable- GLM-5.2
- 62.1
- Kimi K3
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- GLM-5.2
- Not measured
- Kimi K3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- GLM-5.2
- 95.9
- Kimi K3
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-5.2
- Not measured
- Kimi K3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-5.2
- Not measured
- Kimi K3
- 78.5
- Weighted basis
- 0 vs 3 rows
- Reading
- Not comparable
Instruction following
Not comparable- GLM-5.2
- Not measured
- Kimi K3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | GLM-5.2 | Kimi K3 | Weighted basis | Reading |
|---|---|---|---|---|
| Knowledge | 59.6 | 61.0 | Like-for-like2 vs 2 rows | Kimi K3 leads |
| Agentic | 81.0 | 89.5 | Directional only1 vs 2 rows | Directional only |
| Coding | 62.1 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Math | 95.9 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | 78.5 | Not comparable0 vs 3 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
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
HLE
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
- Kimi K3
- $0.0105
- 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
- Kimi K3
- $0.195
- 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
- Kimi K3
- $0.27
- Fits in one request
Kimi K3 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-5.2Kimi K3
Context window
Maximum documented context; output-token limits may be lower.
GLM-5.2
1M
Kimi K3
1.05M
API model ID
GLM-5.2
Not sourced
Kimi K3
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
Kimi K3
$0.3 per 1M cached input tokens
Documented inputs
GLM-5.2
Not sourced
Kimi K3
Not sourced
Documented outputs
GLM-5.2
Not sourced
Kimi K3
Not sourced
Provider availability
GLM-5.2
Not sourced
Kimi K3
Not sourced
Reasoning profile
GLM-5.2
Reasoning
Kimi K3
Reasoning
Weight access
GLM-5.2
Open Weight
Kimi K3
Pending
License
GLM-5.2
Open Weight
Kimi K3
Pending
Release date
GLM-5.2
2026-06-16
Kimi K3
2026-07-16
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
- Kimi K3 has the higher public score estimate, 80.53 versus 63.36, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.0832 vs $0.195. Cache-heavy agent loop: $0.352 vs $0.27.
- Context tradeoff
- Kimi K3 has the larger documented window (1.05M).
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 evidence51 rows
Agentic
Terminal-Bench 3.0
GLM-5.24.6%SourceKimi K3—Not directly comparable
Terminal-Bench 2.0
GLM-5.281%SourceKimi K388.3%SourceKimi K3 leads this result
MCP Atlas
GLM-5.276.8%SourceKimi K384.2%SourceKimi K3 leads this result
Toolathlon
GLM-5.248.2%SourceKimi K3—Not directly comparable
ResearchClawBench
GLM-5.220.7%SourceKimi K3—Not directly comparable
BrowseComp
GLM-5.2—Kimi K391.2%SourceNot directly comparable
DeepSearchQA
GLM-5.2—Kimi K395.0%SourceNot directly comparable
Toolathlon-Verified
GLM-5.2—Kimi K373.2%SourceNot directly comparable
AutomationBench
GLM-5.2—Kimi K330.8%SourceNot directly comparable
JobBench
GLM-5.2—Kimi K352.9%SourceNot directly comparable
APEX-Agents
GLM-5.2—Kimi K337.6%SourceNot directly comparable
SpreadsheetBench 2
GLM-5.2—Kimi K334.8%SourceNot directly comparable
DECK-Bench
GLM-5.2—Kimi K373.5%SourceNot directly comparable
Coding
SWE-bench Pro
GLM-5.262.1%SourceKimi K3—Not directly comparable
NL2Repo
GLM-5.248.9%SourceKimi K3—Not directly comparable
Terminal-Bench 2.0
GLM-5.281.0%SourceKimi K3—Not directly comparable
ProgramBench
GLM-5.263.7%SourceKimi K377.8%SourceKimi K3 leads this result
cursorBench32
Shared sourceGLM-5.255.0%Kimi K360.8%Kimi K3 leads this result
EEBench
Shared sourceGLM-5.216.7%Kimi K338.3%Kimi K3 leads this result
deepSwe
GLM-5.2—Kimi K367.5%SourceNot directly comparable
FrontierSWE
GLM-5.2—Kimi K381.2%SourceNot directly comparable
Kimi Code Bench v2
GLM-5.2—Kimi K372.9%SourceNot directly comparable
sweMarathon
GLM-5.2—Kimi K342%SourceNot directly comparable
PostTrain Bench
GLM-5.2—Kimi K336.6%SourceNot directly comparable
MLS-Bench Lite
GLM-5.2—Kimi K348.3%SourceNot directly comparable
VulcanBench v3
GLM-5.2—Kimi K373.9%SourceNot directly comparable
APEX-SWE
GLM-5.2—Kimi K348.0%SourceNot directly comparable
InferenceEval
GLM-5.2—Kimi K339.8%SourceNot directly comparable
KernelBench Internal
GLM-5.2—Kimi K368.5%SourceNot directly comparable
Reasoning
CritPt
GLM-5.220.9%SourceKimi K3—Not directly comparable
Knowledge
Math
Multimodal
OfficeQA Pro
GLM-5.2—Kimi K363.3%SourceNot directly comparable
MMMU-Pro
GLM-5.2—Kimi K381.6%SourceNot directly comparable
MMMU-Pro w/ Python
GLM-5.2—Kimi K383.4%SourceNot directly comparable
CharXiv w/o tools
GLM-5.2—Kimi K384.8%SourceNot directly comparable
CharXiv
GLM-5.2—Kimi K391.3%SourceNot directly comparable
MathVision
GLM-5.2—Kimi K394.3%SourceNot directly comparable
MathVision w/ Python
GLM-5.2—Kimi K397.8%SourceNot directly comparable
BabyVision w/ Python
GLM-5.2—Kimi K385.7%SourceNot directly comparable
ZeroBench
GLM-5.2—Kimi K323.0%SourceNot directly comparable
ZeroBench w/ Python
GLM-5.2—Kimi K341.0%SourceNot directly comparable
WorldVQA ForceAnswer
GLM-5.2—Kimi K351.0%SourceNot directly comparable
OmniDocBench
GLM-5.2—Kimi K391.1%SourceNot directly comparable
PerceptionBench
GLM-5.2—Kimi K358.5%SourceNot directly comparable
Frequently asked questions
Which is better, GLM-5.2 or Kimi K3?
Kimi K3 has the higher public score estimate, 80.53 versus 63.36, 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 Kimi K3?
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
Which is better for agentic tasks, GLM-5.2 or Kimi K3?
The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which costs less, GLM-5.2 or Kimi K3?
For the stated presets, chat costs $0.0036 on GLM-5.2 and $0.0105 on Kimi K3; repository review costs $0.0832 and $0.195; the cache-heavy agent loop costs $0.352 and $0.27. 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 Kimi K3?
Kimi K3 has the larger documented context window: 1.05M, compared with 1M.
Related comparisons
Last updated August 19, 2026
Watch GLM-5.2 vs Kimi K3
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.