Long documents
Prompts that approach the documented context limit
Kimi K2.6
Kimi K2.6 has the larger documented context window.
Confidence: documented
GLM-4.7-Flash vs Kimi K2.6
Updated October 17, 2026. Rank says Kimi K2.6 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Share or export
Decision reading
Kimi K2.6 has the higher public point estimate, 58.4 versus 39.13. Their conditional score ranges overlap. These ranges do not establish rank confidence. 3 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 3
- GLM-4.7-Flash only
- 1
- Kimi K2.6 only
- 34
- Like-for-like categories
- 0 / 8
Estimated: GLM-4.7-Flash and Kimi K2.6. Conditional ranges do not establish rank confidence.How the comparison works
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.
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
GLM-4.7-Flash is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GLM-4.7-Flash is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limitedChat 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-ratesCache-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-4.7-Flash does not fit this workload in one request. GLM-4.7-Flash has no comparable published API token rate.
Confidence: listed-ratesRepository 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
Which one for a specific job
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
—GLM-4.7-Flash43.1Kimi K2.6
Not comparable · BenchAlign v5.8
The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 GLM-4.7-Flash only
3 Shared
34 Kimi K2.6 only
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.
SWE-bench VerifiedCoding
Normalized gap 21.0GLM-4.7-Flash:59.2%Kimi K2.6:80.2%GPQAKnowledge
Normalized gap 15.3GLM-4.7-Flash:75.2%Kimi K2.6:90.5%
Bars run 0–100 on each benchmark’s normalized display scale
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.8 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.
Agentic
Not comparable- GLM-4.7-Flash
- Not ranked
- Kimi K2.6
- 44.3
- Supported · #59/128
- Basis
- BenchAlign v5.8 lane · 0 vs 12 public rows
- Reading
- Not comparable
Coding
Not comparable- GLM-4.7-Flash
- Not ranked
- Kimi K2.6
- 43.1
- Supported · #58/150
- Basis
- BenchAlign v5.8 lane · 2 vs 10 public rows
- Reading
- Not comparable
Reasoning
Not comparable- GLM-4.7-Flash
- Not ranked
- Kimi K2.6
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-4.7-Flash
- Not ranked
- Kimi K2.6
- 73.8
- #27/54
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- GLM-4.7-Flash
- Not ranked
- Kimi K2.6
- 60.3
- Supported · #49/184
- Basis
- BenchAlign v5.8 lane · 1 vs 5 public rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-4.7-Flash
- Not ranked
- Kimi K2.6
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- GLM-4.7-Flash
- Not ranked
- Kimi K2.6
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- GLM-4.7-Flash
- Not ranked
- Kimi K2.6
- 76.8
- #4/12
- Basis
- Provisional lane · 0 vs 4 weighted rows
- Reading
- Not comparable
| Category | GLM-4.7-Flash | Kimi K2.6 | Basis | Reading |
|---|---|---|---|---|
| Agentic | Not ranked | 44.3Supported · #59/128 | Not comparableBenchAlign v5.8 lane · 0 vs 12 public rows | Not comparable |
| Coding | Not ranked | 43.1Supported · #58/150 | Not comparableBenchAlign v5.8 lane · 2 vs 10 public rows | Not comparable |
| Reasoning | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | 73.8#27/54 | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Knowledge | Not ranked | 60.3Supported · #49/184 | Not comparableBenchAlign v5.8 lane · 1 vs 5 public rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | 76.8#4/12 | Not comparableProvisional lane · 0 vs 4 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Supported evidence per lane · bars run 0–100Methodology
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-4.7-Flash
- Self-hosted; infrastructure cost varies
- Fits in one request
- Kimi K2.6
- $0.00295
- Fits in one request
GLM-4.7-Flash has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- GLM-4.7-Flash
- Self-hosted; infrastructure cost varies
- Fits in one request
- Kimi K2.6
- $0.0595
- Fits in one request
GLM-4.7-Flash has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GLM-4.7-Flash
- Self-hosted; infrastructure cost varies
- Does not fit in one request
- Cached-input rate unavailable
- Kimi K2.6
- $0.091
- Fits in one request
GLM-4.7-Flash does not fit this workload in one request. GLM-4.7-Flash has no comparable published API token rate.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGLM-4.7-FlashKimi K2.6
Context window
Maximum documented context; output-token limits may be lower.
GLM-4.7-Flash
200K
Kimi K2.6
256K
API model ID
GLM-4.7-Flash
Not sourced
Kimi K2.6
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GLM-4.7-Flash
No comparable hosted API rate
Kimi K2.6
$0.16 per 1M cached input tokens
Documented inputs
GLM-4.7-Flash
Not sourced
Kimi K2.6
Not sourced
Documented outputs
GLM-4.7-Flash
Not sourced
Kimi K2.6
Not sourced
Provider availability
GLM-4.7-Flash
Not sourced
Kimi K2.6
Not sourced
Reasoning profile
GLM-4.7-Flash
Reasoning
Kimi K2.6
Reasoning
Weight access
GLM-4.7-Flash
Open Weight
Kimi K2.6
Open Weight
License
GLM-4.7-Flash
Open Weight
Kimi K2.6
Open Weight
Release date
GLM-4.7-Flash
2026-01-19
Kimi K2.6
2026-04-20
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 K2.6 has the higher public point estimate, 58.4 versus 39.13. Their conditional score ranges overlap. These ranges do not establish rank confidence.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Kimi K2.6 has the larger documented window (256K).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, GLM-4.7-Flash or Kimi K2.6?
Kimi K2.6 has the higher public point estimate, 58.4 versus 39.13. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, GLM-4.7-Flash or Kimi K2.6?
GLM-4.7-Flash is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, GLM-4.7-Flash or Kimi K2.6?
GLM-4.7-Flash is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, GLM-4.7-Flash or Kimi K2.6?
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-4.7-Flash or Kimi K2.6?
Kimi K2.6 has the larger documented context window: 256K, compared with 200K.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
GLM-4.7-Flash
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Kimi K2.6
API / mo$3,713
Self-host / mo$27,962
Break-even500M/day
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence38 rows
Agentic
Terminal-Bench 2.0
GLM-4.7-Flash—Kimi K2.666.7%SourceNot directly comparable
BrowseComp
GLM-4.7-Flash—Kimi K2.683.2%SourceNot directly comparable
OSWorld-Verified
GLM-4.7-Flash—Kimi K2.673.1%SourceNot directly comparable
Toolathlon
GLM-4.7-Flash—Kimi K2.650%SourceNot directly comparable
MCP Atlas
GLM-4.7-Flash—Kimi K2.655.9%SourceNot directly comparable
Claw-Eval
GLM-4.7-Flash—Kimi K2.662.3%SourceNot directly comparable
DeepSearchQA
GLM-4.7-Flash—Kimi K2.692.5%SourceNot directly comparable
WideResearch
GLM-4.7-Flash—Kimi K2.680.8%SourceNot directly comparable
Gert Labs
GLM-4.7-Flash—Kimi K2.656.82%SourceNot directly comparable
ResearchClawBench
GLM-4.7-Flash—Kimi K2.618.0%SourceNot directly comparable
OSWorld 2.0
GLM-4.7-Flash—Kimi K2.64.6%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
GLM-4.7-Flash—Kimi K2.653.6%SourceNot directly comparable
Coding
SWE-bench Verified
GLM-4.7-Flash59.2%SourceKimi K2.680.2%SourceKimi K2.6 leads this result
LiveCodeBench v6
GLM-4.7-Flash64.0%SourceKimi K2.689.6%SourceKimi K2.6 leads this result
SWE-bench Pro
GLM-4.7-Flash—Kimi K2.658.6%SourceNot directly comparable
SWE Multilingual
GLM-4.7-Flash—Kimi K2.676.7%SourceNot directly comparable
SciCode
GLM-4.7-Flash—Kimi K2.652.2%SourceNot directly comparable
Terminal-Bench 2.0
GLM-4.7-Flash—Kimi K2.666.7%SourceNot directly comparable
Vibe Code Bench
GLM-4.7-Flash—Kimi K2.637.89%SourceNot directly comparable
cursorBench31
GLM-4.7-Flash—Kimi K2.647.6%SourceNot directly comparable
LiveCodeBench (Vals)
GLM-4.7-Flash—Kimi K2.686.8%SourceNot directly comparable
SWE-bench (Vals)
GLM-4.7-Flash—Kimi K2.676.2%SourceNot directly comparable
Multimodal
MMMU-Pro
GLM-4.7-Flash—Kimi K2.679.4%SourceNot directly comparable
MMMU-Pro w/ Python
GLM-4.7-Flash—Kimi K2.680.1%SourceNot directly comparable
CharXiv
GLM-4.7-Flash—Kimi K2.680.4%SourceNot directly comparable
MathVision
GLM-4.7-Flash—Kimi K2.687.4%SourceNot directly comparable
V*
GLM-4.7-Flash—Kimi K2.696.9%SourceNot directly comparable
Knowledge
GPQA
GLM-4.7-Flash75.2%SourceKimi K2.690.5%SourceKimi K2.6 leads this result
GPQA-D
GLM-4.7-Flash—Kimi K2.690.5%SourceNot directly comparable
HLE
GLM-4.7-Flash—Kimi K2.634.7%SourceNot directly comparable
GPQA Diamond (Vals)
GLM-4.7-Flash—Kimi K2.689.1%SourceNot directly comparable
MMLU-Pro (Vals)
GLM-4.7-Flash—Kimi K2.687.6%SourceNot directly comparable
Math
AIME 2025
GLM-4.7-Flash91.6%SourceKimi K2.6—Not directly comparable
AIME26
GLM-4.7-Flash—Kimi K2.696.4%SourceNot directly comparable
HMMT Feb 2026
GLM-4.7-Flash—Kimi K2.692.7%SourceNot directly comparable
MMAnswerBench
GLM-4.7-Flash—Kimi K2.686.0%SourceNot directly comparable
FrontierMath v2 (Tiers 1-3)
GLM-4.7-Flash—Kimi K2.657.193%SourceNot directly comparable
FrontierMath v2 (Tier 4)
GLM-4.7-Flash—Kimi K2.625.641%SourceNot directly comparable
38 public results · 3 shared
Watch GLM-4.7-Flash vs Kimi K2.6
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,600+ readers.
Last updated October 17, 2026