Agentic
Not comparable- Grok 4.7
- Not ranked
- Kimi K2.7 Code
- 47.7
- Estimated · #72/154
- Basis
- BenchAlign lane · 2 vs 4 public rows
- Reading
- Not comparable
Grok 4.7 vs Kimi K2.7 Code
Decision reading
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Updated September 21, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
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
Grok 4.7
Grok 4.7 has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Kimi K2.7 Code
Kimi K2.7 Code 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
Grok 4.7
Grok 4.7 has the lower estimated token cost for this stated workload. Kimi K2.7 Code 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
Kimi K2.7 Code
Kimi K2.7 Code 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
Grok 4.7 is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Grok 4.7 is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limited
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.
—Grok 4.751.6Kimi K2.7 Code
Not comparable · BenchAlign
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.
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
5 Grok 4.7 only
1 Shared
10 Kimi K2.7 Code only
- Shared results
- 1
- Grok 4.7 only
- 5
- Kimi K2.7 Code only
- 10
- Like-for-like categories
- 0 / 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
Not comparable- Grok 4.7
- Not ranked
- Kimi K2.7 Code
- 51.6
- Estimated · #53/156
- Basis
- BenchAlign lane · 3 vs 7 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Grok 4.7
- 73.7
- Unranked · 2 rankable rows
- Kimi K2.7 Code
- 75.5
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Grok 4.7
- Not ranked
- Kimi K2.7 Code
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- Grok 4.7
- Not ranked
- Kimi K2.7 Code
- 61.6
- Estimated · #31/186
- Basis
- BenchAlign lane · 1 vs 0 public rows
- Reading
- Not comparable
Multilingual
Not comparable- Grok 4.7
- Not ranked
- Kimi K2.7 Code
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Grok 4.7
- Not ranked
- Kimi K2.7 Code
- 75.1
- #59/124
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Grok 4.7
- Not ranked
- Kimi K2.7 Code
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Grok 4.7 | Kimi K2.7 Code | Basis | Reading |
|---|---|---|---|---|
| Agentic | Not ranked | 47.7Estimated · #72/154 | Not comparableBenchAlign lane · 2 vs 4 public rows | Not comparable |
| Coding | Not ranked | 51.6Estimated · #53/156 | Not comparableBenchAlign lane · 3 vs 7 public rows | Not comparable |
| Reasoning | 73.7Unranked · 2 rankable rows | 75.5Unranked · 2 rankable rows | 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 |
| Knowledge | Not ranked | 61.6Estimated · #31/186 | Not comparableBenchAlign lane · 1 vs 0 public rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 75.1#59/124 | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
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
- Grok 4.7
- $0.005
- Fits in one request
- Kimi K2.7 Code
- $0.00295
- Fits in one request
Kimi K2.7 Code has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Grok 4.7
- $0.118
- Fits in one request
- Kimi K2.7 Code
- $0.0595
- Fits in one request
Kimi K2.7 Code has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Grok 4.7
- $0.2
- Fits in one request
- Kimi K2.7 Code
- $0.249
- Fits in one request
- Cached input priced at the published list-input rate
Grok 4.7 has the lower modeled cost
Kimi K2.7 Code 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.
SpecificationGrok 4.7Kimi K2.7 Code
Context window
Maximum documented context; output-token limits may be lower.
Grok 4.7
Kimi K2.7 Code
256K
API model ID
Grok 4.7
grok-4.7
xAI Grok 4.7 model documentationKimi K2.7 Code
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Grok 4.7
$0.5 per 1M cached input tokens
xAI Grok 4.7 model documentationKimi K2.7 Code
Not published
Documented inputs
Grok 4.7
text, image
xAI Grok 4.7 model documentationKimi K2.7 Code
Not sourced
Documented outputs
Grok 4.7
Kimi K2.7 Code
Not sourced
Provider availability
Grok 4.7
Generally Available · xAI API, xAI US regional endpoint, Grok Build, Cursor, model gateways
xAI Grok 4.7 model documentationKimi K2.7 Code
Not sourced
Reasoning profile
Grok 4.7
Reasoning
Kimi K2.7 Code
Reasoning
Weight access
Grok 4.7
Proprietary
Kimi K2.7 Code
Open Weight
License
Grok 4.7
Proprietary
Kimi K2.7 Code
Open Weight
Release date
Grok 4.7
2026-09-21
Kimi K2.7 Code
2026-06-12
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
- At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
- Workload cost
- Repository review: $0.118 vs $0.0595. Cache-heavy agent loop: $0.2 vs $0.249.
- Context tradeoff
- Grok 4.7 has the larger documented window (500K).
Run the same representative tasks against both endpoints before changing production traffic.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Grok 4.7
API / mo$6,000
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Kimi K2.7 Code
API / mo$3,713
Self-host / mo$18,221
Break-even326M/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 evidence16 rows
Agentic
Terminal-Bench 4.0
Grok 4.738.00%SourceKimi K2.7 Code—Not directly comparable
Terminal-Bench 2.1 (Vals)
Grok 4.776.0%SourceKimi K2.7 Code67.0%SourceGrok 4.7 leads this result
Kimi Claw 24/7
Grok 4.7—Kimi K2.7 Code46.9%SourceNot directly comparable
MCP Atlas
Grok 4.7—Kimi K2.7 Code76%SourceNot directly comparable
MCP Mark Verified
Grok 4.7—Kimi K2.7 Code81.1%SourceNot directly comparable
Coding
cursorBench40
Grok 4.746.3%SourceKimi K2.7 Code—Not directly comparable
DeepSWE
Grok 4.771.0%SourceKimi K2.7 Code—Not directly comparable
EEBench
Grok 4.764.0%SourceKimi K2.7 Code—Not directly comparable
Kimi Code Bench v2
Grok 4.7—Kimi K2.7 Code62.0%SourceNot directly comparable
ProgramBench
Grok 4.7—Kimi K2.7 Code53.6%SourceNot directly comparable
MLS-Bench Lite
Grok 4.7—Kimi K2.7 Code35.1%SourceNot directly comparable
cursorBench32
Grok 4.7—Kimi K2.7 Code49.7%SourceNot directly comparable
OpenHarmony Bench
Grok 4.7—Kimi K2.7 Code52.1%SourceNot directly comparable
LiveCodeBench (Vals)
Grok 4.7—Kimi K2.7 Code82.1%SourceNot directly comparable
SWE-bench (Vals)
Grok 4.7—Kimi K2.7 Code78.2%SourceNot directly comparable
Knowledge
HealthBench Professional
Grok 4.756.7%SourceKimi K2.7 Code—Not directly comparable
Questions
Which is better, Grok 4.7 or Kimi K2.7 Code?
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Grok 4.7 or Kimi K2.7 Code?
Grok 4.7 is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Grok 4.7 or Kimi K2.7 Code?
Grok 4.7 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Grok 4.7 or Kimi K2.7 Code?
For the stated presets, chat costs $0.005 on Grok 4.7 and $0.00295 on Kimi K2.7 Code; repository review costs $0.118 and $0.0595; the cache-heavy agent loop costs $0.2 and $0.249. Kimi K2.7 Code has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Grok 4.7 or Kimi K2.7 Code?
Grok 4.7 has the larger documented context window: 500K, compared with 256K.
Related comparisons
Last updated September 21, 2026
Watch Grok 4.7 vs Kimi K2.7 Code
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.