Agentic
Directional only- Claude Sonnet 4.5
- 55.4
- Kimi K3
- 89.5
- Weighted basis
- 2 vs 2 rows
- Reading
- Directional only
Claude Sonnet 4.5 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, 80.53 versus 54.15, and the 90% score intervals do not overlap.
3 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
Show secondary and unsupported calls
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
Chat turn cost
1K fresh input + 500 output tokens
No clear pick
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-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. Claude Sonnet 4.5 does not fit this workload in one request. Claude Sonnet 4.5 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
No clear pick
A complete comparable API-rate estimate is not available for both models.
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.
8 Claude Sonnet 4.5 only
3 Shared
37 Kimi K3 only
- Shared results
- 3
- Claude Sonnet 4.5 only
- 8
- Kimi K3 only
- 37
- Like-for-like categories
- 0 / 8
2 categories use 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.
Knowledge
Directional only- Claude Sonnet 4.5
- 83.4
- Kimi K3
- 61.0
- Weighted basis
- 1 vs 2 rows
- Reading
- Directional only
Coding
Not comparable- Claude Sonnet 4.5
- 77.2
- Kimi K3
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- Claude Sonnet 4.5
- 13.6
- Kimi K3
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- Claude Sonnet 4.5
- 11.2
- Kimi K3
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Sonnet 4.5
- Not measured
- Kimi K3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Sonnet 4.5
- Not measured
- Kimi K3
- 78.5
- Weighted basis
- 0 vs 3 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Sonnet 4.5
- Not measured
- Kimi K3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Claude Sonnet 4.5 | Kimi K3 | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 55.4 | 89.5 | Directional only2 vs 2 rows | Directional only |
| Knowledge | 83.4 | 61.0 | Directional only1 vs 2 rows | Directional only |
| Coding | 77.2 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Reasoning | 13.6 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Math | 11.2 | 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
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
- Claude Sonnet 4.5
- $0.0105
- Fits in one request
- Kimi K3
- $0.0105
- Fits in one request
Modeled costs are equal
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Sonnet 4.5
- $0.195
- Fits in one request
- Kimi K3
- $0.195
- Fits in one request
Modeled costs are equal
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Sonnet 4.5
- $0.81
- Does not fit in one request
- Cached input priced at the published list-input rate
- Kimi K3
- $0.27
- Fits in one request
Claude Sonnet 4.5 does not fit this workload in one request. Claude Sonnet 4.5 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.
SpecificationClaude Sonnet 4.5Kimi K3
Context window
Maximum documented context; output-token limits may be lower.
Claude Sonnet 4.5
200K
Kimi K3
1.05M
API model ID
Claude Sonnet 4.5
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.
Claude Sonnet 4.5
Not published
Kimi K3
$0.3 per 1M cached input tokens
Documented inputs
Claude Sonnet 4.5
Not sourced
Kimi K3
Not sourced
Documented outputs
Claude Sonnet 4.5
Not sourced
Kimi K3
Not sourced
Provider availability
Claude Sonnet 4.5
Not sourced
Kimi K3
Not sourced
Reasoning profile
Claude Sonnet 4.5
Non-Reasoning
Kimi K3
Reasoning
Weight access
Claude Sonnet 4.5
Proprietary
Kimi K3
Pending
License
Claude Sonnet 4.5
Proprietary
Kimi K3
Pending
Release date
Claude Sonnet 4.5
2025-09-01
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, 80.53 versus 54.15, and the 90% score intervals do not overlap.
- Workload cost
- Repository review: $0.195 vs $0.195. Cache-heavy agent loop: $0.81 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 evidence48 rows
Agentic
Terminal-Bench 2.0
Claude Sonnet 4.550%SourceKimi K388.3%SourceKimi K3 leads this result
OSWorld-Verified
Claude Sonnet 4.561.4%SourceKimi K3—Not directly comparable
VITA-Bench
Claude Sonnet 4.517.0%SourceKimi K3—Not directly comparable
Gert Labs
Claude Sonnet 4.548.51%SourceKimi K3—Not directly comparable
JobBench
Claude Sonnet 4.527.7%SourceKimi K352.9%SourceKimi K3 leads this result
BrowseComp
Claude Sonnet 4.5—Kimi K391.2%SourceNot directly comparable
DeepSearchQA
Claude Sonnet 4.5—Kimi K395.0%SourceNot directly comparable
Toolathlon-Verified
Claude Sonnet 4.5—Kimi K373.2%SourceNot directly comparable
MCP Atlas
Claude Sonnet 4.5—Kimi K384.2%SourceNot directly comparable
AutomationBench
Claude Sonnet 4.5—Kimi K330.8%SourceNot directly comparable
APEX-Agents
Claude Sonnet 4.5—Kimi K337.6%SourceNot directly comparable
SpreadsheetBench 2
Claude Sonnet 4.5—Kimi K334.8%SourceNot directly comparable
DECK-Bench
Claude Sonnet 4.5—Kimi K373.5%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Sonnet 4.577.2%SourceKimi K3—Not directly comparable
deepSwe
Claude Sonnet 4.5—Kimi K367.5%SourceNot directly comparable
cursorBench32
Claude Sonnet 4.5—Kimi K360.8%SourceNot directly comparable
FrontierSWE
Claude Sonnet 4.5—Kimi K381.2%SourceNot directly comparable
ProgramBench
Claude Sonnet 4.5—Kimi K377.8%SourceNot directly comparable
Kimi Code Bench v2
Claude Sonnet 4.5—Kimi K372.9%SourceNot directly comparable
sweMarathon
Claude Sonnet 4.5—Kimi K342%SourceNot directly comparable
PostTrain Bench
Claude Sonnet 4.5—Kimi K336.6%SourceNot directly comparable
MLS-Bench Lite
Claude Sonnet 4.5—Kimi K348.3%SourceNot directly comparable
VulcanBench v3
Claude Sonnet 4.5—Kimi K373.9%SourceNot directly comparable
APEX-SWE
Claude Sonnet 4.5—Kimi K348.0%SourceNot directly comparable
EEBench
Claude Sonnet 4.5—Kimi K338.3%SourceNot directly comparable
InferenceEval
Claude Sonnet 4.5—Kimi K339.8%SourceNot directly comparable
KernelBench Internal
Claude Sonnet 4.5—Kimi K368.5%SourceNot directly comparable
Reasoning
ARC-AGI-2
Claude Sonnet 4.513.6%SourceKimi K3—Not directly comparable
Knowledge
Math
Multimodal
OfficeQA Pro
Claude Sonnet 4.5—Kimi K363.3%SourceNot directly comparable
MMMU-Pro
Claude Sonnet 4.5—Kimi K381.6%SourceNot directly comparable
MMMU-Pro w/ Python
Claude Sonnet 4.5—Kimi K383.4%SourceNot directly comparable
CharXiv w/o tools
Claude Sonnet 4.5—Kimi K384.8%SourceNot directly comparable
CharXiv
Claude Sonnet 4.5—Kimi K391.3%SourceNot directly comparable
MathVision
Claude Sonnet 4.5—Kimi K394.3%SourceNot directly comparable
MathVision w/ Python
Claude Sonnet 4.5—Kimi K397.8%SourceNot directly comparable
BabyVision w/ Python
Claude Sonnet 4.5—Kimi K385.7%SourceNot directly comparable
ZeroBench
Claude Sonnet 4.5—Kimi K323.0%SourceNot directly comparable
ZeroBench w/ Python
Claude Sonnet 4.5—Kimi K341.0%SourceNot directly comparable
WorldVQA ForceAnswer
Claude Sonnet 4.5—Kimi K351.0%SourceNot directly comparable
OmniDocBench
Claude Sonnet 4.5—Kimi K391.1%SourceNot directly comparable
PerceptionBench
Claude Sonnet 4.5—Kimi K358.5%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Sonnet 4.5 or Kimi K3?
Kimi K3 has the higher public score, 80.53 versus 54.15, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, Claude Sonnet 4.5 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, Claude Sonnet 4.5 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, Claude Sonnet 4.5 or Kimi K3?
For the stated presets, chat costs $0.0105 on Claude Sonnet 4.5 and $0.0105 on Kimi K3; repository review costs $0.195 and $0.195; the cache-heavy agent loop costs $0.81 and $0.27. Claude Sonnet 4.5 does not fit this workload in one request. Claude Sonnet 4.5 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Sonnet 4.5 or Kimi K3?
Kimi K3 has the larger documented context window: 1.05M, compared with 200K.
Related comparisons
Last updated August 19, 2026
Watch Claude Sonnet 4.5 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.