Agentic
Not comparable- Claude Haiku 4.5
- Not measured
- Kimi K3
- 89.5
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Claude Haiku 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 57.04, 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
Chat turn cost
1K fresh input + 500 output tokens
Claude Haiku 4.5
Claude Haiku 4.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Claude Haiku 4.5
Claude Haiku 4.5 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
No shared weighted benchmark basis supports a winner.
Confidence: limited
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 Haiku 4.5 does not fit this workload in one request.
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.
3 Claude Haiku 4.5 only
3 Shared
37 Kimi K3 only
- Shared results
- 3
- Claude Haiku 4.5 only
- 3
- Kimi K3 only
- 37
- Like-for-like categories
- 0 / 8
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.
Coding
Not comparable- Claude Haiku 4.5
- 73.3
- Kimi K3
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- Claude Haiku 4.5
- Not measured
- Kimi K3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude Haiku 4.5
- Not measured
- Kimi K3
- 61.0
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Math
Not comparable- Claude Haiku 4.5
- 4.9
- Kimi K3
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Haiku 4.5
- Not measured
- Kimi K3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Haiku 4.5
- Not measured
- Kimi K3
- 78.5
- Weighted basis
- 0 vs 3 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Haiku 4.5
- Not measured
- Kimi K3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Claude Haiku 4.5 | Kimi K3 | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | Not measured | 89.5 | Not comparable0 vs 2 rows | Not comparable |
| Coding | 73.3 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Knowledge | Not measured | 61.0 | Not comparable0 vs 2 rows | Not comparable |
| Math | 4.9 | 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.
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
- Claude Haiku 4.5
- $0.0035
- Fits in one request
- Kimi K3
- $0.0105
- Fits in one request
Claude Haiku 4.5 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Haiku 4.5
- $0.065
- Fits in one request
- Kimi K3
- $0.195
- Fits in one request
Claude Haiku 4.5 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Haiku 4.5
- $0.09
- Does not fit in one request
- Kimi K3
- $0.27
- Fits in one request
Claude Haiku 4.5 does not fit this workload in one request.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Haiku 4.5Kimi K3
Context window
Maximum documented context; output-token limits may be lower.
Claude Haiku 4.5
Kimi K3
1.05M
API model ID
Claude Haiku 4.5
claude-haiku-4-5-20251001
Claude API pricingKimi 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 Haiku 4.5
$0.1 per 1M cached input tokens
Claude API pricingKimi K3
$0.3 per 1M cached input tokens
Documented inputs
Claude Haiku 4.5
Not sourced
Kimi K3
Not sourced
Documented outputs
Claude Haiku 4.5
Not sourced
Kimi K3
Not sourced
Provider availability
Claude Haiku 4.5
Not sourced
Kimi K3
Not sourced
Reasoning profile
Claude Haiku 4.5
Non-Reasoning
Kimi K3
Reasoning
Weight access
Claude Haiku 4.5
Proprietary
Kimi K3
Pending
License
Claude Haiku 4.5
Proprietary
Kimi K3
Pending
Release date
Claude Haiku 4.5
2025-10-15
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 57.04, and the 90% score intervals do not overlap.
- Workload cost
- Repository review: $0.065 vs $0.195. Cache-heavy agent loop: $0.09 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 evidence43 rows
Agentic
JobBench
Claude Haiku 4.516.0%SourceKimi K352.9%SourceKimi K3 leads this result
Terminal-Bench 2.0
Claude Haiku 4.5—Kimi K388.3%SourceNot directly comparable
BrowseComp
Claude Haiku 4.5—Kimi K391.2%SourceNot directly comparable
DeepSearchQA
Claude Haiku 4.5—Kimi K395.0%SourceNot directly comparable
Toolathlon-Verified
Claude Haiku 4.5—Kimi K373.2%SourceNot directly comparable
MCP Atlas
Claude Haiku 4.5—Kimi K384.2%SourceNot directly comparable
AutomationBench
Claude Haiku 4.5—Kimi K330.8%SourceNot directly comparable
APEX-Agents
Claude Haiku 4.5—Kimi K337.6%SourceNot directly comparable
SpreadsheetBench 2
Claude Haiku 4.5—Kimi K334.8%SourceNot directly comparable
DECK-Bench
Claude Haiku 4.5—Kimi K373.5%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Haiku 4.573.3%SourceKimi K3—Not directly comparable
VulcanBench v3
Shared sourceClaude Haiku 4.578.3%Kimi K373.9%Claude Haiku 4.5 leads this result
EEBench
Shared sourceClaude Haiku 4.53.5%Kimi K338.3%Kimi K3 leads this result
deepSwe
Claude Haiku 4.5—Kimi K367.5%SourceNot directly comparable
cursorBench32
Claude Haiku 4.5—Kimi K360.8%SourceNot directly comparable
FrontierSWE
Claude Haiku 4.5—Kimi K381.2%SourceNot directly comparable
ProgramBench
Claude Haiku 4.5—Kimi K377.8%SourceNot directly comparable
Kimi Code Bench v2
Claude Haiku 4.5—Kimi K372.9%SourceNot directly comparable
sweMarathon
Claude Haiku 4.5—Kimi K342%SourceNot directly comparable
PostTrain Bench
Claude Haiku 4.5—Kimi K336.6%SourceNot directly comparable
MLS-Bench Lite
Claude Haiku 4.5—Kimi K348.3%SourceNot directly comparable
APEX-SWE
Claude Haiku 4.5—Kimi K348.0%SourceNot directly comparable
InferenceEval
Claude Haiku 4.5—Kimi K339.8%SourceNot directly comparable
KernelBench Internal
Claude Haiku 4.5—Kimi K368.5%SourceNot directly comparable
Knowledge
Math
Multimodal
OfficeQA Pro
Claude Haiku 4.5—Kimi K363.3%SourceNot directly comparable
MMMU-Pro
Claude Haiku 4.5—Kimi K381.6%SourceNot directly comparable
MMMU-Pro w/ Python
Claude Haiku 4.5—Kimi K383.4%SourceNot directly comparable
CharXiv w/o tools
Claude Haiku 4.5—Kimi K384.8%SourceNot directly comparable
CharXiv
Claude Haiku 4.5—Kimi K391.3%SourceNot directly comparable
MathVision
Claude Haiku 4.5—Kimi K394.3%SourceNot directly comparable
MathVision w/ Python
Claude Haiku 4.5—Kimi K397.8%SourceNot directly comparable
BabyVision w/ Python
Claude Haiku 4.5—Kimi K385.7%SourceNot directly comparable
ZeroBench
Claude Haiku 4.5—Kimi K323.0%SourceNot directly comparable
ZeroBench w/ Python
Claude Haiku 4.5—Kimi K341.0%SourceNot directly comparable
WorldVQA ForceAnswer
Claude Haiku 4.5—Kimi K351.0%SourceNot directly comparable
OmniDocBench
Claude Haiku 4.5—Kimi K391.1%SourceNot directly comparable
PerceptionBench
Claude Haiku 4.5—Kimi K358.5%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Haiku 4.5 or Kimi K3?
Kimi K3 has the higher public score, 80.53 versus 57.04, 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 Haiku 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 Haiku 4.5 or Kimi K3?
The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.
Which costs less, Claude Haiku 4.5 or Kimi K3?
For the stated presets, chat costs $0.0035 on Claude Haiku 4.5 and $0.0105 on Kimi K3; repository review costs $0.065 and $0.195; the cache-heavy agent loop costs $0.09 and $0.27. Claude Haiku 4.5 does not fit this workload in one request.
Which has the larger context window, Claude Haiku 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 Haiku 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.