Coding
Like-for-like- Claude Haiku 4.5
- 27.2
- Supported · #144/151
- Kimi K2.7 Code
- 50.9
- Supported · #51/151
- Basis
- BenchAlign lane · 4 vs 5 public rows
- Reading
- Kimi K2.7 Code leads
Claude Haiku 4.5 vs Kimi K2.7 Code
Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.
0 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
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.
Coding work
Code generation, repair, and software-engineering tasks
Kimi K2.7 Code
Kimi K2.7 Code leads on the public coding lane, 50.9 to 27.2, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: stronger
Long documents
Prompts that approach the documented context limit
Kimi K2.7 Code
Kimi K2.7 Code 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
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
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Kimi K2.7 Code is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
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. Kimi K2.7 Code has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
10 Claude Haiku 4.5 only
8 Kimi K2.7 Code only
- Shared results
- 0
- Claude Haiku 4.5 only
- 10
- Kimi K2.7 Code only
- 8
- Like-for-like categories
- 1 / 8
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
Agentic
Directional only- Claude Haiku 4.5
- 27.0
- Supported · #142/152
- Kimi K2.7 Code
- 46.8
- Estimated · #72/152
- Basis
- BenchAlign lane · 2 vs 3 public rows
- Reading
- Directional only
Knowledge
Directional only- Claude Haiku 4.5
- 44.2
- Estimated · #115/183
- Kimi K2.7 Code
- 61.6
- Estimated · #31/183
- Basis
- BenchAlign lane · 2 vs 0 public rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Haiku 4.5
- Not ranked
- Kimi K2.7 Code
- 75.5
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Haiku 4.5
- 28.9
- Unranked · 2 rankable rows
- Kimi K2.7 Code
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Haiku 4.5
- Not ranked
- Kimi K2.7 Code
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Haiku 4.5
- Not ranked
- Kimi K2.7 Code
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Haiku 4.5
- Not ranked
- Kimi K2.7 Code
- 76.6
- #58/123
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Haiku 4.5 | Kimi K2.7 Code | Basis | Reading |
|---|---|---|---|---|
| Coding | 27.2Supported · #144/151 | 50.9Supported · #51/151 | Like-for-likeBenchAlign lane · 4 vs 5 public rows | Kimi K2.7 Code leads |
| Agentic | 27.0Supported · #142/152 | 46.8Estimated · #72/152 | Directional onlyBenchAlign lane · 2 vs 3 public rows | Directional only |
| Knowledge | 44.2Estimated · #115/183 | 61.6Estimated · #31/183 | Directional onlyBenchAlign lane · 2 vs 0 public rows | Directional only |
| Reasoning | Not ranked | 75.5Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 28.9Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | 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 |
| Instruction following | Not ranked | 76.6#58/123 | 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
- Claude Haiku 4.5
- $0.0035
- 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
- Claude Haiku 4.5
- $0.065
- 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
- Claude Haiku 4.5
- $0.09
- Does not fit in one request
- Kimi K2.7 Code
- $0.249
- Fits in one request
- Cached input priced at the published list-input rate
Claude Haiku 4.5 does not fit this workload in one request. 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.
SpecificationClaude Haiku 4.5Kimi K2.7 Code
Context window
Maximum documented context; output-token limits may be lower.
Claude Haiku 4.5
Kimi K2.7 Code
256K
API model ID
Claude Haiku 4.5
claude-haiku-4-5-20251001
Claude API pricingKimi 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.
Claude Haiku 4.5
$0.1 per 1M cached input tokens
Claude API pricingKimi K2.7 Code
Not published
Documented inputs
Claude Haiku 4.5
Not sourced
Kimi K2.7 Code
Not sourced
Documented outputs
Claude Haiku 4.5
Not sourced
Kimi K2.7 Code
Not sourced
Provider availability
Claude Haiku 4.5
Not sourced
Kimi K2.7 Code
Not sourced
Reasoning profile
Claude Haiku 4.5
Non-Reasoning
Kimi K2.7 Code
Reasoning
Weight access
Claude Haiku 4.5
Proprietary
Kimi K2.7 Code
Open Weight
License
Claude Haiku 4.5
Proprietary
Kimi K2.7 Code
Open Weight
Release date
Claude Haiku 4.5
2025-10-15
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
- The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
- Workload cost
- Repository review: $0.065 vs $0.0595. Cache-heavy agent loop: $0.09 vs $0.249.
- Context tradeoff
- Kimi K2.7 Code has the larger documented window (256K).
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.
Claude Haiku 4.5
API / mo$4,500
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 evidence18 rows
Agentic
JobBench
Claude Haiku 4.516.0%SourceKimi K2.7 Code—Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Haiku 4.543.8%SourceKimi K2.7 Code—Not directly comparable
Kimi Claw 24/7
Claude Haiku 4.5—Kimi K2.7 Code46.9%SourceNot directly comparable
MCP Atlas
Claude Haiku 4.5—Kimi K2.7 Code76%SourceNot directly comparable
MCP Mark Verified
Claude Haiku 4.5—Kimi K2.7 Code81.1%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Haiku 4.573.3%SourceKimi K2.7 Code—Not directly comparable
VulcanBench v3
Claude Haiku 4.576.2%SourceKimi K2.7 Code—Not directly comparable
LiveCodeBench (Vals)
Claude Haiku 4.541.2%SourceKimi K2.7 Code—Not directly comparable
SWE-bench (Vals)
Claude Haiku 4.566.6%SourceKimi K2.7 Code—Not directly comparable
Kimi Code Bench v2
Claude Haiku 4.5—Kimi K2.7 Code62.0%SourceNot directly comparable
ProgramBench
Claude Haiku 4.5—Kimi K2.7 Code53.6%SourceNot directly comparable
MLS-Bench Lite
Claude Haiku 4.5—Kimi K2.7 Code35.1%SourceNot directly comparable
cursorBench32
Claude Haiku 4.5—Kimi K2.7 Code49.7%SourceNot directly comparable
OpenHarmony Bench
Claude Haiku 4.5—Kimi K2.7 Code52.1%SourceNot directly comparable
Knowledge
Math
Frequently asked questions
Which is better, Claude Haiku 4.5 or Kimi K2.7 Code?
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Claude Haiku 4.5 or Kimi K2.7 Code?
Kimi K2.7 Code leads the public coding lane, 50.9 to 27.2, with Supported evidence for both models and non-overlapping 90% intervals.
Which is better for agentic tasks, Claude Haiku 4.5 or Kimi K2.7 Code?
Kimi K2.7 Code scores higher for agentic tasks on the public lane, 46.8 to 27. Kimi K2.7 Code is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Claude Haiku 4.5 or Kimi K2.7 Code?
For the stated presets, chat costs $0.0035 on Claude Haiku 4.5 and $0.00295 on Kimi K2.7 Code; repository review costs $0.065 and $0.0595; the cache-heavy agent loop costs $0.09 and $0.249. Claude Haiku 4.5 does not fit this workload in one request. Kimi K2.7 Code has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Haiku 4.5 or Kimi K2.7 Code?
Kimi K2.7 Code has the larger documented context window: 256K, compared with 200K.
Related comparisons
Last updated September 10, 2026
Watch Claude Haiku 4.5 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.