Skip to main content
BenchLM
Data

Claude Haiku 5.5 vs Kimi K2.7 Code

Updated November 21, 2026. Rank says Claude Haiku 5.5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Claude Haiku 5.5 has the higher public score, 63.5 versus 51.8, and the 90% score intervals do not overlap. 3 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Anthropic logo

Anthropic

63.5/100

Supported · Public rank #38

90% interval 59.5–67.6

Model B
Moonshot AI logo

Moonshot AI

51.8/100

Supported · Public rank #86

90% interval 47.0–56.5

API price per 1M tokens

Claude Haiku 5.5: $0.10 input / $0.50 output

Kimi K2.7 Code: $0.95 input / $4 output

Context window

Claude Haiku 5.5: 1M

Kimi K2.7 Code: 256K

Released

Claude Haiku 5.5: October 7, 2026

Kimi K2.7 Code: June 12, 2026

Shared results
3
Claude Haiku 5.5 only
24
Kimi K2.7 Code only
11
Like-for-like categories
4 / 8
Supported: Claude Haiku 5.5 and Kimi K2.7 CodeHow 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.

  • Coding work

    Code generation, repair, and software-engineering tasks

    Claude Haiku 5.5

    Claude Haiku 5.5 has the higher public coding point estimate, 67.9 to 49.2, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
  • Agentic work

    Tool use, computer use, and multi-step task completion

    Claude Haiku 5.5

    Claude Haiku 5.5 has the higher public agentic point estimate, 68.3 to 53.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
  • Long documents

    Prompts that approach the documented context limit

    Claude Haiku 5.5

    Claude Haiku 5.5 has the larger documented context window.

    Confidence: documented
Show secondary and unsupported calls
  • Chat turn cost

    1K fresh input + 500 output tokens

    Claude Haiku 5.5

    Claude Haiku 5.5 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

    Claude Haiku 5.5

    Claude Haiku 5.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates
  • Repository review cost

    50K fresh input + 3K output tokens

    Claude Haiku 5.5

    Claude Haiku 5.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    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.

67.9Claude Haiku 5.549.2Kimi K2.7 Code

Like-for-like · BenchAlign v6.0

Claude Haiku 5.5 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

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.

  • FrontierMath v2 (Tier 4)Math

    Normalized gap 34.1
    Claude Haiku 5.5:46.341%
    Kimi K2.7 Code:12.195%
  • FrontierMath v2 (Tiers 1-3)Math

    Normalized gap 21.1
    Claude Haiku 5.5:75.088%
    Kimi K2.7 Code:54.035%
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 v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Like-for-like
Claude Haiku 5.5
68.3
Supported · #25/182
Kimi K2.7 Code
53.6
Supported · #83/182
Basis
BenchAlign v6.0 lane · 9 vs 5 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Coding

Like-for-like
Claude Haiku 5.5
67.9
Supported · #28/180
Kimi K2.7 Code
49.2
Supported · #88/180
Basis
BenchAlign v6.0 lane · 7 vs 7 public rows
Reading
Claude Haiku 5.5 leads

Reasoning

Like-for-like
Claude Haiku 5.5
62.6
Supported · #38/161
Kimi K2.7 Code
46.8
Supported · #87/161
Basis
BenchAlign v6.0 lane · 4 vs 0 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Math

Like-for-like
Claude Haiku 5.5
62.1
Supported · #29/125
Kimi K2.7 Code
49.4
Supported · #59/125
Basis
BenchAlign v6.0 lane · 2 vs 2 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Knowledge

Directional only
Claude Haiku 5.5
50.2
Supported · #84/158
Kimi K2.7 Code
55.9
Estimated · #69/158
Basis
BenchAlign v6.0 lane · 1 vs 0 public rows
Reading
Directional only

Instruction following

Directional only
Claude Haiku 5.5
58.3
Supported · #37/143
Kimi K2.7 Code
46.4
Estimated · #85/143
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Directional only

Multimodal

Not comparable
Claude Haiku 5.5
63.9
Supported · #39/119
Kimi K2.7 Code
Not ranked
Basis
BenchAlign v6.0 lane · 4 vs 0 public rows
Reading
Not comparable

Multilingual

Not comparable
Claude Haiku 5.5
56.1
Estimated · #36/88
Kimi K2.7 Code
Not ranked
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. 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

Claude Haiku 5.5
$0.00035
Fits in one request
Kimi K2.7 Code
$0.00295
Fits in one request

Claude Haiku 5.5 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Haiku 5.5
$0.0065
Fits in one request
Kimi K2.7 Code
$0.0595
Fits in one request

Claude Haiku 5.5 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 5.5
$0.009
Fits in one request
Kimi K2.7 Code
$0.097
Fits in one request

Claude Haiku 5.5 has the lower modeled cost

Costs use the listed standard API rates.

Your workload

Enter a month of tokens to price it at both models’ listed API rates.

Claude Haiku 5.5
$2.00
per month
Kimi K2.7 Code
$17.50
per month

Standard listed rates, no batch or volume discounts.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 21, 2026.

Claude Haiku 5.5Kimi K2.7 Code

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • Claude Haiku 5.5 is on the efficiency frontier: no cheaper model scores at least as high.
  • 15 models score at least as high as Kimi K2.7 Code for the same price or less. The nearest is Kimi K2.6 (score 54.3, also $4.00 per 1M output tokens).

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See Kimi K2.7 Code on the full price vs performance chart

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Claude Haiku 5.5

$0.01 per 1M cached input tokens

Claude API pricing

Kimi K2.7 Code

$0.19 per 1M cached input tokens

Reasoning profile

Claude Haiku 5.5

Reasoning

Kimi K2.7 Code

Reasoning

Weight access

Claude Haiku 5.5

Proprietary

Kimi K2.7 Code

Open Weight

License

Claude Haiku 5.5

Proprietary

Kimi K2.7 Code

Open Weight

Release date

Claude Haiku 5.5

2026-10-07

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
Claude Haiku 5.5 has the higher public score, 63.5 versus 51.8, and the 90% score intervals do not overlap.
Workload cost
Repository review: $0.0065 vs $0.0595. Cache-heavy agent loop: $0.009 vs $0.097.
Context tradeoff
Claude Haiku 5.5 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Claude Haiku 5.5 or Kimi K2.7 Code?

Claude Haiku 5.5 has the higher public score, 63.5 versus 51.8, 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 5.5 or Kimi K2.7 Code?

Claude Haiku 5.5 has the higher public coding point estimate, 67.9 to 49.2, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which is better for agentic tasks, Claude Haiku 5.5 or Kimi K2.7 Code?

Claude Haiku 5.5 has the higher public agentic tasks point estimate, 68.3 to 53.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which costs less, Claude Haiku 5.5 or Kimi K2.7 Code?

For the stated presets, chat costs $0.00035 on Claude Haiku 5.5 and $0.00295 on Kimi K2.7 Code; repository review costs $0.0065 and $0.0595; the cache-heavy agent loop costs $0.009 and $0.097. Costs use the listed standard API rates.

Which has the larger context window, Claude Haiku 5.5 or Kimi K2.7 Code?

Claude Haiku 5.5 has the larger documented context window: 1M, compared with 256K.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Claude Haiku 5.5
API / mo$450
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Kimi K2.7 Code
API / mo$3,713
Self-host / mo$27,962
Break-evenNot reached at 70% load
Model the full break-even

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

  • Claude Haiku 5.558.62%
    Kimi K2.7 Code40.66%

    Claude Haiku 5.5 leads this result

  • Terminal-Bench 4.1

    Claude Haiku 5.540.00%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Agents' Last Exam (Linux)

    Claude Haiku 5.557.0%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Terminal-Bench 4.0

    Claude Haiku 5.539.20%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • HLE w/ tools

    Claude Haiku 5.557.4%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • MazeBench

    Claude Haiku 5.51%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Hermes Index

    Claude Haiku 5.537.0%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Hermes Bench

    Claude Haiku 5.571.0%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • OSWorld 2.1 Offline

    Claude Haiku 5.572.4%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Kimi Claw 24/7

    Claude Haiku 5.5—
    Kimi K2.7 Code46.9%
    Source

    Not directly comparable

  • MCP Atlas

    Claude Haiku 5.5—
    Kimi K2.7 Code76%
    Source

    Not directly comparable

  • MCP Mark Verified

    Claude Haiku 5.5—
    Kimi K2.7 Code81.1%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Haiku 5.5—
    Kimi K2.7 Code67.0%
    Source

    Not directly comparable

Coding

  • FrontierCode 1.1 Main

    Claude Haiku 5.546.4%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Bug Hunt Bench

    Claude Haiku 5.521.5 fixes
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • FrontierSWE v2

    Claude Haiku 5.543.8%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • FrontierCode 2.0

    Claude Haiku 5.528.9%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • CursorBench 4.0

    Claude Haiku 5.548.4%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • VulcanBench Frontier v4

    Claude Haiku 5.592.2%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • CursorBench 4.1

    Claude Haiku 5.548.4%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Kimi Code Bench v2

    Claude Haiku 5.5—
    Kimi K2.7 Code62.0%
    Source

    Not directly comparable

  • ProgramBench

    Claude Haiku 5.5—
    Kimi K2.7 Code53.6%
    Source

    Not directly comparable

  • MLS-Bench Lite

    Claude Haiku 5.5—
    Kimi K2.7 Code35.1%
    Source

    Not directly comparable

  • CursorBench 3.2

    Claude Haiku 5.5—
    Kimi K2.7 Code49.7%
    Source

    Not directly comparable

  • OpenHarmony Bench v1.0

    Claude Haiku 5.5—
    Kimi K2.7 Code52.1%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Claude Haiku 5.5—
    Kimi K2.7 Code82.1%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    Claude Haiku 5.5—
    Kimi K2.7 Code78.2%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-1

    Claude Haiku 5.589.00%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • ARC-AGI-2

    Claude Haiku 5.561.3%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • ARC-AGI-3

    Claude Haiku 5.50.5%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • ARC-AGI-3 Provider Adapter

    Claude Haiku 5.52.82%
    Source
    Kimi K2.7 Code—

    Not directly comparable

Multimodal

  • ParseBench-2

    Claude Haiku 5.571.24%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • PerceptionBench (tools)

    Claude Haiku 5.578.6%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • ParseBench-1

    Claude Haiku 5.556.06%
    Source
    Kimi K2.7 Code—

    Not directly comparable

  • Chartography (no tools)

    Claude Haiku 5.546.4%
    Source
    Kimi K2.7 Code—

    Not directly comparable

Knowledge

  • HLE w/o tools

    Claude Haiku 5.545.9%
    Source
    Kimi K2.7 Code—

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Claude Haiku 5.575.088%
    Kimi K2.7 Code54.035%

    Claude Haiku 5.5 leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    Claude Haiku 5.546.341%
    Kimi K2.7 Code12.195%

    Claude Haiku 5.5 leads this result

38 public results · 3 shared

Watch Claude Haiku 5.5 vs Kimi K2.7 Code

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 7,000+ subscribers.

Last updated November 21, 2026