Skip to main content
BenchLM
Data

Claude Haiku 5.5 vs GPT-6 Luna

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 estimate, 63.5 versus 61.3, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 19 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
OpenAI logo

OpenAI

61.3/100

Supported · Public rank #49

90% interval 57.1–65.4

API price per 1M tokens

Claude Haiku 5.5: $0.10 input / $0.50 output

GPT-6 Luna: $0.10 input / $0.50 output

Context window

Claude Haiku 5.5: 1M

GPT-6 Luna: 1.05M

Released

Claude Haiku 5.5: October 7, 2026

GPT-6 Luna: September 22, 2026

Shared results
19
Claude Haiku 5.5 only
8
GPT-6 Luna only
11
Like-for-like categories
7 / 8
Supported: Claude Haiku 5.5 and GPT-6 LunaHow 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 61.2, 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 63.8, 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

    GPT-6 Luna

    GPT-6 Luna has the larger documented context window.

    Confidence: documented
Show secondary and unsupported calls
  • 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

    No clear pick

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates
  • 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

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 5.561.2GPT-6 Luna

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.

1 category rests 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.

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
GPT-6 Luna
63.8
Supported · #42/182
Basis
BenchAlign v6.0 lane · 9 vs 9 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Coding

Like-for-like
Claude Haiku 5.5
67.9
Supported · #28/180
GPT-6 Luna
61.2
Supported · #46/180
Basis
BenchAlign v6.0 lane · 7 vs 4 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Reasoning

Like-for-like
Claude Haiku 5.5
62.6
Supported · #38/161
GPT-6 Luna
56.5
Supported · #54/161
Basis
BenchAlign v6.0 lane · 4 vs 5 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Multimodal

Like-for-like
Claude Haiku 5.5
63.9
Supported · #39/119
GPT-6 Luna
65.2
Supported · #34/119
Basis
BenchAlign v6.0 lane · 4 vs 5 public rows
Reading
GPT-6 Luna leads · intervals overlap

Knowledge

Like-for-like
Claude Haiku 5.5
50.2
Supported · #84/158
GPT-6 Luna
62.8
Supported · #35/158
Basis
BenchAlign v6.0 lane · 1 vs 5 public rows
Reading
GPT-6 Luna leads · intervals overlap

Instruction following

Like-for-like
Claude Haiku 5.5
58.3
Supported · #37/143
GPT-6 Luna
57.2
Supported · #42/143
Basis
BenchAlign v6.0 lane · 0 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
GPT-6 Luna
61.5
Supported · #30/125
Basis
BenchAlign v6.0 lane · 2 vs 2 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Multilingual

Directional only
Claude Haiku 5.5
56.1
Estimated · #36/88
GPT-6 Luna
58.6
Estimated · #29/88
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Directional only

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
GPT-6 Luna
$0.00035
Fits in one request

Modeled costs are equal

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
GPT-6 Luna
$0.0065
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 Haiku 5.5
$0.009
Fits in one request
GPT-6 Luna
$0.009
Fits in one request

Modeled costs are equal

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
GPT-6 Luna
$2.00
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.

AClaude Haiku 5.5BGPT-6 Luna

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.
  • 1 model at the same price scores higher than GPT-6 Luna. The nearest is Claude Haiku 5.5 (score 63.5, also $0.50 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 GPT-6 Luna 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.

Reasoning profile

Claude Haiku 5.5

Reasoning

GPT-6 Luna

Reasoning

Weight access

Claude Haiku 5.5

Proprietary

GPT-6 Luna

Proprietary

License

Claude Haiku 5.5

Proprietary

GPT-6 Luna

Proprietary

Release date

Claude Haiku 5.5

2026-10-07

GPT-6 Luna

2026-09-22

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 estimate, 63.5 versus 61.3, but the 90% score intervals overlap.
Workload cost
Repository review: $0.0065 vs $0.0065. Cache-heavy agent loop: $0.009 vs $0.009.
Context tradeoff
GPT-6 Luna has the larger documented window (1.05M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Claude Haiku 5.5 or GPT-6 Luna?

Claude Haiku 5.5 has the higher public score estimate, 63.5 versus 61.3, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Claude Haiku 5.5 or GPT-6 Luna?

Claude Haiku 5.5 has the higher public coding point estimate, 67.9 to 61.2, 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 GPT-6 Luna?

Claude Haiku 5.5 has the higher public agentic tasks point estimate, 68.3 to 63.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which costs less, Claude Haiku 5.5 or GPT-6 Luna?

For the stated presets, chat costs $0.00035 on Claude Haiku 5.5 and $0.00035 on GPT-6 Luna; repository review costs $0.0065 and $0.0065; the cache-heavy agent loop costs $0.009 and $0.009. Costs use the listed standard API rates.

Which has the larger context window, Claude Haiku 5.5 or GPT-6 Luna?

GPT-6 Luna has the larger documented context window: 1.05M, compared with 1M.

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%
    GPT-6 Luna58.79%

    GPT-6 Luna leads this result

  • Terminal-Bench 4.1

    Shared source
    Claude Haiku 5.540.00%
    GPT-6 Luna15.20%

    Claude Haiku 5.5 leads this result

  • Agents' Last Exam (Linux)

    Shared source
    Claude Haiku 5.557.0%
    GPT-6 Luna57.1%

    GPT-6 Luna leads this result

  • Terminal-Bench 4.0

    Claude Haiku 5.539.20%
    Source
    GPT-6 Luna—

    Not directly comparable

  • HLE w/ tools

    Claude Haiku 5.557.4%
    Source
    GPT-6 Luna—

    Not directly comparable

  • MazeBench

    Claude Haiku 5.51%
    Source
    GPT-6 Luna0%
    Source

    Claude Haiku 5.5 leads this result

  • Hermes Index

    Shared source
    Claude Haiku 5.537.0%
    GPT-6 Luna33.9%

    Claude Haiku 5.5 leads this result

  • Hermes Bench

    Shared source
    Claude Haiku 5.571.0%
    GPT-6 Luna70.5%

    Claude Haiku 5.5 leads this result

  • OSWorld 2.1 Offline

    Shared source
    Claude Haiku 5.572.4%
    GPT-6 Luna48.9%

    Claude Haiku 5.5 leads this result

  • ExploitGym

    Claude Haiku 5.5—
    GPT-6 Luna11.6%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Haiku 5.5—
    GPT-6 Luna73.0%
    Source

    Not directly comparable

Coding

  • FrontierCode 1.1 Main

    Claude Haiku 5.546.4%
    Source
    GPT-6 Luna—

    Not directly comparable

  • Bug Hunt Bench

    Shared source
    Claude Haiku 5.521.5 fixes
    GPT-6 Luna18.3 fixes

    Claude Haiku 5.5 leads this result

  • FrontierSWE v2

    Claude Haiku 5.543.8%
    Source
    GPT-6 Luna—

    Not directly comparable

  • FrontierCode 2.0

    Shared source
    Claude Haiku 5.528.9%
    GPT-6 Luna22.7%

    Claude Haiku 5.5 leads this result

  • CursorBench 4.0

    Claude Haiku 5.548.4%
    Source
    GPT-6 Luna—

    Not directly comparable

  • VulcanBench Frontier v4

    Shared source
    Claude Haiku 5.592.2%
    GPT-6 Luna71.9%

    Claude Haiku 5.5 leads this result

  • CursorBench 4.1

    Claude Haiku 5.548.4%
    Source
    GPT-6 Luna—

    Not directly comparable

  • DeepSWE

    Claude Haiku 5.5—
    GPT-6 Luna66.6%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-1

    Claude Haiku 5.589.00%
    Source
    GPT-6 Luna86.67%
    Source

    Claude Haiku 5.5 leads this result

  • ARC-AGI-2

    Claude Haiku 5.561.3%
    Source
    GPT-6 Luna59.3%
    Source

    Claude Haiku 5.5 leads this result

  • ARC-AGI-3

    Claude Haiku 5.50.5%
    Source
    GPT-6 Luna0.1%
    Source

    Claude Haiku 5.5 leads this result

  • ARC-AGI-3 Provider Adapter

    Claude Haiku 5.52.82%
    Source
    GPT-6 Luna0.59%
    Source

    Claude Haiku 5.5 leads this result

  • BioBasicsBench

    Claude Haiku 5.5—
    GPT-6 Luna37.6%
    Source

    Not directly comparable

Multimodal

  • ParseBench-2

    Shared source
    Claude Haiku 5.571.24%
    GPT-6 Luna74.59%

    GPT-6 Luna leads this result

  • PerceptionBench (tools)

    Shared source
    Claude Haiku 5.578.6%
    GPT-6 Luna62.8%

    Claude Haiku 5.5 leads this result

  • ParseBench-1

    Shared source
    Claude Haiku 5.556.06%
    GPT-6 Luna64.13%

    GPT-6 Luna leads this result

  • Chartography (no tools)

    Claude Haiku 5.546.4%
    Source
    GPT-6 Luna—

    Not directly comparable

  • ExtractBench Pro

    Claude Haiku 5.5—
    GPT-6 Luna0%
    Source

    Not directly comparable

  • ExtractBench (LlamaIndex)

    Claude Haiku 5.5—
    GPT-6 Luna91.01%
    Source

    Not directly comparable

Knowledge

  • HLE w/o tools

    Claude Haiku 5.545.9%
    Source
    GPT-6 Luna—

    Not directly comparable

  • HealthBench (raw)

    Claude Haiku 5.5—
    GPT-6 Luna50.0%
    Source

    Not directly comparable

  • HealthBench (length-adjusted)

    Claude Haiku 5.5—
    GPT-6 Luna54.5%
    Source

    Not directly comparable

  • HealthBench Professional

    Claude Haiku 5.5—
    GPT-6 Luna60.8%
    Source

    Not directly comparable

  • HealthBench Professional (raw)

    Claude Haiku 5.5—
    GPT-6 Luna61.2%
    Source

    Not directly comparable

  • HealthBench Hard

    Claude Haiku 5.5—
    GPT-6 Luna31.4%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Claude Haiku 5.575.088%
    GPT-6 Luna78.947%

    GPT-6 Luna leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    Claude Haiku 5.546.341%
    GPT-6 Luna56.098%

    GPT-6 Luna leads this result

38 public results · 19 shared

Watch Claude Haiku 5.5 vs GPT-6 Luna

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