Skip to main content

AnthropicOpenAILLM matchup

Claude Haiku 4.5vs.GPT-6 Luna

Which one is better?

GPT-6 Luna performs better than Claude Haiku 4.5 and is cheaper: Claude Haiku 4.5 costs 10 times as much.

GPT-6 Luna ahead
IntelligenceOverall index, 100 points = average
53.9

Claude Haiku 4.5

Rank 80

96.3

GPT-6 Luna

Rank 35

about as fast
SpeedTokens per second
97

Claude Haiku 4.5

101

GPT-6 Luna

GPT-6 Luna cheaper
Price$ per 1M tokens
$2

Claude Haiku 4.5

$0.20

GPT-6 Luna

GPT-6 Luna more popular
Popularity0 to 100
32

Claude Haiku 4.5

Rank 497 of 785

60

GPT-6 Luna

Rank 30 of 785

Above 272,000 tokens of context, GPT-6 Luna costs more: $0.20 input and $0.75 output per 1M tokens.

Choose Claude Haiku 4.5 for

No clear advantage

Choose GPT-6 Luna for

CodingReasoningGeneralFinanceAgentsProductivityKnowledge

Where is the difference?

Strengths at a glance

Haiku 4.5GPT-6 LunaMedian of all ranked models

608010012040CodingGPT-6 LunaReasoningGPT-6 LunaKnowledgeGPT-6 LunaAgentsGPT-6 LunaGeneralGPT-6 LunaFinanceGPT-6 Luna
CodingGPT-6 Luna ahead
Haiku 4.549.2Rank 95
GPT-6 Luna97.5Rank 35
Median of ranked models84.1

95 % range: Haiku 4.5 39.0 to 59.3, GPT-6 Luna 94.5 to 100.5.

AreaHaiku 4.5GPT-6 Luna

The same values and verdicts as the bars below. In the close-up the net starts at 40 points, just below the weaker model's lowest value; the reference group average is 100. Not in the net because a model has no own value there or the data are too thin: Mathematics, Multimodal, Legal, Health.

GPT-6 Luna is ahead in 6 of 10 areas, Haiku 4.5 in none.

too little data: 4GPT-6 Luna ahead: 6

Areas in the overall index
CodingGPT-6 Luna +4849.2 to 97.5
ReasoningGPT-6 Luna +4552.5 to 97.8
GeneralGPT-6 Luna +4252.3 to 94.4
AgentsGPT-6 Luna +3960.3 to 99.5
KnowledgeGPT-6 Luna +2960.4 to 89.2
Mathematicsonly GPT-6 Luna has a score
Multimodalonly GPT-6 Luna has a score
Specialist fields
FinanceGPT-6 Luna +4058.1 to 98.3
Legalonly GPT-6 Luna has a score
Healthonly GPT-6 Luna has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Show 4 more areas that do not count toward the overall index
ProductivityGPT-6 Luna +3259.0 to 90.5
Cybersecurityonly GPT-6 Luna has a score
Searchonly GPT-6 Luna has a score
Educationonly GPT-6 Luna has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Which model for which task?

Everyday tasks, translated from the area values above. Each row names the values it rests on.

Writing and debugging codeGPT-6 LunaCoding 49.2 to 97.5
Maths and data analysisGPT-6 LunaMathematics without a score for Haiku 4.5, Reasoning 52.5 to 97.8
Facts and researchGPT-6 LunaKnowledge 60.4 to 89.2, Search without a score for Haiku 4.5
Agents and workflowsGPT-6 LunaAgents 60.3 to 99.5
Fast chat repliesabout the same97 to 101 tokens per second
Security analysisopenCybersecurity without a score for Haiku 4.5
Many requests on a small budgetGPT-6 Luna$2 to $0.20 per 1M tokens
Finance, legal and medical textsGPT-6 LunaFinance 58.1 to 98.3, Legal without a score for Haiku 4.5, Health without a score for Haiku 4.5
Images, screenshots and PDFsopenMultimodal without a score for Haiku 4.5

See for yourself: same task, one attempt

The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

Claude Haiku 4.5

Claude Haiku 4.5: Pelican on a bicycle
A community classic for free-form SVG drawing.

Oct 1, 2026 · 10 s · $0.0080

Test details
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
anthropic/claude-haiku-4.5
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
1,585 tokens
Cost of the attempt
$0.0080
Response time
10.1 s
API model reported in response
anthropic/claude-haiku-4.5
Pinned endpoint
Anthropic | anthropic/claude-4.5-haiku-20251001
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

GPT-6 Luna

GPT-6 Luna: Pelican on a bicycle
A community classic for free-form SVG drawing.

Oct 1, 2026 · 47 s · $0.0022

Test details
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
openai/gpt-6-luna
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
4,493 tokens
Cost of the attempt
$0.0022
Response time
46.7 s
API model reported in response
openai/gpt-6-luna
Pinned endpoint
OpenAI | openai/gpt-6-luna-20260922
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

SVG short test

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Prompt

Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.

Claude Haiku 4.5

Claude Haiku 4.5: SVG short test

Oct 14, 2026 · $0.0043

Test details
Test run
Oct 14, 2026
Provider
anthropic
API model
anthropic/claude-haiku-4.5
Output
848 tokens
Reasoning
API reports 0 reasoning tokens
Cost of the attempt
$0.0043
Test round
43b8c5c46830

GPT-6 Luna

Unavailable in this round

Claude Haiku 4.5 and GPT-6 Luna in the overall index

Every model with a place in the overall index, both models of this matchup highlighted. You can add or hide other models.

Overall index (Gradually Meta-Score v4)

20 of 92 models

4 models in this view are measured at a lower reasoning effort than max in the overall index. Dashed column: lower reasoning effort than the top.

Claude Opus 5.5max126.1
Gemini 4 Carbonhigh125.8
Claude Fable 5.1max123.8
Claude Sonnet 5.5max122.8
Gemini 4 Argonhigh122.3
GPT-6 Astramax121.3
GPT-6.1 Solmax119.2
Muse Wonder Fullmax118.3
Claude Opus 5max117.2
Muse Wondermax113.4
Kimi K3.1 Promax112.9
Claude Fable 5max112.5
GPT-6 Solmax110.5
GPT-5.6 Solmax108.7
Muse Spark 1.3max107.4
Gemini 3.7 Flashhigh107.1
DeepSeek V4.1 Flash 1017max106.6
Gemini 3.8 Flashhigh106.5
GPT-6 Lunamax96.3
Claude Haiku 4.553.9

Popularity compared

How often the models are searched for, used and mentioned, on a scale from 0 to 100.

GPT-6 Luna is more popular than Claude Haiku 4.5: 60 to 32 out of 100.

Over time

Weekly values from October 18, 2026 to November 7, 2026

Claude Haiku 4.5GPT-6 Luna

All data side by side

The better value is bold. For the overall index only when the gap is clear.

MetricClaude Haiku 4.5GPT-6 Luna
Intelligence
Overall indexpoints, 100 = reference group average, higher is better53.996.3
RankRank 80 of 92Rank 35 of 92
Price per 1M tokens
Inputwhat you send$1$0.10above 272,000 tokens: $0.20
Outputwhat the model writes$5$0.50above 272,000 tokens: $0.75
Cost per task (own tests)average of 3 original-protocol tasks both models passed (SVG short test not included)$0.023$0.003
Speed
Tokens per second97101
Popularity
Popularitysearch, usage and mentions, 0 to 10032Rank 497 of 78560Rank 30 of 785
Technical
Context windowhow much text the model reads at once200,000 tokens≈ 300 A4 pages1.05 M tokens≈ 1,580 A4 pages
Knowledge cutoffFebruary 2025May 18, 2026
ReleasedOctober 2025Sep 22, 2026
AvailabilityActiveActive
Open weightsnono

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Is there a better choice?

Successor of Haiku 4.5Claude Haiku 5.5

Overall index 103.4, rank 20$0.10 input and $0.50 output per 1M tokens

GPT-6 Luna vs. Claude Haiku 5.5
Cheaper than GPT-6 LunaMiMo V2.6 Flash

Overall index 98.3, rank 31$0.14 input and $0.28 output per 1M tokens

View profile
Best model in the overall indexClaude Opus 5.5

Overall index 126.1, rank 1$4 input and $20 output per 1M tokens

GPT-6 Luna vs. Claude Opus 5.5

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

A: Claude Haiku 4.5B: GPT-6 Luna

MMMU-ProOverall · higher is betterClaude Haiku 4.5: 55.1%GPT-6 Luna: 62.1%Artificial AnalysisAs of 11/07/2026
Public Benefits Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 4.5: 54.3%GPT-6 Luna: 57.6%Vals AIAs of 10/12/2026

More comparisons

Compare Claude Haiku 4.5 and GPT-6 Luna with the models people compare them with most often.

Compare another matchup

The most popular comparisons

  1. 1GPT-6 Luna vs. GPT-5.6 Terra
  2. 2Claude Haiku 5.5 vs. GPT-6 Luna
  3. 3GPT-6 Luna vs. Gemini 3.8 Flash
  4. 4GPT-6 Luna vs. DeepSeek-V4.1-Flash
  5. 5GPT-6 Luna vs. GPT-5.4 mini
  6. 6GPT-6 Astra vs. GPT-6 Luna
  7. 7GPT-6 Luna vs. GLM-5.3-Flash
  8. 8GPT-6.1 Sol vs. GPT-6 Luna
  9. 9GPT-6 Luna vs. DeepSeek-V4-Pro
Show all 60 comparisons
  1. 10Claude Sonnet 5 vs. GPT-6 Luna
  2. 11GPT-6 Luna vs. Gemini 3.5 Flash-Lite
  3. 12Claude Sonnet 4.6 vs. GPT-6 Luna
  4. 13GPT-6 Luna vs. GPT-5.4
  5. 14GPT-6 Luna vs. Gemini 3.1 Pro Preview
  6. 15Claude Sonnet 5.5 vs. GPT-6 Luna
  7. 16GPT-6 Luna vs. DeepSeek V4.1 Flash 1017
  8. 17Claude Opus 4.8 vs. GPT-6 Luna
  9. 18GPT-6 Luna vs. GPT-5.6 Sol
  10. 19GPT-6 Luna vs. Grok 4.7
  11. 20GPT-6 Luna vs. Gemini 3.6 Flash
  12. 21GPT-6 Sol vs. GPT-6 Luna
  13. 22Claude Opus 4.6 vs. GPT-6 Luna
  14. 23Claude Sonnet 4.5 vs. GPT-6 Luna
  15. 24GPT-6 Luna vs. Muse Spark 1.3
  16. 25GPT-6 Luna vs. DeepSeek-V4-Flash
  17. 26Claude Opus 5.5 vs. GPT-6 Luna
  18. 27Claude Haiku 4.5 vs. DeepSeek-V4.1-Flash
  19. 28GPT-6 Luna vs. Qwen 3.8 27B
  20. 29GPT-6 Luna vs. Qwen 3.8 Max 0902
  21. 30Claude Haiku 4.5 vs. GLM-5.3-Flash
  22. 31GPT-6 Luna vs. GLM-5.2
  23. 32GPT-6 Luna vs. GPT-5.5
  24. 33GPT-6 Luna vs. Gemini 3.7 Flash
  25. 34Claude Opus 5.5 vs. Claude Haiku 4.5
  26. 35Claude Fable 5.1 vs. GPT-6 Luna
  27. 36GPT-6 Luna vs. GLM-5.3
  28. 37GPT-6 Luna vs. Grok 4.6
  29. 38Claude Opus 4.5 vs. GPT-6 Luna
  30. 39Claude Sonnet 5 vs. Claude Haiku 4.5
  31. 40Claude Sonnet 5.5 vs. Claude Haiku 4.5
  32. 41GPT-6 Luna vs. MiMo-V2.5
  33. 42Claude Sonnet 4.5 vs. Claude Haiku 4.5
  34. 43Claude Fable 5 vs. GPT-6 Luna
  35. 44GPT-6 Luna vs. Mistral Large 4
  36. 45Claude Haiku 4.5 vs. Gemini 3.8 Flash
  37. 46GPT-6 Luna vs. Gemini 3.5 Flash
  38. 47GPT-6.1 Terra vs. GPT-6 Luna
  39. 48Claude Haiku 4.5 vs. DeepSeek V4.1 Flash 1017
  40. 49Claude Haiku 4.5 vs. GPT-6 Sol
  41. 50GPT-6 Luna vs. Mistral Medium 3.5
  42. 51Claude Haiku 4.5 vs. Qwen 3.8 Max 0902
  43. 52Claude Haiku 4.5 vs. Grok 4.7
  44. 53Claude Haiku 4.5 vs. GPT-6.1 Sol
  45. 54GPT-6 Luna vs. Grok 4.5
  46. 55Claude Opus 4.7 vs. GPT-6 Luna
  47. 56Claude Sonnet 4.6 vs. Claude Haiku 4.5
  48. 57Claude Haiku 4.5 vs. Gemini 3.5 Flash-Lite
  49. 58Claude Haiku 4.5 vs. GPT-5.6 Luna
  50. 59GPT-6 Luna vs. Gemini 4 Argon
  51. 60Claude Haiku 4.5 vs. GPT-5.5