Skip to content

GPT-6 Luna · Data analysis

GPT-6 Luna for data analysis: our test runs

GPT-6 Luna ran our 5 data analysis prompts in llmwise, through the same pipeline your messages take. Here's every reply as it came, whether it passed, what it cost and what it counts as on Pro, next to the other models.

Based on 5 of our test runs on , through OpenRouter with the app's own prompt and settings. Updated .

Short answer

In our test runs on September 27, 2026, GPT-6 Luna passed 5 of 5 of our data analysis prompts (both hard ones): tied 1st of 15 models. Each reply counted as 1 message on Pro, where it has 60 a day, and cost $0.0002 to run on average.

Prompt by prompt

Each of the 5 data analysis prompts, and how GPT-6 Luna's reply did.

GPT-6 Luna on each data analysis prompt
PromptResultCostTime
The region with the most revenueEverydayPassed: Final answer North — 1,085.00: right.$0.00012.5 s
Average order value in AugustEverydayPassed: Final answer 300.00: right.$0.00012.6 s
Revenue change from July to AugustEverydayPassed: Final answer 67.4% increase: right.$0.00012.5 s
A median, filtered two waysHardPassed: Final answer 6.25 hours: right.$0.00012.5 s
Correlation between ad spend and sign-upsHardPassed: Final answer 0.97: right.$0.00046.7 s

Every data analysis reply from GPT-6 Luna

  1. The region with the most revenue

    An everyday prompt: “The region with the most revenue”, in full.

    Passed: Final answer North — 1,085.00: right.

    West: $90 + $310 + $240 + $225 = $865  
    East: $120 + $135 + $310 + $360 = $925  
    North: $180 + $240 + $620 + $45 = $1,085  
    
    Final answer: North — $1,085.00

    640 tokens in, 135 out (65 of them reasoning) · 2.5 s · $0.0001 · 1 message on Pro · answered by openai/gpt-6-luna via OpenAI ·

  2. Average order value in August

    An everyday prompt: “Average order value in August”, in full.

    Passed: Final answer 300.00: right.

    August revenue: $240 + $310 + $620 + $225 + $360 + $45 = $1,800.  
    There were 6 orders, so the average is $1,800 ÷ 6 = $300.00.
    
    Final answer: $300.00

    647 tokens in, 131 out (67 of them reasoning) · 2.6 s · $0.0001 · 1 message on Pro · answered by openai/gpt-6-luna via OpenAI ·

  3. Revenue change from July to August

    An everyday prompt: “Revenue change from July to August”, in full.

    Passed: Final answer 67.4% increase: right.

    July revenue: $1,075.00. August revenue: $1,800.00.
    
    Percentage change = (($1,800 − $1,075) ÷ $1,075) × 100 = 67.4% increase.
    
    Final answer: 67.4% increase

    652 tokens in, 135 out (69 of them reasoning) · 2.5 s · $0.0001 · 1 message on Pro · answered by openai/gpt-6-luna via OpenAI ·

  4. A median, filtered two ways

    A hard prompt: “A median, filtered two ways”, in full.

    Passed: Final answer 6.25 hours: right.

    Billing high-priority resolution times, sorted: 2, 4, 5.5, 7, 9, 26. With six values, the median is the average of the middle two: (5.5 + 7) / 2 = 6.25 hours.
    
    Final answer: 6.25 hours

    512 tokens in, 128 out (53 of them reasoning) · 2.5 s · $0.0001 · 1 message on Pro · answered by openai/gpt-6-luna via OpenAI ·

  5. Correlation between ad spend and sign-ups

    A hard prompt: “Correlation between ad spend and sign-ups”, in full.

    Passed: Final answer 0.97: right.

    Using \(r=\frac{\sum (x-\bar{x})(y-\bar{y})}{\sqrt{\sum(x-\bar{x})^2\sum(y-\bar{y})^2}}\), the centered sums are \(23{,}912.5\), \(624{,}687.5\), and \(971.5\). Thus \(r \approx 0.9707\).
    
    Final answer: 0.97

    451 tokens in, 651 out (552 of them reasoning) · 6.7 s · $0.0004 · 1 message on Pro · answered by openai/gpt-6-luna via OpenAI ·

How it compares on data analysis

GPT-6 Luna beside the job's picks among every model. 11 models share the hard-problems pick, GPT-6 Luna among them.

GPT-6 Luna beside other models on data analysis
ModelPassedOn ProCost per reply
DeepSeek V4 ProOur pick: hard problems (shared), best value5 of 5250 a month on Pro$0.0016
GPT-6 LunaOur pick: hard problems (shared), everyday5 of 560 a day on Pro$0.0002
On Pro: Pro's count on each model. Cost: what OpenRouter charged us per reply, on average.

Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.

GPT-6 Luna next to each model on data analysis

GPT-6 Luna against each model on the same 5 data analysis prompts. One run each, through OpenRouter: a wait depends on the provider and the load that day, so a lead under 10% counts as close.

  • Against Claude Fable 5.1: GPT-6 Luna answered 2.0× sooner (2.5 s to 4.9 s), cost 160.7× less, and passed 5 of 5 to its 5.

  • Against Claude Opus 5.5: GPT-6 Luna answered 1.8× sooner (2.5 s to 4.6 s), cost 74.3× less, and passed 5 of 5 to its 5.

  • Against Claude Sonnet 5: GPT-6 Luna answered 2.1× sooner (2.5 s to 5.3 s), cost 39.1× less, and passed 5 of 5 to its 4. Only GPT-6 Luna passed Correlation between ad spend and sign-ups.

  • Against Claude Haiku 4.5: GPT-6 Luna answered within 10% of its time (2.5 s to 2.7 s), cost 14.2× less, and passed 5 of 5 to its 3. Only GPT-6 Luna passed Average order value in August; Correlation between ad spend and sign-ups.

  • Against GPT-6 Astra: GPT-6 Luna answered 1.3× sooner (2.5 s to 3.3 s), cost 87.7× less, and passed 5 of 5 to its 5.

  • Against GPT-6 Sol: GPT-6 Luna answered 1.1× sooner (2.5 s to 2.8 s), cost 19.2× less, and passed 5 of 5 to its 5.

  • Against Gemini 3.1 Pro (preview): GPT-6 Luna answered 3.5× sooner (2.5 s to 8.6 s), cost 87.9× less, and passed 5 of 5 to its 5.

  • Against Gemini 3.8 Flash: GPT-6 Luna answered 2.2× sooner (2.5 s to 5.4 s), cost 15.7× less, and passed 5 of 5 to its 4. Only GPT-6 Luna passed Correlation between ad spend and sign-ups.

  • Against DeepSeek V4.1 Flash: GPT-6 Luna answered 1.2× sooner (2.5 s to 3.0 s), cost 2.9× less, and passed 5 of 5 to its 5.

  • Against DeepSeek V4 Pro: GPT-6 Luna answered within 10% of its time (2.5 s to 2.5 s), cost 9.2× less, and passed 5 of 5 to its 5.

  • Against Grok 4.7: GPT-6 Luna answered 3.8× sooner (2.5 s to 9.4 s), cost 48.0× less, and passed 5 of 5 to its 5.

  • Against Kimi K3: GPT-6 Luna answered 1.4× sooner (2.5 s to 3.5 s), cost 38.5× less, and passed 5 of 5 to its 5.

  • Against GLM 5.3: GPT-6 Luna answered 1.3× later (2.5 s to 1.9 s), cost 10.9× less, and passed 5 of 5 to its 5.

  • Against GLM 5.3 Flash: GPT-6 Luna answered 3.9× sooner (2.5 s to 9.8 s), cost 2.2× less, and passed 5 of 5 to its 4. Only GPT-6 Luna passed Correlation between ad spend and sign-ups.

How these runs were done

Final answer. Automatic. The reply's last “Final answer:” line must hold the right value.

How the runs were done, and every data analysis prompt.

GPT-6 Luna, and data analysis, elsewhere

Questions

Is GPT-6 Luna good for data analysis?

In our test runs it passed 5 of 5 data analysis prompts, tied 1st of the 15 models in llmwise. Every reply is on this page, so you can judge them yourself.

How many of my messages does a data analysis reply from GPT-6 Luna use?

1 message each on Pro, where it has 60 a day on Pro. The price of a message is fixed and shown before you send it, however long the reply.

How were these runs done?

The same way for every model: each prompt sent through llmwise's own pipeline, each reply checked the same way. The methods page has every prompt and how each is scored.

Claude, GPT, Gemini, DeepSeek, Grok, Kimi, and GLM, in one chat.

See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.