Compare / GPT-6.1 Sol vs GPT-6 Luna

GPT-6.1 Sol vs GPT-6 Luna

Which is cheaper, which is more capable, and which does better at each kind of work, from 98 results on 8 sources that measured both models.

OpenAIGPT-6.1 Sol Released 29 Sep 2026 · $2.00 in · $10.00 out
OpenAIGPT-6 Luna Released 22 Sep 2026 · $0.10 in · $0.50 out
GPT-6.1 Sol wins 5628 too close to callGPT-6 Luna wins 14

Of the 98 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).

GPT-6.1 Sol or GPT-6 Luna? The short answer

Pick GPT-6.1 Sol if quality matters most: it scores higher (Spring Prompt overall 80 against 39). Pick GPT-6 Luna if cost matters more: it costs 18 times less per product listing on CatalogBench. GPT-6 Luna is also faster.

  • Spring Prompt overall: GPT-6.1 Sol 80, GPT-6 Luna 39 (out of 100; how the score works).
  • GPT-6 Luna is cheaper to run: $0.000 against $0.008 per product listing on CatalogBench (18 times less).
  • GPT-6.1 Sol scores higher on the Artificial Analysis Intelligence Index: 51.8 against 38.1.
  • GPT-6 Luna writes faster: 127 tokens a second against 53.
  • GPT-6.1 Sol is newer: released 29 Sep 2026, against 22 Sep 2026 for GPT-6 Luna.
  • On our own benchmarks, on the results both models have: GPT-6.1 Sol does better for product listings, user surveys and speed under pressure.
  • On third-party benchmarks, on the results both models have: GPT-6.1 Sol does better for agents and tool use, professional work, reasoning and knowledge, writing and sticking to the facts.

Head to head

80
Spring Prompt overall
39
51.8
Intelligence Index
38.1
$4.00
Price per million tokens, blendedlower is better
$0.20
53
Output speed, tokens a second
127
1,050,000
Context window, tokens
1,050,000

Every fact side by side

GPT-6.1 SolGPT-6 Luna
Price per million tokens$2.00 in · $10.00 out$0.10 in · $0.50 out
Blended (3 in : 1 out)$4.00$0.20
Cheapest host, blended$4.00 (Amazon Bedrock)$0.20 (Amazon Bedrock)
Cost per product listing (CatalogBench)$0.008$0.000
Cached input, per million$0.10 cached input$0.010 cached input
Intelligence Index51.838.1
Spring Prompt overall8039
Output speed, tokens a second53127
Context window1,050,000 tokens1,050,000 tokens
Released29 Sep 2026 (newer)22 Sep 2026
WeightsClosedClosed
Developer based inthe USthe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live 2 of 32 7 of 32
Decks from an analysisTurning a finished analysis into a deck you could present as it is 5 of 32 10 of 32
User surveysPlanning a user survey and reading its results without being misled 3 of 23 12 of 23
Marketing planningPlanning a year of ad spend without overspending not measured 6 of 32
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 6 of 159 53 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 9 of 51 25 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 6 of 187 48 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 16 of 169 61 of 169
Sticking to the factsSummarising without inventing things, and factual answers 18 of 139 89 of 139
Speed under pressureGood decisions against a real clock (fast chess) 3 of 35 24 of 35

Their slides, side by side

The same brief for both: Manchester store investment review for Hearthside Coffee, an invented company. First slide of each deck from DeckBench.

First slide of GPT-6.1 Sol's deck for Hearthside Coffee
GPT-6.1 Sol · deck rating 1,391 · presentable as it is
First slide of GPT-6 Luna's deck for Hearthside Coffee
GPT-6 Luna · deck rating 1,267 · needs work

Every slide, side by side →

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureGPT-6.1 SolGPT-6 Luna
BulletBench measured by Spring Prompt · 3 results
Cost per game · Blitz 3+2US dollars, lower is better 10 · 1 of 20 measured $0.0767 $0.0072
Cost per game · Bullet 60sUS dollars, lower is better 50 · 21 of 59 measured $0.0210 $0.0016no reasoning
Ladder Elo · Bullet 60sladder Elo, higher is better 2 · 49 of 59 measured 928Ultrafast (low reasoning) 249no reasoning
CatalogBench measured by Spring Prompt · 3 results
Cost per productUS dollars, lower is better 16 · 2 of 33 measured $0.0084 $0.0005
Reliably publish-ready% of products, higher is better 1 · 10 of 32 measured 75.0% 55.4%
Reliably publish-ready · sales brief% of products, higher is better 2 · 5 of 32 measured 67.9% 51.8%
DeckBench measured by Spring Prompt · 3 results
Cost per deckUS dollars, lower is better 21 · 3 of 33 measured $0.15 $0.0087
Deck ratingrating, higher is betterThe rating weighs each win by how strong the other deck was; the win rate counts wins against whichever decks a model happened to meet, so the two can disagree. 5 · 10 of 33 measured 1,391 1,267
Accurate decks% of tasks, higher is better 1 · 15 of 33 measured 100.0% 50.0%
SurveyBench measured by Spring Prompt · 3 results
Analysis ratingrating, higher is betterThe rating weighs each win by how strong the other analysis was; the win rate counts wins against whichever analyses a model happened to meet, so the two can disagree. 3 · 12 of 24 measured 1,432 1,093
Cost per taskUS dollars, lower is better 16 · 1 of 24 measured $0.14 $0.0088
Analysis scorepoints of 100, higher is better 2 · 6 of 24 measured 96.6 90.8
APEX-Agents reported by APEX-Agents · 1 result
Tasks passed% of tasks, higher is better 10 · 27 of 37 measured 60.0%max reasoning 44.3%max reasoning
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 18 · 78 of 387 measured 1,483max reasoning 1,443max reasoning
Overall · Text factualityArena rating, higher is better 37 · 98 of 163 measured 1,463max reasoning 1,430max reasoning
Business, management and finance · TextArena rating, higher is better 27 · 71 of 380 measured 1,475max reasoning 1,447max reasoning
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 7 · 39 of 249 measured 51.8max reasoning 38.1max reasoning
Humanity's Last Exam% of questions, higher is better 8 · 53 of 250 measured 52.9%max reasoning 38.5%max reasoning
Terminal-Bench 4.0% of tasks, higher is better 6 · 37 of 120 measured 56.1%max reasoning 12.6%max reasoning
SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result
Correct answers% of questions, higher is better 2 · 40 of 76 measured 73.9%max reasoning 41.4%max reasoning
Show all 98 results (78 more)
MeasureGPT-6.1 SolGPT-6 Luna
BulletBench measured by Spring Prompt · 7 results
Games lost on time · Blitz 3+2% of games, lower is better 1 · 13 of 20 measured 0.0%Ultrafast 50.0%
Games lost on time · Bullet 60s% of games, lower is better 31 · 39 of 59 measured 25.0%Ultrafast (low reasoning) 50.0%no reasoning
Invalid moves · Blitz 3+2% of moves, lower is better 1 · 1 of 20 measured 0.0% 0.0%
Invalid moves · Bullet 60s% of moves, lower is better 1 · 1 of 59 measured 0.0% 0.0%no reasoning
Ladder Elo · Blitz 3+2ladder Elo, higher is better 5 · 11 of 20 measured 927Ultrafast 557
Median move time · Blitz 3+2milliseconds, lower is better 6 · 16 of 20 measured 2.1 sUltrafast 7.0 s
Median move time · Bullet 60smilliseconds, lower is better 37 · 39 of 59 measured 1.4 sUltrafast (low reasoning) 1.5 sno reasoning
CatalogBench measured by Spring Prompt · 28 results
Channel compliance% of products, higher is better 1 · 1 of 33 measured 100.0% 100.0%
Channel rules broken% of products, lower is better 1 · 1 of 33 measured 0.0% 0.0%
Channel rules broken · sales brief% of products, lower is better 1 · 1 of 33 measured 0.0% 0.0%
Claims to check% of products, lower is better 1 · 1 of 31 measured 0.0% 0.0%
Claims to check · sales brief% of products, lower is better 1 · 1 of 31 measured 0.0% 0.0%
Conflicts caught% of conflicts, higher is better 1 · 1 of 33 measured 100.0% 100.0%
Content quality% of checks, higher is better 3 · 18 of 33 measured 98.6% 97.0%
Content quality · sales brief% of checks, higher is better 2 · 15 of 33 measured 98.8% 97.4%
Decision accuracy% of decisions, higher is better 3 · 14 of 33 measured 98.7% 97.0%
Failed outputs% of products, lower is better 1 · 1 of 33 measured 0.0% 0.0%
Failed outputs · sales brief% of products, lower is better 1 · 1 of 33 measured 0.0% 0.0%
Field accuracy% of missing fields, higher is better 8 · 15 of 33 measured 94.4% 93.7%
Invented values% of filled values, lower is better 25 · 16 of 33 measured 2.2% 1.7%
Missing UK information% of products, lower is better 1 · 1 of 33 measured 0.0% 0.0%
Missing UK information · sales brief% of products, lower is better 1 · 1 of 33 measured 0.0% 0.0%
Not findable% of products, lower is better 19 · 29 of 33 measured 4.8% 10.1%
Not findable · sales brief% of products, lower is better 22 · 29 of 33 measured 5.4% 10.1%
Publish-ready listings% of products, higher is better 3 · 14 of 33 measured 78.0% 67.9%
Publish-ready listings · sales brief% of products, higher is better 5 · 6 of 33 measured 72.0% 67.9%
Time per productseconds, lower is better 11 · 7 of 33 measured 10.2 8.20
Unsupported claims% of products, lower is better 1 · 10 of 33 measured 0.0% 8.9%
Unsupported claimsclaims per product, lower is better 1 · 10 of 33 measured 0.00 0.31
Unsupported claims · sales brief% of products, lower is better 5 · 6 of 33 measured 3.6% 8.3%
Unsupported claims · sales briefclaims per product, lower is better 2 · 6 of 33 measured 0.07 0.35
Wrong attributes% of products, lower is better 16 · 21 of 33 measured 16.7% 18.5%
Wrong attributes · sales brief% of products, lower is better 20 · 20 of 33 measured 19.1% 19.1%
Wrong category or variant% of products, lower is better 6 · 6 of 33 measured 1.8% 1.8%
Wrong category or variant · sales brief% of products, lower is better 6 · 1 of 33 measured 1.8% 0.0%
DeckBench measured by Spring Prompt · 14 results
Caveat dropped% of tasks, lower is better 1 · 1 of 33 measured 0.0% 0.0%
Clean layout% of tasks, higher is better 3 · 8 of 33 measured 83.3% 66.7%
Design quality% of the maximum, higher is better 12 · 8 of 33 measured 71.4% 78.1%
Draft figure quoted% of tasks, lower is better 1 · 19 of 33 measured 0.0% 33.3%
Findings missing% of tasks, lower is better 1 · 1 of 33 measured 0.0% 0.0%
Head-to-head win rate% of comparisons, higher is betterThe rating weighs each win by how strong the other deck was; the win rate counts wins against whichever decks a model happened to meet, so the two can disagree. 5 · 10 of 33 measured 81.0% 70.9%
Layout defects% of tasks, lower is better 3 · 8 of 33 measured 16.7% 33.3%
Misleading metric used% of tasks, lower is better 1 · 1 of 33 measured 0.0% 0.0%
Presentable decks% of tasks, higher is better 3 · 15 of 33 measured 50.0% 0.0%
Recommendation late or wrong% of tasks, lower is better 1 · 15 of 33 measured 0.0% 16.7%
Slides needing work% of tasks, lower is better 17 · 3 of 33 measured 50.0% 16.7%
Time per deckseconds, lower is better 22 · 15 of 33 measured 179 101
Unsupported claims% of tasks, lower is better 1 · 1 of 33 measured 0.0% 0.0%
Unsupported numbers% of tasks, lower is better 1 · 1 of 33 measured 0.0% 0.0%
SurveyBench measured by Spring Prompt · 17 results
Head-to-head win rate% of comparisons, higher is betterThe rating weighs each win by how strong the other analysis was; the win rate counts wins against whichever analyses a model happened to meet, so the two can disagree. 2 · 14 of 24 measured 78.2% 48.5%
Leading or double-barrelled questions% of tasks, lower is better 1 · 3 of 24 measured 0.0% 11.1%
Mistaken next steps% of tasks, lower is better 5 · 5 of 24 measured 11.1% 11.1%
Numbers right% of answers, higher is better 1 · 18 of 24 measured 100.0% 98.0%
Objectives unanswerable% of tasks, lower is better 1 · 1 of 24 measured 0.0% 0.0%
Precision ignored% of tasks, lower is better 1 · 1 of 24 measured 0.0% 0.0%
Research scorepoints of 100, higher is better 2 · 6 of 24 measured 97.0 91.7
Sound research% of tasks, higher is better 1 · 4 of 24 measured 66.7% 33.3%
Stakeholder's view presumed% of tasks, lower is better 1 · 10 of 24 measured 0.0% 11.1%
Survey plan scorepoints of 100, higher is better 1 · 7 of 24 measured 97.8 94.0
Survey structure% of tasks, lower is better 3 · 11 of 24 measured 11.1% 22.2%
Time per taskseconds, lower is better 15 · 10 of 24 measured 222 138
Traps handled% of traps, higher is better 5 · 8 of 24 measured 95.7% 94.2%
Traps missed% of tasks, lower is better 6 · 6 of 24 measured 33.3% 33.3%
Unsupported findings% of tasks, lower is better 1 · 5 of 24 measured 0.0% 22.2%
Wrong numbers% of tasks, lower is better 1 · 13 of 24 measured 0.0% 11.1%
Wrong recommendation% of tasks, lower is better 5 · 5 of 24 measured 11.1% 11.1%
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 8 results
Confirmed task success · AgentIPS effect estimate, higher is better 2 · 29 of 48 measured 0.15max reasoning, arena agent -0.00max reasoning, arena agent
Creative writing · TextArena rating, higher is better 21 · 77 of 385 measured 1,460max reasoning 1,413max reasoning
Expert prompts · TextArena rating, higher is better 4 · 40 of 338 measured 1,543max reasoning 1,498max reasoning
Instruction following · TextArena rating, higher is better 10 · 57 of 387 measured 1,490max reasoning 1,448max reasoning
Praise over complaint · AgentIPS effect estimate, higher is better 6 · 30 of 48 measured 0.26max reasoning, arena agent -0.02max reasoning, arena agent
Steerability · AgentIPS effect estimate, higher is better 3 · 16 of 48 measured 0.11max reasoning, arena agent 0.04max reasoning, arena agent
Tool grounding · AgentIPS effect estimate, higher is better 1 · 39 of 48 measured 0.00max reasoning, arena agent -0.00max reasoning, arena agent
Writing, literature and language · TextArena rating, higher is better 17 · 79 of 386 measured 1,472max reasoning 1,421max reasoning
Artificial Analysis reported by Artificial Analysis · 4 results
Long-context reasoning (AA-LCR)% of questions, higher is better 7 · 13 of 241 measured 84.0%low reasoning 83.3%max reasoning
Output speedtokens per second, higher is better 67 · 37 of 78 measured 53.1max reasoning 127max reasoning
SciCode% of problems, higher is better 26 · 31 of 121 measured 55.8%high reasoning 54.6%max reasoning
Time to first answer tokenseconds, lower is better 35 · 20 of 78 measured 1.71low reasoning 0.74no reasoning

Quick answers

Is GPT-6.1 Sol better than GPT-6 Luna?

Pick GPT-6.1 Sol if quality matters most: it scores higher (Spring Prompt overall 80 against 39). Pick GPT-6 Luna if cost matters more: it costs 18 times less per product listing on CatalogBench. GPT-6 Luna is also faster.

Which is cheaper, GPT-6.1 Sol or GPT-6 Luna?

GPT-6 Luna is cheaper to run: $0.000 against $0.008 per product listing on CatalogBench (18 times less).

Which is faster, GPT-6.1 Sol or GPT-6 Luna?

GPT-6 Luna writes about 127 tokens a second on its usual API, against 53 for GPT-6.1 Sol (Artificial Analysis).

Which is better for product listings, GPT-6.1 Sol or GPT-6 Luna?

GPT-6.1 Sol ranks 2 of 32 models on sale for turning a sparse product feed and photos into listings that can go live, against 7 for GPT-6 Luna.

Which is better for decks from an analysis, GPT-6.1 Sol or GPT-6 Luna?

GPT-6.1 Sol ranks 5 of 32 models on sale for turning a finished analysis into a deck you could present as it is, against 10 for GPT-6 Luna.

Which is better for user surveys, GPT-6.1 Sol or GPT-6 Luna?

GPT-6.1 Sol ranks 3 of 23 models on sale for planning a user survey and reading its results without being misled, against 12 for GPT-6 Luna.

Which is better for agents and tool use, GPT-6.1 Sol or GPT-6 Luna?

GPT-6.1 Sol ranks 6 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 53 for GPT-6 Luna.

Run GPT-6.1 Sol and GPT-6 Luna on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.