Compare / DeepSeek-V4.1-Flash vs GPT-6 Luna
DeepSeek-V4.1-Flash vs GPT-6 Luna
Which is cheaper, which is more capable, and which does better at each kind of work, from 49 results on 3 sources that measured both models.
Of the 49 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). See also DeepSeek vs OpenAI, every model from both labs.
DeepSeek-V4.1-Flash or GPT-6 Luna? The short answer
Pick DeepSeek-V4.1-Flash if quality matters most: it scores higher (Spring Prompt overall 51 against 39). Pick GPT-6 Luna if cost matters more: it costs 13 times less per product listing on CatalogBench. DeepSeek-V4.1-Flash is also faster.
- Spring Prompt overall: DeepSeek-V4.1-Flash 51, GPT-6 Luna 39 (out of 100; how the score works).
- GPT-6 Luna is cheaper to run: $0.000 against $0.006 per product listing on CatalogBench (13 times less).
- DeepSeek-V4.1-Flash scores higher on the Artificial Analysis Intelligence Index: 39.5 against 38.1.
- DeepSeek-V4.1-Flash writes faster: 369 tokens a second against 127.
- GPT-6 Luna is newer: released 22 Sep 2026, against 10 Sep 2026 for DeepSeek-V4.1-Flash.
- On our own benchmarks, on the results both models have: GPT-6 Luna does better for product listings.
- On third-party benchmarks, on the results both models have: DeepSeek-V4.1-Flash does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
Head to head
Every fact side by side
| DeepSeek-V4.1-Flash | GPT-6 Luna | |
|---|---|---|
| Price per million tokens | $0.30 in · $1.20 out | $0.10 in · $0.50 out |
| Blended (3 in : 1 out) | $0.52 | $0.20 |
| Cheapest host, blended | $0.12 (Morph, FP8) | $0.20 (Amazon Bedrock) |
| Cost per product listing (CatalogBench) | $0.006 | $0.000 |
| Cached input, per million | $0.006 cached input | $0.010 cached input |
| Intelligence Index | 39.5 | 38.1 |
| Spring Prompt overall | 51 | 39 |
| Output speed, tokens a second | 369 | 127 |
| Context window | 1,048,576 tokens | 1,050,000 tokens |
| Released | 10 Sep 2026 | 22 Sep 2026 (newer) |
| Weights | Open | Closed |
| Developer based in | China | the 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.
From our research
- DeepSeek-V4.1-Flash-1017 review: better at analysis, much worse at sticking to the product data 19 Oct 2026
- We Told 11 AI Models What Happened in 2026. Most of Them Thought We Were Making It Up. 12 Oct 2026
- Claude Haiku 5.5 Is Far Better Than Haiku 4.5 at a Tenth of the Price. GPT-6 Luna Still Beats It at Business Work. 8 Oct 2026
- Mistral Large 4 Is Fast, Cheap and Europe's Best Model. On Business Work, It Still Makes Things Up. 7 Oct 2026
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.
| Measure | DeepSeek-V4.1-Flash | GPT-6 Luna |
|---|---|---|
| CatalogBench measured by Spring Prompt · 3 results | ||
| Cost per productUS dollars, lower is better 11 · 2 of 33 measured | $0.0061 | $0.0005 |
| Reliably publish-ready% of products, higher is better 17 · 10 of 32 measured | 41.1% | 55.4% |
| Reliably publish-ready · sales brief% of products, higher is better 11 · 5 of 32 measured | 23.2% | 51.8% |
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 32 · 78 of 387 measured | 1,474max reasoning | 1,443max reasoning |
| Overall · Text factualityArena rating, higher is better 28 · 98 of 163 measured | 1,467max reasoning | 1,430max reasoning |
| Business, management and finance · TextArena rating, higher is better 22 · 71 of 380 measured | 1,479max reasoning | 1,447max reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 32 · 39 of 249 measured | 39.5max reasoning | 38.1max reasoning |
| Humanity's Last Exam% of questions, higher is better 50 · 53 of 250 measured | 39.2%max reasoning | 38.5%max reasoning |
| Terminal-Bench 4.0% of tasks, higher is better 22 · 37 of 120 measured | 26.8%max reasoning | 12.6%max reasoning |
Show all 49 results (40 more)
| Measure | DeepSeek-V4.1-Flash | GPT-6 Luna |
|---|---|---|
| CatalogBench measured by Spring Prompt · 28 results | ||
| Channel compliance% of products, higher is better 25 · 1 of 33 measured | 99.4% | 100.0% |
| Channel rules broken% of products, lower is better 32 · 1 of 33 measured | 3.0% | 0.0% |
| Channel rules broken · sales brief% of products, lower is better 29 · 1 of 33 measured | 1.8% | 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 20 · 18 of 33 measured | 96.7% | 97.0% |
| Content quality · sales brief% of checks, higher is better 23 · 15 of 33 measured | 96.2% | 97.4% |
| Decision accuracy% of decisions, higher is better 15 · 14 of 33 measured | 96.9% | 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 26 · 1 of 33 measured | 0.6% | 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 28 · 16 of 33 measured | 3.1% | 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 12 · 29 of 33 measured | 3.6% | 10.1% |
| Not findable · sales brief% of products, lower is better 16 · 29 of 33 measured | 3.6% | 10.1% |
| Publish-ready listings% of products, higher is better 16 · 14 of 33 measured | 63.7% | 67.9% |
| Publish-ready listings · sales brief% of products, higher is better 12 · 6 of 33 measured | 47.0% | 67.9% |
| Time per productseconds, lower is better 18 · 7 of 33 measured | 17.6 | 8.20 |
| Unsupported claimsclaims per product, lower is better 17 · 10 of 33 measured | 0.54 | 0.31 |
| Unsupported claims% of products, lower is better 13 · 10 of 33 measured | 13.1% | 8.9% |
| Unsupported claims · sales briefclaims per product, lower is better 12 · 6 of 33 measured | 1.25 | 0.35 |
| Unsupported claims · sales brief% of products, lower is better 13 · 6 of 33 measured | 39.9% | 8.3% |
| Wrong attributes% of products, lower is better 26 · 21 of 33 measured | 20.2% | 18.5% |
| Wrong attributes · sales brief% of products, lower is better 23 · 20 of 33 measured | 20.2% | 19.1% |
| Wrong category or variant% of products, lower is better 24 · 6 of 33 measured | 3.0% | 1.8% |
| Wrong category or variant · sales brief% of products, lower is better 18 · 1 of 33 measured | 2.4% | 0.0% |
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 8 results | ||
| Confirmed task success · AgentIPS effect estimate, higher is better 8 · 29 of 48 measured | 0.08max reasoning, arena agent | -0.00max reasoning, arena agent |
| Creative writing · TextArena rating, higher is better 49 · 77 of 385 measured | 1,440max reasoning | 1,413max reasoning |
| Expert prompts · TextArena rating, higher is better 18 · 40 of 338 measured | 1,517max reasoning | 1,498max reasoning |
| Instruction following · TextArena rating, higher is better 18 · 57 of 387 measured | 1,479max reasoning | 1,448max reasoning |
| Praise over complaint · AgentIPS effect estimate, higher is better 23 · 30 of 48 measured | 0.02max reasoning, arena agent | -0.02max reasoning, arena agent |
| Steerability · AgentIPS effect estimate, higher is better 24 · 16 of 48 measured | 0.01max reasoning, arena agent | 0.04max reasoning, arena agent |
| Tool grounding · AgentIPS effect estimate, higher is better 16 · 39 of 48 measured | 0.00max reasoning, arena agent | -0.00max reasoning, arena agent |
| Writing, literature and language · TextArena rating, higher is better 37 · 79 of 386 measured | 1,454max 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%max reasoning | 83.3%max reasoning |
| Output speedtokens per second, higher is better 3 · 37 of 78 measured | 369no reasoning | 127max reasoning |
| SciCode% of problems, higher is better 44 · 31 of 121 measured | 51.9%max reasoning | 54.6%max reasoning |
| Time to first answer tokenseconds, lower is better 13 · 20 of 78 measured | 0.63no reasoning | 0.74no reasoning |
Compare them with other models
Quick answers
Is DeepSeek-V4.1-Flash better than GPT-6 Luna?
Pick DeepSeek-V4.1-Flash if quality matters most: it scores higher (Spring Prompt overall 51 against 39). Pick GPT-6 Luna if cost matters more: it costs 13 times less per product listing on CatalogBench. DeepSeek-V4.1-Flash is also faster.
Which is cheaper, DeepSeek-V4.1-Flash or GPT-6 Luna?
GPT-6 Luna is cheaper to run: $0.000 against $0.006 per product listing on CatalogBench (13 times less).
Which is faster, DeepSeek-V4.1-Flash or GPT-6 Luna?
DeepSeek-V4.1-Flash writes about 369 tokens a second on its usual API, against 127 for GPT-6 Luna (Artificial Analysis).
Which is better for product listings, DeepSeek-V4.1-Flash or GPT-6 Luna?
GPT-6 Luna ranks 7 of 32 models on sale for turning a sparse product feed and photos into listings that can go live, against 15 for DeepSeek-V4.1-Flash.
Which is better for agents and tool use, DeepSeek-V4.1-Flash or GPT-6 Luna?
DeepSeek-V4.1-Flash ranks 31 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 53 for GPT-6 Luna.
Which is better for reasoning and knowledge, DeepSeek-V4.1-Flash or GPT-6 Luna?
DeepSeek-V4.1-Flash ranks 42 of 187 models on sale for hard questions across science, maths and general knowledge, against 48 for GPT-6 Luna.
Which is better for writing, DeepSeek-V4.1-Flash or GPT-6 Luna?
DeepSeek-V4.1-Flash ranks 29 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 61 for GPT-6 Luna.
Which has the bigger context window, DeepSeek-V4.1-Flash or GPT-6 Luna?
GPT-6 Luna: 1,050,000 tokens, against 1,048,576 for DeepSeek-V4.1-Flash.
Run DeepSeek-V4.1-Flash 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.