Compare / DeepSeek-V4.1-Flash vs GPT-6.1 Sol
DeepSeek-V4.1-Flash vs GPT-6.1 Sol
Which is cheaper, which is more capable, and which does better at each kind of work, from 48 results on 3 sources that measured both models.
Results as of 8 October 2026 (catalogue release 2026-10-08-4199ce0620fe).
DeepSeek-V4.1-Flash or GPT-6.1 Sol? The short answer
Pick GPT-6.1 Sol if quality matters most: it scores higher (Spring Prompt overall 81 against 56). Pick DeepSeek-V4.1-Flash if cost matters more: it costs 28% less per product listing on CatalogBench. DeepSeek-V4.1-Flash is also faster.
- Spring Prompt overall: DeepSeek-V4.1-Flash 56, GPT-6.1 Sol 81 (out of 100; how the score works).
- DeepSeek-V4.1-Flash is cheaper to run: $0.006 against $0.008 per product listing on CatalogBench (28% less).
- GPT-6.1 Sol scores higher on the Artificial Analysis Intelligence Index: 51.8 against 39.5.
- DeepSeek-V4.1-Flash writes faster: 217 tokens a second against 55.
- GPT-6.1 Sol is newer: released 29 Sep 2026, against 10 Sep 2026 for DeepSeek-V4.1-Flash.
- On our own benchmarks, on the results both models have: GPT-6.1 Sol does better for product listings.
- On third-party benchmarks, on the results both models have: GPT-6.1 Sol does better for agents and tool use and reasoning and knowledge.
At a glance
| DeepSeek-V4.1-Flash | GPT-6.1 Sol | |
|---|---|---|
| Price per million tokens | $0.30 in · $1.20 out | $2.00 in · $10.00 out |
| Blended (3 in : 1 out) | $0.52 | $4.00 |
| Cheapest host, blended | $0.11 (Decart, FP4) | $4.00 (Azure) |
| Cost per product listing (CatalogBench) | $0.006 | $0.008 |
| Cached input, per million | $0.006 cached input | $0.10 cached input |
| Intelligence Index | 39.5 | 51.8 |
| Spring Prompt overall | 56 | 81 |
| Output speed, tokens a second | 217 | 55 |
| Context window | 1,048,576 tokens | 1,050,000 tokens |
| Released | 10 Sep 2026 | 29 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 models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | DeepSeek-V4.1-Flash | GPT-6.1 Sol |
|---|---|---|
| Product listingsTurning a sparse product feed and photos into listings that can go live | 7 of 20 | 2 of 20 |
| Decks from an analysisTurning a finished analysis into a deck you could present as it is | not measured | 3 of 19 |
| User surveysPlanning a user survey and reading its results without being misled | not measured | 1 of 8 |
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 21 of 164 | 3 of 164 |
| Professional workReal tasks from banking, consulting and law, business documents and freelance projects | not measured | 9 of 51 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 35 of 198 | 5 of 198 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 28 of 188 | 15 of 188 |
| Sticking to the factsSummarising without inventing things, and factual answers | 23 of 152 | 18 of 152 |
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. 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-6.1 Sol |
|---|---|---|
| CatalogBench measured by Spring Prompt · 3 results | ||
| Cost per productUS dollars, lower is better | $0.0061 | $0.0084 |
| Reliably publish-ready% of products, higher is better | 41.1% | 75.0% |
| Reliably publish-ready · sales brief% of products, higher is better | 23.2% | 67.9% |
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better | 1,474max reasoning | 1,483max reasoning |
| Overall · Text factualityArena rating, higher is better | 1,467max reasoning | 1,463max reasoning |
| Business, management and finance · TextArena rating, higher is better | 1,479max reasoning | 1,475max reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better | 39.5max reasoning | 51.8max reasoning |
| Humanity's Last Exam% of questions, higher is better | 39.2%max reasoning | 52.9%max reasoning |
| Terminal-Bench 4.0% of tasks, higher is better | 26.8%max reasoning | 56.1%max reasoning |
Show all 48 results (39 more)
| Measure | DeepSeek-V4.1-Flash | GPT-6.1 Sol |
|---|---|---|
| CatalogBench measured by Spring Prompt · 27 results | ||
| Channel compliance% of products, higher is better | 99.4% | 100.0% |
| Channel rules broken% of products, lower is better | 3.0% | 0.0% |
| Channel rules broken · sales brief% of products, lower is better | 1.8% | 0.0% |
| Claims to check% of products, lower is better | 0.0% | 0.0% |
| Claims to check · sales brief% of products, lower is better | 0.0% | 0.0% |
| Conflicts caught% of conflicts, higher is better | 100.0% | 100.0% |
| Content quality% of checks, higher is better | 96.7% | 98.6% |
| Content quality · sales brief% of checks, higher is better | 96.2% | 98.8% |
| Decision accuracy% of decisions, higher is better | 96.9% | 98.7% |
| Failed outputs% of products, lower is better | 0.0% | 0.0% |
| Failed outputs · sales brief% of products, lower is better | 0.6% | 0.0% |
| Field accuracy% of missing fields, higher is better | 94.4% | 94.4% |
| Invented values% of filled values, lower is better | 3.1% | 2.2% |
| Missing UK information% of products, lower is better | 0.0% | 0.0% |
| Missing UK information · sales brief% of products, lower is better | 0.0% | 0.0% |
| Not findable% of products, lower is better | 3.6% | 4.8% |
| Not findable · sales brief% of products, lower is better | 3.6% | 5.4% |
| Publish-ready listings% of products, higher is better | 63.7% | 78.0% |
| Publish-ready listings · sales brief% of products, higher is better | 47.0% | 72.0% |
| Unsupported claims% of products, lower is better | 13.1% | 0.0% |
| Unsupported claimsclaims per product, lower is better | 0.54 | 0.00 |
| Unsupported claims · sales brief% of products, lower is better | 39.9% | 3.6% |
| Unsupported claims · sales briefclaims per product, lower is better | 1.25 | 0.07 |
| Wrong attributes% of products, lower is better | 20.2% | 16.7% |
| Wrong attributes · sales brief% of products, lower is better | 20.2% | 19.1% |
| Wrong category or variant% of products, lower is better | 3.0% | 1.8% |
| Wrong category or variant · sales brief% of products, lower is better | 2.4% | 1.8% |
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 8 results | ||
| Confirmed task success · AgentIPS effect estimate, higher is better | 0.08max reasoning, arena agent | 0.15max reasoning, arena agent |
| Creative writing · TextArena rating, higher is better | 1,440max reasoning | 1,460max reasoning |
| Expert prompts · TextArena rating, higher is better | 1,517max reasoning | 1,543max reasoning |
| Instruction following · TextArena rating, higher is better | 1,479max reasoning | 1,490max reasoning |
| Praise over complaint · AgentIPS effect estimate, higher is better | 0.02max reasoning, arena agent | 0.26max reasoning, arena agent |
| Steerability · AgentIPS effect estimate, higher is better | 0.01max reasoning, arena agent | 0.11max reasoning, arena agent |
| Tool grounding · AgentIPS effect estimate, higher is better | 0.00max reasoning, arena agent | 0.00max reasoning, arena agent |
| Writing, literature and language · TextArena rating, higher is better | 1,454max reasoning | 1,472max reasoning |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| Long-context reasoning (AA-LCR)% of questions, higher is better | 84.0%max reasoning | 84.0%low reasoning |
| Output speedtokens per second, higher is better | 217max reasoning | 55.2max reasoning |
| SciCode% of problems, higher is better | 51.9%max reasoning | 55.8%high reasoning |
| Time to first answer tokenseconds, lower is better | 0.85no reasoning | 1.69low reasoning |
Quick answers
Is DeepSeek-V4.1-Flash better than GPT-6.1 Sol?
Pick GPT-6.1 Sol if quality matters most: it scores higher (Spring Prompt overall 81 against 56). Pick DeepSeek-V4.1-Flash if cost matters more: it costs 28% less per product listing on CatalogBench. DeepSeek-V4.1-Flash is also faster.
Which is cheaper, DeepSeek-V4.1-Flash or GPT-6.1 Sol?
DeepSeek-V4.1-Flash is cheaper to run: $0.006 against $0.008 per product listing on CatalogBench (28% less).
Which is faster, DeepSeek-V4.1-Flash or GPT-6.1 Sol?
DeepSeek-V4.1-Flash writes about 217 tokens a second on its usual API, against 55 for GPT-6.1 Sol (Artificial Analysis).
Run DeepSeek-V4.1-Flash and GPT-6.1 Sol on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.