Compare / DeepSeek-R1 vs DeepSeek-V4.1-Flash

DeepSeek-R1 vs DeepSeek-V4.1-Flash

Which is cheaper, which is more capable, and which does better at each kind of work, from 11 results on 2 sources that measured both models.

DeepSeekDeepSeek-R1 Released 20 Jan 2025 · Not on sale
DeepSeekDeepSeek-V4.1-Flash Released 10 Sep 2026 · $0.30 in · $1.20 out
DeepSeek-R1 wins 0DeepSeek-V4.1-Flash wins 11

Of the 11 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).

DeepSeek-R1 or DeepSeek-V4.1-Flash? The short answer

Pick DeepSeek-V4.1-Flash: it scores higher (Intelligence Index 39.5 against 11.4) at about the same price.

  • DeepSeek-V4.1-Flash scores higher on the Artificial Analysis Intelligence Index: 39.5 against 11.4.
  • DeepSeek-V4.1-Flash is newer: released 10 Sep 2026, against 20 Jan 2025 for DeepSeek-R1.
  • On third-party benchmarks, on the results both models have: DeepSeek-V4.1-Flash does better for agents and tool use, reasoning and knowledge and writing.

Head to head

11.4
Intelligence Index
39.5

Every fact side by side

DeepSeek-R1DeepSeek-V4.1-Flash
Price per million tokensNot on sale$0.30 in · $1.20 out
Blended (3 in : 1 out)–$0.52
Cheapest host, blended–$0.12 (Morph, FP8)
Cached input, per million–$0.006 cached input
Intelligence Index11.439.5
Spring Prompt overall–51
Output speed, tokens a second–369
Context window–1,048,576 tokens
Released20 Jan 202510 Sep 2026 (newer)
WeightsClosedOpen
Developer based inChinaChina

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 not measured 15 of 32
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 129 of 160 31 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 132 of 188 42 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 90 of 170 29 of 169
Sticking to the factsSummarising without inventing things, and factual answers 104 of 140 23 of 139

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.

MeasureDeepSeek-R1DeepSeek-V4.1-Flash
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 141 · 32 of 387 measured 1,398 1,474max reasoning
Business, management and finance · TextArena rating, higher is better 151 · 22 of 380 measured 1,388 1,479max reasoning
Creative writing · TextArena rating, higher is better 125 · 49 of 385 measured 1,374 1,440max reasoning
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 163 · 32 of 249 measured 11.4 39.5max reasoning
Humanity's Last Exam% of questions, higher is better 170 · 50 of 250 measured 8.5% 39.2%max reasoning
Terminal-Bench 4.0% of tasks, higher is better 72 · 22 of 120 measured 0.0% 26.8%max reasoning
Show all 11 results (5 more)
MeasureDeepSeek-R1DeepSeek-V4.1-Flash
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 151 · 18 of 338 measured 1,402 1,517max reasoning
Instruction following · TextArena rating, higher is better 128 · 18 of 387 measured 1,397 1,479max reasoning
Writing, literature and language · TextArena rating, higher is better 130 · 37 of 386 measured 1,382 1,454max reasoning
Artificial Analysis reported by Artificial Analysis · 2 results
Long-context reasoning (AA-LCR)% of questions, higher is better 148 · 7 of 241 measured 57.7% 84.0%max reasoning
SciCode% of problems, higher is better 92 · 44 of 121 measured 38.3% 51.9%max reasoning

Quick answers

Is DeepSeek-R1 better than DeepSeek-V4.1-Flash?

Pick DeepSeek-V4.1-Flash: it scores higher (Intelligence Index 39.5 against 11.4) at about the same price.

Which is better for agents and tool use, DeepSeek-R1 or DeepSeek-V4.1-Flash?

DeepSeek-V4.1-Flash ranks 31 of 160 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 129 for DeepSeek-R1.

Which is better for reasoning and knowledge, DeepSeek-R1 or DeepSeek-V4.1-Flash?

DeepSeek-V4.1-Flash ranks 42 of 188 models on sale for hard questions across science, maths and general knowledge, against 132 for DeepSeek-R1.

Which is better for writing, DeepSeek-R1 or DeepSeek-V4.1-Flash?

DeepSeek-V4.1-Flash ranks 29 of 170 models on sale for what people prefer in blind comparisons, and judged writing quality, against 90 for DeepSeek-R1.

Which is better for sticking to the facts, DeepSeek-R1 or DeepSeek-V4.1-Flash?

DeepSeek-V4.1-Flash ranks 23 of 140 models on sale for summarising without inventing things, and factual answers, against 104 for DeepSeek-R1.

Run DeepSeek-R1 and DeepSeek-V4.1-Flash 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.