DeepSeek V4.1 Flash 1017 vs GPT-4.1 Mini
DeepSeek V4.1 Flash 1017 leads GPT-4.1 Mini on the Artificial Analysis Intelligence Index, 39.5 to 10.2, and DeepSeek V4.1 Flash 1017 costs 2.7x less per output token ($0.60 vs $1.60 per million). Updated October 22, 2026; 15 benchmarks have a result for both.
DeepSeek V4.1 Flash 1017 or GPT-4.1 Mini: which to pick
Only DeepSeek V4.1 Flash 1017 has a coding score, 70.3 on the Vibe Coding Index; GPT-4.1 Mini has none, so the two cannot be ranked on coding.
Compare them on price, context and the boards below.
- Shared results
- 15
- DeepSeek V4.1 Flash 1017 only
- 24
- GPT-4.1 Mini only
- 71
- Like-for-like categories
- 6 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only DeepSeek V4.1 Flash 1017 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 leads, 39.5 against 10.2.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only GPT-4.1 Mini has a GPQA Diamond result, 67.9%.
Directional only
Math
AIME
No call
Only GPT-4.1 Mini has a AIME result, 49.4%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-4.1 Mini has a MMLU Pro result, 77.2%.
Directional only
Web design
Design Arena: websites
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 leads, 1311 against 997.
Same board, both measured
General
Vals Index
No call
Only DeepSeek V4.1 Flash 1017 has a Vals Index result, 61.3%.
Directional only
Long documents
Listed context window
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 $0.0004, GPT-4.1 Mini $0.0012 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-4.1 Mini has the number, $1.818.
Directional only
At a glance
- Coding index
- DeepSeek V4.1 Flash 1017 70.3 from 4 benchmarks, GPT-4.1 Mini not benchmarked.
- Widest category
- Math, 59.6 points apart on average over 2 shared benchmarks.
- Widest single gap
- Design Arena: 3D: DeepSeek V4.1 Flash 1017 1358 against GPT-4.1 Mini 836, 65.3 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4.1 Flash 1017 $0.60 against GPT-4.1 Mini $1.60 per million output tokens, 2.7x apart.
- Context window
- DeepSeek V4.1 Flash 1017 takes 1.05M tokens, GPT-4.1 Mini 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | DeepSeek V4.1 Flash 1017 | Bars | GPT-4.1 Mini | Ties |
|---|---|---|---|---|
| Intelligence | 1 | 0 | ||
| Reasoning | 4 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 1 | 0 | ||
| Web design | 6 | 0 | ||
| General | 1 | 0 | ||
| All shared boards | 15 | 0 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index18 boards, none shared
| Benchmark | DeepSeek V4.1 Flash 1017 | GPT-4.1 Mini | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 32.4% | Only GPT-4.1 Mini measured |
| SWE-bench Verified | Not measured | 23.9% | Only GPT-4.1 Mini measured |
| LiveBench coding | 96.0% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LMArena WebDev | 1664 | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| AA Coding Index | Not measured | 20.2 | Only GPT-4.1 Mini measured |
| LiveCodeBench (Vals AI) | Not measured | 58.2% | Only GPT-4.1 Mini measured |
| Terminal-Bench 4 (Vals AI) | 31.8% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Vibe Code Bench (Vals AI) | 87.7% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Code migration (Vals AI) | 44.2% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 48.3% | Only GPT-4.1 Mini measured |
| SciCode | 55.9% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 7.6% | Only GPT-4.1 Mini measured |
| WeirdML | Not measured | 37.6% | Only GPT-4.1 Mini measured |
| ALE-Bench | 1622.0 | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LMArena Text: coding | Not measured | 1367 | Only GPT-4.1 Mini measured |
| LMArena Text: software and IT | Not measured | 1360 | Only GPT-4.1 Mini measured |
| LMArena WebDev: React | 1667 | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LMArena WebDev: HTML | 1687 | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4.1 Flash 1017 | GPT-4.1 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 39.5 | 10.2 | DeepSeek V4.1 Flash 1017 |
| Epoch Capabilities Index | Not measured | 134.9 | Only GPT-4.1 Mini measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | DeepSeek V4.1 Flash 1017 | GPT-4.1 Mini | Leader |
|---|---|---|---|
| Design Arena: spreadsheets | 1245 | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench research | 79.5% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench browser | 76.0% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench long agentic | 50.9% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Finance Agent (Vals AI) | 57.0% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Tax Agent Bench (Vals AI) | 44.4% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Legal Research Bench (Vals AI) | 45.2% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 14.2% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Excel Modeling Benchmark (Vals AI) | 61.8% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| τ²-Bench Telecom | Not measured | 52.9% | Only GPT-4.1 Mini measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 50.4% | Only GPT-4.1 Mini measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | DeepSeek V4.1 Flash 1017 | GPT-4.1 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 67.9% | Only GPT-4.1 Mini measured |
| LiveBench reasoning | 89.1% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| MMMU Pro (Vals AI) | Not measured | 70.5% | Only GPT-4.1 Mini measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 66.4% | Only GPT-4.1 Mini measured |
| Humanity's Last Exam (Artificial Analysis run) | 43.3% | 5.0% | DeepSeek V4.1 Flash 1017 |
| GPQA Diamond (Epoch AI run) | 93.2% | 65.8% | DeepSeek V4.1 Flash 1017 |
| ARC-AGI | Not measured | 3.5% | Only GPT-4.1 Mini measured |
| ARC-AGI-2 | Not measured | 0.0% | Only GPT-4.1 Mini measured |
| Chess puzzles | 46.0% | 1.0% | DeepSeek V4.1 Flash 1017 |
| Mystery game puzzles | 49.0% | 7.0% | DeepSeek V4.1 Flash 1017 |
| LMArena Text: hard prompts | Not measured | 1349 | Only GPT-4.1 Mini measured |
| LMArena Text: expert | Not measured | 1338 | Only GPT-4.1 Mini measured |
| LMArena Text: hard prompts in English | Not measured | 1362 | Only GPT-4.1 Mini measured |
| LMArena Vision: diagrams | Not measured | 1182 | Only GPT-4.1 Mini measured |
| LMArena Vision: homework | Not measured | 1214 | Only GPT-4.1 Mini measured |
| Kagi LLM Benchmark | Not measured | 48.6% | Only GPT-4.1 Mini measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4.1 Flash 1017 | GPT-4.1 Mini | Leader |
|---|---|---|---|
| AIME | Not measured | 49.4% | Only GPT-4.1 Mini measured |
| MATH 500 (Vals AI) | Not measured | 88.0% | Only GPT-4.1 Mini measured |
| MGSM (Vals AI) | Not measured | 87.8% | Only GPT-4.1 Mini measured |
| AA Math Index | Not measured | 46.3 | Only GPT-4.1 Mini measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 46.3% | Only GPT-4.1 Mini measured |
| OTIS Mock AIME | 99.4% | 44.7% | DeepSeek V4.1 Flash 1017 |
| FrontierMath, tiers 1 to 3 | 71.2% | 6.7% | DeepSeek V4.1 Flash 1017 |
| FrontierMath, tier 4 | 46.3% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| MATH level 5 | Not measured | 87.3% | Only GPT-4.1 Mini measured |
| LMArena Text: math | Not measured | 1343 | Only GPT-4.1 Mini measured |
| LMArena Text: mathematical work | Not measured | 1347 | Only GPT-4.1 Mini measured |
| Neither model has a result on the other 2 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4.1 Flash 1017 | GPT-4.1 Mini | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 77.2% | Only GPT-4.1 Mini measured |
| LegalBench (Vals AI) | Not measured | 78.0% | Only GPT-4.1 Mini measured |
| CorpFin (Vals AI) | Not measured | 57.9% | Only GPT-4.1 Mini measured |
| TaxEval (Vals AI) | Not measured | 71.9% | Only GPT-4.1 Mini measured |
| MortgageTax (Vals AI) | Not measured | 65.5% | Only GPT-4.1 Mini measured |
| MedQA (Vals AI) | Not measured | 84.6% | Only GPT-4.1 Mini measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 78.1% | Only GPT-4.1 Mini measured |
| SimpleQA Verified | 42.5% | 12.7% | DeepSeek V4.1 Flash 1017 |
| LMArena Text: science | Not measured | 1328 | Only GPT-4.1 Mini measured |
| LMArena Text: medicine and healthcare | Not measured | 1324 | Only GPT-4.1 Mini measured |
| LMArena Text: legal and government | Not measured | 1343 | Only GPT-4.1 Mini measured |
| LMArena Text: business and finance | Not measured | 1322 | Only GPT-4.1 Mini measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | DeepSeek V4.1 Flash 1017 | GPT-4.1 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1311 | 997 | DeepSeek V4.1 Flash 1017 |
| Design Arena: UI components | 1303 | 958 | DeepSeek V4.1 Flash 1017 |
| Design Arena: game dev | 1357 | 1070 | DeepSeek V4.1 Flash 1017 |
| Design Arena: data viz | 1330 | 1034 | DeepSeek V4.1 Flash 1017 |
| Design Arena: 3D | 1358 | 836 | DeepSeek V4.1 Flash 1017 |
| Design Arena: all code categories | 1332 | 993 | DeepSeek V4.1 Flash 1017 |
| Design Arena: ASCII art | 1242 | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench design | 83.4% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4.1 Flash 1017 | GPT-4.1 Mini | Leader |
|---|---|---|---|
| Vals Index | 61.3% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench data analysis | 79.5% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| IFBench | Not measured | 38.3% | Only GPT-4.1 Mini measured |
| Long context reasoning (AA-LCR) | 82.7% | 44.0% | DeepSeek V4.1 Flash 1017 |
| DTBench | Not measured | 68.8% | Only GPT-4.1 Mini measured |
| LMCA | Not measured | 21.1% | Only GPT-4.1 Mini measured |
| Fiction.LiveBench | Not measured | 44.4% | Only GPT-4.1 Mini measured |
| LMArena Text | Not measured | 1341 | Only GPT-4.1 Mini measured |
| LMArena Text: instruction following | Not measured | 1333 | Only GPT-4.1 Mini measured |
| LMArena Text: creative writing | Not measured | 1299 | Only GPT-4.1 Mini measured |
| LMArena Vision | Not measured | 1181 | Only GPT-4.1 Mini measured |
| LMArena Text: English | Not measured | 1356 | Only GPT-4.1 Mini measured |
| LMArena Text: non-English | Not measured | 1318 | Only GPT-4.1 Mini measured |
| LMArena Text: Chinese | Not measured | 1329 | Only GPT-4.1 Mini measured |
| LMArena Text: German | Not measured | 1350 | Only GPT-4.1 Mini measured |
| LMArena Text: Japanese | Not measured | 1290 | Only GPT-4.1 Mini measured |
| LMArena Text: Korean | Not measured | 1298 | Only GPT-4.1 Mini measured |
| LMArena Text: French | Not measured | 1358 | Only GPT-4.1 Mini measured |
| LMArena Text: Spanish | Not measured | 1319 | Only GPT-4.1 Mini measured |
| LMArena Text: Russian | Not measured | 1324 | Only GPT-4.1 Mini measured |
| LMArena Text: Polish | Not measured | 1326 | Only GPT-4.1 Mini measured |
| LMArena Text: multi-turn | Not measured | 1354 | Only GPT-4.1 Mini measured |
| LMArena Text: longer queries | Not measured | 1344 | Only GPT-4.1 Mini measured |
| LMArena Text: writing and language | Not measured | 1319 | Only GPT-4.1 Mini measured |
| LMArena Text: entertainment and media | Not measured | 1300 | Only GPT-4.1 Mini measured |
| LMArena Vision: English | Not measured | 1191 | Only GPT-4.1 Mini measured |
| LMArena Vision: Chinese | Not measured | 1186 | Only GPT-4.1 Mini measured |
| LMArena Vision: reading text | Not measured | 1188 | Only GPT-4.1 Mini measured |
| LMArena Vision: humor | Not measured | 1182 | Only GPT-4.1 Mini measured |
| LMArena Vision: captioning | Not measured | 1174 | Only GPT-4.1 Mini measured |
| LMArena Vision: recognizing things | Not measured | 1187 | Only GPT-4.1 Mini measured |
| LMArena Vision: creative writing | Not measured | 1182 | Only GPT-4.1 Mini measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4.1 Flash 1017 | GPT-4.1 Mini | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
DeepSeek V4.1 Flash 1017 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4.1 Flash 1017 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4.1 Flash 1017 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | DeepSeek V4.1 Flash 1017 | OpenAI GPT-4.1 Mini |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | October 17, 2026 | April 14, 2025 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.15 | $0.40 |
| Output $/Mtok | $0.60 | $1.60 |
| Coding index | 70.3 | Not benchmarked |
| Independent measurements behind it | 4 | 0 |
| Cost per solved task | Not computable | $1.818 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4.1 Flash 1017 better than GPT-4.1 Mini for coding?
Only DeepSeek V4.1 Flash 1017 has a coding score, 70.3 on the Vibe Coding Index; GPT-4.1 Mini has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.
Which is cheaper, DeepSeek V4.1 Flash 1017 or GPT-4.1 Mini?
DeepSeek V4.1 Flash 1017 costs $0.15 per million input tokens and $0.60 per million output tokens; GPT-4.1 Mini costs $0.40 and $1.60. Cost per solved task is known for GPT-4.1 Mini only.
Which has the bigger context window, DeepSeek V4.1 Flash 1017 or GPT-4.1 Mini?
DeepSeek V4.1 Flash 1017, with 1.05M tokens against 1.05M.
How many benchmarks is the DeepSeek V4.1 Flash 1017 vs GPT-4.1 Mini comparison based on?
15 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4.1 Flash 1017's coding index rests on 4 independent benchmarks and GPT-4.1 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.