DeepSeek V4.1 Flash vs Gemini 3.1 Pro Preview
DeepSeek V4.1 Flash leads Gemini 3.1 Pro Preview on coding, 62.5 to 32.3 on the Vibe Coding Index, and DeepSeek V4.1 Flash costs 15.4x less per output token ($0.78 vs $12.00 per million). Updated October 21, 2026; 88 benchmarks have a result for both.
vs boards won of 88 shared, 1 tied
DeepSeek V4.1 Flash or Gemini 3.1 Pro Preview: which to pick
Pick DeepSeek V4.1 Flash for coding: it scores 62.5 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview.
Pick Gemini 3.1 Pro Preview for work measured by IOI (Vals AI) or SciCode, where it leads.
Model ADeepSeek V4.1 FlashDeepSeek62.5/1005 independent benchmarksNo cost per solved taskModel BGemini 3.1 Pro PreviewGoogle32.3/1004 independent benchmarks$0.99 per solved task
- Shared results
- 88
- DeepSeek V4.1 Flash only
- 13
- Gemini 3.1 Pro Preview only
- 45
- Like-for-like categories
- 8 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
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash scores 62.5 against 32.3.
5 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 29.7 against 24.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemini 3.1 Pro Preview has a AA Agentic Index result, 8.2.
Directional only
Reasoning
GPQA Diamond
No call
Only Gemini 3.1 Pro Preview has a GPQA Diamond result, 95.5%.
Directional only
Math
AIME
No call
Only Gemini 3.1 Pro Preview has a AIME result, 98.1%.
Directional only
Knowledge
MMLU Pro
No call
Only Gemini 3.1 Pro Preview has a MMLU Pro result, 91.0%.
Directional only
Web design
Design Arena: websites
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash leads, 1309 against 1234.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash $0.0006, Gemini 3.1 Pro Preview $0.0080 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Gemini 3.1 Pro Preview has the number, $0.99.
Directional only
At a glance
- Coding index
- DeepSeek V4.1 Flash 62.5 from 5 benchmarks, Gemini 3.1 Pro Preview 32.3 from 4 benchmarks.
- Widest category
- Coding, 15.5 points apart on average over 15 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V4.1 Flash 84.7% against Gemini 3.1 Pro Preview 32.0%, 52.7 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4.1 Flash $0.78 against Gemini 3.1 Pro Preview $12.00 per million output tokens, 15.4x apart.
- Context window
- Both take 1.05M tokens.
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 | Bars | Gemini 3.1 Pro Preview | Ties |
|---|---|---|---|---|
| Coding | 12 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 8 | 1 | ||
| Reasoning | 4 | 8 | ||
| Math | 4 | 1 | 1 tie | |
| Knowledge | 1 | 6 | ||
| Web design | 6 | 2 | ||
| General | 6 | 24 | ||
| All shared boards | 41 | 46 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index123
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| LiveBench coding | 90.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena WebDev | 1618 | 1447 | DeepSeek V4.1 Flash |
| AA Coding Index | Not measured | 68.8 | Only Gemini 3.1 Pro Preview measured |
| LiveCodeBench (Vals AI) | Not measured | 88.5% | Only Gemini 3.1 Pro Preview measured |
| SWE-bench Verified (Vals AI) | Not measured | 78.8% | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench 4 (Vals AI) | 19.7% | 2.5% | DeepSeek V4.1 Flash |
| Vibe Code Bench (Vals AI) | 84.7% | 32.0% | DeepSeek V4.1 Flash |
| Code migration (Vals AI) | 45.6% | 17.3% | DeepSeek V4.1 Flash |
| ProgramBench (Vals AI) | 0.5% | 0.0% | DeepSeek V4.1 Flash |
| IOI (Vals AI) | 40.3% | 51.8% | Gemini 3.1 Pro Preview |
| Terminal-Bench 2.1 (Vals AI) | 74.5% | 70.8% | DeepSeek V4.1 Flash |
| SWE-bench Multimodal (Vals AI) | 46.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| Vibe Code Bench 1-100 (Vals AI) | 16.4% | 6.7% | DeepSeek V4.1 Flash |
| SkillsBench (Vals AI) | 69.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| CyberBench (Vals AI) | 73.7% | Not measured | Only DeepSeek V4.1 Flash measured |
| SciCode | 51.9% | 58.7% | Gemini 3.1 Pro Preview |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 53.8% | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench | Not measured | 80.2% | Only Gemini 3.1 Pro Preview measured |
| FrontierCode | 43.9% | Not measured | Only DeepSeek V4.1 Flash measured |
| GSO-Bench | Not measured | 22.6% | Only Gemini 3.1 Pro Preview measured |
| WeirdML | Not measured | 72.1% | Only Gemini 3.1 Pro Preview measured |
| MirrorCode | Not measured | 8.9% | Only Gemini 3.1 Pro Preview measured |
| ALE-Bench | 1092.3 | 1160.6 | Gemini 3.1 Pro Preview |
| LMArena Text: coding | 1502 | 1484 | DeepSeek V4.1 Flash |
| LMArena Text: software and IT | 1496 | 1487 | DeepSeek V4.1 Flash |
| LMArena WebDev: React | 1628 | 1438 | DeepSeek V4.1 Flash |
| LMArena WebDev: HTML | 1612 | 1490 | DeepSeek V4.1 Flash |
| LMArena WebDev: from an image | 1606 | 1481 | DeepSeek V4.1 Flash |
| SciCode | Not measured | 14.3% | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 10 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 24.7 | 29.7 | Gemini 3.1 Pro Preview |
| Epoch Capabilities Index | 155.9 | Not measured | Only DeepSeek V4.1 Flash measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index81
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 8.2 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building web apps | Not measured | 1125 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building full-stack apps | Not measured | 1068 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building mobile apps | Not measured | 1093 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building Android apps | Not measured | 1048 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building Godot games | Not measured | 1236 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building games | Not measured | 1114 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: HTML slides | Not measured | 1153 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: PowerPoint slides | Not measured | 1066 | Only Gemini 3.1 Pro Preview measured |
| LiveBench research | 86.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| LiveBench browser | 84.0% | Not measured | Only DeepSeek V4.1 Flash measured |
| LiveBench long agentic | 40.1% | Not measured | Only DeepSeek V4.1 Flash measured |
| SREBench (Vals AI) | 0.8% | 0.0% | DeepSeek V4.1 Flash |
| Finance Agent (Vals AI) | 53.5% | 43.0% | DeepSeek V4.1 Flash |
| Tax Agent Bench (Vals AI) | 26.6% | 9.3% | DeepSeek V4.1 Flash |
| Legal Research Bench (Vals AI) | 41.4% | 20.7% | DeepSeek V4.1 Flash |
| Excel Modeling Benchmark (Vals AI) | 57.2% | 52.6% | DeepSeek V4.1 Flash |
| BioMysteryBench (Vals AI) | 67.8% | 60.0% | DeepSeek V4.1 Flash |
| Terminal-Bench-Science (Vals AI) | 0.0% | 1.4% | Gemini 3.1 Pro Preview |
| Vals Science Index | 29.6% | 27.4% | DeepSeek V4.1 Flash |
| τ²-Bench Telecom | Not measured | 95.6% | Only Gemini 3.1 Pro Preview measured |
| APEX-Agents | 39.5% | 35.1% | DeepSeek V4.1 Flash |
| METR time horizons | Not measured | 77.0% | Only Gemini 3.1 Pro Preview measured |
| BALROG | Not measured | 57.0% | Only Gemini 3.1 Pro Preview measured |
| DeepResearch Bench | Not measured | 47.8% | Only Gemini 3.1 Pro Preview measured |
| PostTrainBench | Not measured | 22.0% | Only Gemini 3.1 Pro Preview measured |
| Vending-Bench 2 | Not measured | $911 | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 14 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index48
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 95.5% | Only Gemini 3.1 Pro Preview measured |
| LiveBench reasoning | 86.7% | Not measured | Only DeepSeek V4.1 Flash measured |
| MysteryMechanism (Vals AI) | 21.2% | 20.7% | DeepSeek V4.1 Flash |
| MMMU Pro (Vals AI) | Not measured | 88.2% | Only Gemini 3.1 Pro Preview measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 94.1% | Only Gemini 3.1 Pro Preview measured |
| Humanity's Last Exam (Artificial Analysis run) | 39.2% | 47.0% | Gemini 3.1 Pro Preview |
| GPQA Diamond (Epoch AI run) | 89.8% | 94.4% | Gemini 3.1 Pro Preview |
| ARC-AGI | 94.5% | 98.0% | Gemini 3.1 Pro Preview |
| ARC-AGI-2 | 72.9% | 77.1% | Gemini 3.1 Pro Preview |
| SimpleBench | Not measured | 79.6% | Only Gemini 3.1 Pro Preview measured |
| Chess puzzles | 48.0% | 51.0% | Gemini 3.1 Pro Preview |
| Mystery game puzzles | 43.0% | 34.0% | DeepSeek V4.1 Flash |
| EBR-bench | Not measured | 14.3% | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: hard prompts | 1483 | 1485 | Gemini 3.1 Pro Preview |
| LMArena Text: expert | 1501 | 1483 | DeepSeek V4.1 Flash |
| LMArena Text: hard prompts in English | 1488 | 1480 | DeepSeek V4.1 Flash |
| LMArena Vision: diagrams | 1297 | 1311 | Gemini 3.1 Pro Preview |
| LMArena Vision: homework | 1307 | 1316 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AIME | Not measured | 98.1% | Only Gemini 3.1 Pro Preview measured |
| OTIS Mock AIME | 98.3% | 95.6% | DeepSeek V4.1 Flash |
| FrontierMath, tiers 1 to 3 | 67.4% | 59.6% | DeepSeek V4.1 Flash |
| FrontierMath, tier 4 | 26.8% | 26.8% | Tie |
| ProofBench | 54.0% | 26.0% | DeepSeek V4.1 Flash |
| LMArena Text: math | 1478 | 1486 | Gemini 3.1 Pro Preview |
| LMArena Text: mathematical work | 1485 | 1478 | DeepSeek V4.1 Flash |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index16
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 91.0% | Only Gemini 3.1 Pro Preview measured |
| LegalBench (Vals AI) | 83.3% | 87.4% | Gemini 3.1 Pro Preview |
| CaseLaw (Vals AI) | Not measured | 64.8% | Only Gemini 3.1 Pro Preview measured |
| CorpFin (Vals AI) | Not measured | 64.5% | Only Gemini 3.1 Pro Preview measured |
| TaxEval (Vals AI) | Not measured | 72.9% | Only Gemini 3.1 Pro Preview measured |
| MortgageTax (Vals AI) | Not measured | 69.4% | Only Gemini 3.1 Pro Preview measured |
| MedQA (Vals AI) | Not measured | 96.4% | Only Gemini 3.1 Pro Preview measured |
| MedCode (Vals AI) | 41.2% | 59.1% | Gemini 3.1 Pro Preview |
| SimpleQA Verified | 42.9% | 73.5% | Gemini 3.1 Pro Preview |
| LMArena Text: science | 1469 | 1497 | Gemini 3.1 Pro Preview |
| LMArena Text: medicine and healthcare | 1484 | 1486 | Gemini 3.1 Pro Preview |
| LMArena Text: legal and government | 1443 | 1487 | Gemini 3.1 Pro Preview |
| LMArena Text: business and finance | 1461 | 1459 | DeepSeek V4.1 Flash |
| FACTS Benchmark Suite | Not measured | 67.4% | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index62
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1309 | 1234 | DeepSeek V4.1 Flash |
| Design Arena: UI components | 1315 | 1227 | DeepSeek V4.1 Flash |
| Design Arena: game dev | 1330 | 1203 | DeepSeek V4.1 Flash |
| Design Arena: data viz | 1290 | 1209 | DeepSeek V4.1 Flash |
| Design Arena: 3D | 1356 | 1234 | DeepSeek V4.1 Flash |
| Design Arena: all code categories | 1320 | 1231 | DeepSeek V4.1 Flash |
| Design Arena: SVG | 1244 | 1285 | Gemini 3.1 Pro Preview |
| Design Arena: ASCII art | 1265 | 1270 | Gemini 3.1 Pro Preview |
| LiveBench design | 79.2% | Not measured | Only DeepSeek V4.1 Flash measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index624
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| LiveBench data analysis | 79.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| Public Benefits Bench (Vals AI) | 64.3% | 53.8% | DeepSeek V4.1 Flash |
| SAGE (Vals AI) | 47.9% | 48.7% | Gemini 3.1 Pro Preview |
| MedScribe (Vals AI) | 85.5% | 76.1% | DeepSeek V4.1 Flash |
| Vals Multimodal Index | Not measured | 56.1% | Only Gemini 3.1 Pro Preview measured |
| IFBench | Not measured | 77.1% | Only Gemini 3.1 Pro Preview measured |
| Long context reasoning (AA-LCR) | 84.0% | 82.0% | DeepSeek V4.1 Flash |
| DTBench | 89.9% | 97.1% | Gemini 3.1 Pro Preview |
| LMCA | 47.0% | 53.8% | Gemini 3.1 Pro Preview |
| CL-bench | Not measured | 20.8% | Only Gemini 3.1 Pro Preview measured |
| Surface Evolver Bench | 46.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| Furniture assembly | 34.2% | 26.7% | DeepSeek V4.1 Flash |
| ExploitBench | Not measured | 26.1% | Only Gemini 3.1 Pro Preview measured |
| CL-bench Life | Not measured | 16.9% | Only Gemini 3.1 Pro Preview measured |
| LMArena Text | 1464 | 1480 | Gemini 3.1 Pro Preview |
| LMArena Text: instruction following | 1473 | 1466 | DeepSeek V4.1 Flash |
| LMArena Text: creative writing | 1437 | 1482 | Gemini 3.1 Pro Preview |
| LMArena Vision | 1278 | 1296 | Gemini 3.1 Pro Preview |
| LMArena Text: English | 1473 | 1478 | Gemini 3.1 Pro Preview |
| LMArena Text: non-English | 1449 | 1476 | Gemini 3.1 Pro Preview |
| LMArena Text: Chinese | 1501 | 1527 | Gemini 3.1 Pro Preview |
| LMArena Text: German | 1470 | 1490 | Gemini 3.1 Pro Preview |
| LMArena Text: Japanese | 1432 | 1491 | Gemini 3.1 Pro Preview |
| LMArena Text: Korean | 1436 | 1455 | Gemini 3.1 Pro Preview |
| LMArena Text: French | 1465 | 1487 | Gemini 3.1 Pro Preview |
| LMArena Text: Spanish | 1459 | 1481 | Gemini 3.1 Pro Preview |
| LMArena Text: Russian | 1467 | 1497 | Gemini 3.1 Pro Preview |
| LMArena Text: Polish | 1457 | 1498 | Gemini 3.1 Pro Preview |
| LMArena Text: multi-turn | 1461 | 1487 | Gemini 3.1 Pro Preview |
| LMArena Text: longer queries | 1473 | 1482 | Gemini 3.1 Pro Preview |
| LMArena Text: writing and language | 1450 | 1481 | Gemini 3.1 Pro Preview |
| LMArena Text: entertainment and media | 1445 | 1465 | Gemini 3.1 Pro Preview |
| LMArena Vision: English | 1288 | 1287 | DeepSeek V4.1 Flash |
| LMArena Vision: Chinese | 1327 | 1364 | Gemini 3.1 Pro Preview |
| LMArena Vision: reading text | 1282 | 1304 | Gemini 3.1 Pro Preview |
| LMArena Vision: humor | 1260 | 1322 | Gemini 3.1 Pro Preview |
| LMArena Vision: captioning | Not measured | 1345 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: recognizing things | Not measured | 1330 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: creative writing | 1275 | 1324 | Gemini 3.1 Pro Preview |
| LMArena Document | Not measured | 1444 | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 6 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview | 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$0.0006Fits in one request
Gemini 3.1 Pro Preview$0.0080Fits in one request
DeepSeek V4.1 Flash costs less
Repository review
50K input + 3K output tokens
DeepSeek V4.1 Flash$0.013Fits in one request
Gemini 3.1 Pro Preview$0.136Fits in one request
DeepSeek V4.1 Flash costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4.1 Flash$0.050Fits in one request
Gemini 3.1 Pro Preview$0.520Fits in one request
DeepSeek V4.1 Flash 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 | Google Gemini 3.1 Pro Preview |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | No public weights listed |
| Released | September 10, 2026 | February 19, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.21 | $2.00 |
| Output $/Mtok | $0.78 | $12.00 |
| Coding index | 62.5 | 32.3 |
| Independent measurements behind it | 5 | 4 |
| Cost per solved task | Not computable | $0.99 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4.1 Flash better than Gemini 3.1 Pro Preview for coding?
Pick DeepSeek V4.1 Flash for coding: it scores 62.5 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview. Pick Gemini 3.1 Pro Preview for work measured by IOI (Vals AI) or SciCode, where it leads.
Which is cheaper, DeepSeek V4.1 Flash or Gemini 3.1 Pro Preview?
DeepSeek V4.1 Flash costs $0.21 per million input tokens and $0.78 per million output tokens; Gemini 3.1 Pro Preview costs $2.00 and $12.00. Cost per solved task is known for Gemini 3.1 Pro Preview only.
Which has the bigger context window, DeepSeek V4.1 Flash or Gemini 3.1 Pro Preview?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4.1 Flash vs Gemini 3.1 Pro Preview comparison based on?
88 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4.1 Flash's coding index rests on 5 independent benchmarks and Gemini 3.1 Pro Preview's on 4. Where only one model has a result, the page says so instead of naming a winner.