DeepSeek V4.1 Flash vs Gemma 4 31B
Updated October 21, 2026. 56 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick DeepSeek V4.1 Flash for coding: it scores 77.2 on the Vibe Coding Index against 38.3 for Gemma 4 31B.
Pick Gemma 4 31B when output tokens cost 1.3x less, or when what matters is LMArena Vision: homework or SAGE (Vals AI), where it leads.
- Shared results
- 56
- DeepSeek V4.1 Flash only
- 45
- Gemma 4 31B only
- 12
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash scores 77.2 against 38.3.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash leads, 24.7 against 14.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemma 4 31B has a AA Agentic Index result, 4.2.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V4.1 Flash has a Design Arena: websites result, 1309.
Directional only
Long documents
Listed context window
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash $0.0003, Gemma 4 31B $0.0004 per turn.
List prices
At a glance
- Coding index
- DeepSeek V4.1 Flash 77.2 from 2 benchmarks, Gemma 4 31B 38.3 from 2 benchmarks.
- Widest category
- Agentic work, 49.7 points apart on average over 3 shared benchmarks.
- Widest single gap
- LiveBench browser: DeepSeek V4.1 Flash 84.0% against Gemma 4 31B 4.0%, 80.0 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4.1 Flash $0.525 against Gemma 4 31B $0.40 per million output tokens, 1.3x apart.
- Context window
- DeepSeek V4.1 Flash takes 1.05M tokens, Gemma 4 31B 262K.
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 | Gemma 4 31B | Ties |
|---|---|---|---|---|
| Coding | 8 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 3 | 0 | ||
| Reasoning | 7 | 1 | ||
| Math | 3 | 0 | ||
| Knowledge | 5 | 0 | ||
| Web design | 1 | 0 | ||
| General | 23 | 3 | ||
| All shared boards | 52 | 4 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index80
| Benchmark | DeepSeek V4.1 Flash | Gemma 4 31B | Leader |
|---|---|---|---|
| LiveBench coding | 90.2% | 49.0% | DeepSeek V4.1 Flash |
| LMArena WebDev | 1618 | 1367 | DeepSeek V4.1 Flash |
| AA Coding Index | Not measured | 43.4 | Only Gemma 4 31B measured |
| Terminal-Bench 4 (Vals AI) | 19.7% | Not measured | Only DeepSeek V4.1 Flash measured |
| Vibe Code Bench (Vals AI) | 84.7% | Not measured | Only DeepSeek V4.1 Flash measured |
| Code migration (Vals AI) | 45.6% | Not measured | Only DeepSeek V4.1 Flash measured |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| IOI (Vals AI) | 40.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| Terminal-Bench 2.1 (Vals AI) | 74.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| SWE-bench Multimodal (Vals AI) | 46.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| Vibe Code Bench 1-100 (Vals AI) | 16.4% | Not measured | Only DeepSeek V4.1 Flash measured |
| 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% | 45.5% | DeepSeek V4.1 Flash |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 36.4% | Only Gemma 4 31B measured |
| FrontierCode | 43.9% | Not measured | Only DeepSeek V4.1 Flash measured |
| WeirdML | Not measured | 52.3% | Only Gemma 4 31B measured |
| ALE-Bench | 1092.3 | 925.5 | DeepSeek V4.1 Flash |
| LMArena Text: coding | 1502 | 1459 | DeepSeek V4.1 Flash |
| LMArena Text: software and IT | 1496 | 1463 | DeepSeek V4.1 Flash |
| LMArena WebDev: React | 1628 | 1359 | DeepSeek V4.1 Flash |
| LMArena WebDev: HTML | 1612 | 1380 | DeepSeek V4.1 Flash |
| LMArena WebDev: from an image | 1606 | Not measured | Only DeepSeek V4.1 Flash measured |
| Neither model has a result on the other 15 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4.1 Flash | Gemma 4 31B | Leader |
|---|---|---|---|
| AA Intelligence Index | 24.7 | 14.7 | DeepSeek V4.1 Flash |
| Epoch Capabilities Index | 155.9 | 143.0 | DeepSeek V4.1 Flash |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | DeepSeek V4.1 Flash | Gemma 4 31B | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 4.2 | Only Gemma 4 31B measured |
| LiveBench research | 86.8% | 44.4% | DeepSeek V4.1 Flash |
| LiveBench browser | 84.0% | 4.0% | DeepSeek V4.1 Flash |
| LiveBench long agentic | 40.1% | 13.3% | DeepSeek V4.1 Flash |
| SREBench (Vals AI) | 0.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| Finance Agent (Vals AI) | 53.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| Tax Agent Bench (Vals AI) | 26.6% | Not measured | Only DeepSeek V4.1 Flash measured |
| Legal Research Bench (Vals AI) | 41.4% | Not measured | Only DeepSeek V4.1 Flash measured |
| Excel Modeling Benchmark (Vals AI) | 57.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| BioMysteryBench (Vals AI) | 67.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| Terminal-Bench-Science (Vals AI) | 0.0% | Not measured | Only DeepSeek V4.1 Flash measured |
| Vals Science Index | 29.6% | Not measured | Only DeepSeek V4.1 Flash measured |
| τ²-Bench Telecom | Not measured | 65.5% | Only Gemma 4 31B measured |
| APEX-Agents | 39.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
| Benchmark | DeepSeek V4.1 Flash | Gemma 4 31B | Leader |
|---|---|---|---|
| LiveBench reasoning | 86.7% | 68.3% | DeepSeek V4.1 Flash |
| MysteryMechanism (Vals AI) | 21.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 85.7% | Only Gemma 4 31B measured |
| Humanity's Last Exam (Artificial Analysis run) | 39.2% | 23.6% | DeepSeek V4.1 Flash |
| GPQA Diamond (Epoch AI run) | 89.8% | 75.8% | DeepSeek V4.1 Flash |
| ARC-AGI | 94.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| ARC-AGI-2 | 72.9% | Not measured | Only DeepSeek V4.1 Flash measured |
| Chess puzzles | 48.0% | Not measured | Only DeepSeek V4.1 Flash measured |
| Mystery game puzzles | 43.0% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: hard prompts | 1483 | 1448 | DeepSeek V4.1 Flash |
| LMArena Text: expert | 1501 | 1464 | DeepSeek V4.1 Flash |
| LMArena Text: hard prompts in English | 1488 | 1456 | DeepSeek V4.1 Flash |
| LMArena Vision: diagrams | 1297 | 1283 | DeepSeek V4.1 Flash |
| LMArena Vision: homework | 1307 | 1310 | Gemma 4 31B |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | DeepSeek V4.1 Flash | Gemma 4 31B | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.3% | 73.3% | DeepSeek V4.1 Flash |
| FrontierMath, tiers 1 to 3 | 67.4% | Not measured | Only DeepSeek V4.1 Flash measured |
| FrontierMath, tier 4 | 26.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| ProofBench | 54.0% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: math | 1478 | 1463 | DeepSeek V4.1 Flash |
| LMArena Text: mathematical work | 1485 | 1465 | DeepSeek V4.1 Flash |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | DeepSeek V4.1 Flash | Gemma 4 31B | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | 83.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| CaseLaw (Vals AI) | Not measured | 52.6% | Only Gemma 4 31B measured |
| MortgageTax (Vals AI) | Not measured | 61.4% | Only Gemma 4 31B measured |
| MedCode (Vals AI) | 41.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| SimpleQA Verified | 42.9% | 10.4% | DeepSeek V4.1 Flash |
| LMArena Text: science | 1469 | 1457 | DeepSeek V4.1 Flash |
| LMArena Text: medicine and healthcare | 1484 | 1451 | DeepSeek V4.1 Flash |
| LMArena Text: legal and government | 1443 | 1438 | DeepSeek V4.1 Flash |
| LMArena Text: business and finance | 1461 | 1430 | DeepSeek V4.1 Flash |
| Neither model has a result on the other 8 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4.1 Flash | Gemma 4 31B | Leader |
|---|---|---|---|
| Design Arena: websites | 1309 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: UI components | 1314 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: game dev | 1331 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: data viz | 1290 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: 3D | 1356 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: all code categories | 1320 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: SVG | 1243 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: ASCII art | 1265 | Not measured | Only DeepSeek V4.1 Flash measured |
| LiveBench design | 79.2% | 58.4% | DeepSeek V4.1 Flash |
GeneralLike-for-likePublic boards, shown as published, kept out of the index233
| Benchmark | DeepSeek V4.1 Flash | Gemma 4 31B | Leader |
|---|---|---|---|
| LiveBench data analysis | 79.3% | 53.3% | DeepSeek V4.1 Flash |
| Public Benefits Bench (Vals AI) | 64.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| SAGE (Vals AI) | 47.9% | 55.0% | Gemma 4 31B |
| MedScribe (Vals AI) | 85.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| IFBench | Not measured | 75.6% | Only Gemma 4 31B measured |
| Long context reasoning (AA-LCR) | 84.0% | 69.7% | DeepSeek V4.1 Flash |
| DTBench | 89.9% | 82.7% | DeepSeek V4.1 Flash |
| LMCA | 47.0% | 39.3% | DeepSeek V4.1 Flash |
| Surface Evolver Bench | 46.3% | 30.6% | DeepSeek V4.1 Flash |
| Furniture assembly | 34.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text | 1464 | 1443 | DeepSeek V4.1 Flash |
| LMArena Text: instruction following | 1473 | 1433 | DeepSeek V4.1 Flash |
| LMArena Text: creative writing | 1437 | 1417 | DeepSeek V4.1 Flash |
| LMArena Vision | 1278 | 1276 | DeepSeek V4.1 Flash |
| LMArena Text: English | 1473 | 1451 | DeepSeek V4.1 Flash |
| LMArena Text: non-English | 1449 | 1430 | DeepSeek V4.1 Flash |
| LMArena Text: Chinese | 1501 | 1475 | DeepSeek V4.1 Flash |
| LMArena Text: German | 1470 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: Japanese | 1432 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: Korean | 1436 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: French | 1465 | 1436 | DeepSeek V4.1 Flash |
| LMArena Text: Spanish | 1459 | 1442 | DeepSeek V4.1 Flash |
| LMArena Text: Russian | 1467 | 1460 | DeepSeek V4.1 Flash |
| LMArena Text: Polish | 1457 | 1433 | DeepSeek V4.1 Flash |
| LMArena Text: multi-turn | 1461 | 1452 | DeepSeek V4.1 Flash |
| LMArena Text: longer queries | 1473 | 1446 | DeepSeek V4.1 Flash |
| LMArena Text: writing and language | 1450 | 1432 | DeepSeek V4.1 Flash |
| LMArena Text: entertainment and media | 1445 | 1405 | DeepSeek V4.1 Flash |
| LMArena Vision: English | 1288 | 1271 | DeepSeek V4.1 Flash |
| LMArena Vision: Chinese | 1327 | 1326 | DeepSeek V4.1 Flash |
| LMArena Vision: reading text | 1282 | 1282 | DeepSeek V4.1 Flash |
| LMArena Vision: humor | 1260 | 1280 | Gemma 4 31B |
| LMArena Vision: captioning | Not measured | 1218 | Only Gemma 4 31B measured |
| LMArena Vision: recognizing things | Not measured | 1226 | Only Gemma 4 31B measured |
| LMArena Vision: creative writing | 1275 | 1285 | Gemma 4 31B |
| LMArena Document | Not measured | 1425 | Only Gemma 4 31B measured |
| Neither model has a result on the other 10 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4.1 Flash | Gemma 4 31B | 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 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4.1 Flash costs less
Agent loop
200K input + 10K output tokens
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 Gemma 4 31B |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | Open weights |
| Released | September 10, 2026 | April 2, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $0.049 | $0.20 |
| Output $/Mtok | $0.525 | $0.40 |
| Coding index | 77.2 | 38.3 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4.1 Flash better than Gemma 4 31B for coding?
Pick DeepSeek V4.1 Flash for coding: it scores 77.2 on the Vibe Coding Index against 38.3 for Gemma 4 31B. Pick Gemma 4 31B when output tokens cost 1.3x less, or when what matters is LMArena Vision: homework or SAGE (Vals AI), where it leads.
Which is cheaper, DeepSeek V4.1 Flash or Gemma 4 31B?
DeepSeek V4.1 Flash costs $0.049 per million input tokens and $0.525 per million output tokens; Gemma 4 31B costs $0.20 and $0.40. Cost per solved task is known for neither of them.
Which has the bigger context window, DeepSeek V4.1 Flash or Gemma 4 31B?
DeepSeek V4.1 Flash, with 1.05M tokens against 262K.
How many benchmarks is the DeepSeek V4.1 Flash vs Gemma 4 31B comparison based on?
56 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4.1 Flash's coding index rests on 2 independent benchmarks and Gemma 4 31B's on 2. Where only one model has a result, the page says so instead of naming a winner.