DeepSeek V4.1 Flash vs Inkling 2 Small
DeepSeek V4.1 Flash leads Inkling 2 Small on coding, 56.6 to 48.9 on the Vibe Coding Index, and DeepSeek V4.1 Flash costs 1.3x less per output token ($0.79 vs $1.00 per million). Updated November 14, 2026; 43 benchmarks have a result for both.
vs boards won of 43 shared, 1 tied
DeepSeek V4.1 Flash or Inkling 2 Small: which to pick
Pick DeepSeek V4.1 Flash for coding: it scores 56.6 on the Vibe Coding Index against 48.9 for Inkling 2 Small.
Pick Inkling 2 Small for work measured by LMArena WebDev or SciCode, where it leads.
Model ADeepSeek V4.1 FlashDeepSeek56.6/1004 independent benchmarksNo cost per solved taskModel BInkling 2 SmallThinking Machines48.9/1003 independent benchmarksNo cost per solved task
- Shared results
- 43
- DeepSeek V4.1 Flash only
- 58
- Inkling 2 Small only
- 8
- 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
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash scores 56.6 against 48.9.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only Inkling 2 Small has a AA Intelligence Index result, 30.6.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V4.1 Flash has a Design Arena: websites result, 1298.
Directional only
General
Vals Index
No call
Only Inkling 2 Small has a Vals Index result, 56.1%.
Directional only
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, Inkling 2 Small $0.0008 per turn.
List prices
At a glance
- Coding index
- DeepSeek V4.1 Flash 56.6 from 4 benchmarks, Inkling 2 Small 48.9 from 3 benchmarks.
- Widest category
- General, 9.5 points apart on average over 13 shared benchmarks.
- Widest single gap
- LMArena Text: Russian: DeepSeek V4.1 Flash 1469 against Inkling 2 Small 1377, 15.3 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4.1 Flash $0.79 against Inkling 2 Small $1.00 per million output tokens, 1.3x 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 | Inkling 2 Small | Ties |
|---|---|---|---|---|
| Coding | 7 | 4 | 1 tie | |
| Agentic work | 0 | 7 | ||
| Reasoning | 3 | 5 | ||
| Math | 0 | 1 | ||
| Knowledge | 2 | 0 | ||
| General | 11 | 2 | ||
| All shared boards | 23 | 19 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index74
| Benchmark | DeepSeek V4.1 Flash | Inkling 2 Small | Leader |
|---|---|---|---|
| LMArena WebDev | 1621 | 1647 | Inkling 2 Small |
| Terminal-Bench 4 (Vals AI) | 19.7% | 12.6% | DeepSeek V4.1 Flash |
| Vibe Code Bench (Vals AI) | 84.7% | 81.5% | DeepSeek V4.1 Flash |
| Code migration (Vals AI) | 45.6% | Not measured | Only DeepSeek V4.1 Flash measured |
| ProgramBench (Vals AI) | 0.5% | 0.5% | Tie |
| 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% | 43.1% | DeepSeek V4.1 Flash |
| 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% | 72.7% | DeepSeek V4.1 Flash |
| SciCode | 51.9% | 52.3% | Inkling 2 Small |
| Terminal-Bench 4.0 (Artificial Analysis run) | 26.8% | 13.1% | DeepSeek V4.1 Flash |
| FrontierCode 2.0 | Not measured | 25.4% | Only Inkling 2 Small measured |
| FrontierCode | 43.9% | Not measured | Only DeepSeek V4.1 Flash measured |
| MirrorCode | 64.4% | Not measured | Only DeepSeek V4.1 Flash measured |
| ALE-Bench | 1092.3 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: coding | 1504 | 1455 | DeepSeek V4.1 Flash |
| LMArena Text: software and IT | 1496 | 1443 | DeepSeek V4.1 Flash |
| LMArena WebDev: React | 1630 | 1660 | Inkling 2 Small |
| LMArena WebDev: HTML | 1618 | 1661 | Inkling 2 Small |
| LMArena WebDev: from an image | 1610 | Not measured | Only DeepSeek V4.1 Flash measured |
| SWE-Bench Pro V2 | Not measured | 97.7% | Only Inkling 2 Small measured |
| GameBench 2 | 68.4 | Not measured | Only DeepSeek V4.1 Flash measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | DeepSeek V4.1 Flash | Inkling 2 Small | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 30.6 | Only Inkling 2 Small measured |
| Epoch Capabilities Index | 156.7 | Not measured | Only DeepSeek V4.1 Flash measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | DeepSeek V4.1 Flash | Inkling 2 Small | Leader |
|---|---|---|---|
| SREBench (Vals AI) | 0.8% | 1.9% | Inkling 2 Small |
| Finance Agent (Vals AI) | 53.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| Tax Agent Bench (Vals AI) | 26.6% | 38.9% | Inkling 2 Small |
| Legal Research Bench (Vals AI) | 41.4% | 46.6% | Inkling 2 Small |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 21.7% | Only Inkling 2 Small measured |
| Excel Modeling Benchmark (Vals AI) | 57.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| BioMysteryBench (Vals AI) | 67.8% | 70.0% | Inkling 2 Small |
| Terminal-Bench-Science (Vals AI) | 0.0% | 2.9% | Inkling 2 Small |
| Vals Science Index | 29.6% | 32.7% | Inkling 2 Small |
| APEX-Agents | 39.5% | 46.8% | Inkling 2 Small |
| MCP Atlas | Not measured | 85.4% | Only Inkling 2 Small measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index35
| Benchmark | DeepSeek V4.1 Flash | Inkling 2 Small | Leader |
|---|---|---|---|
| MysteryMechanism (Vals AI) | 21.2% | 25.2% | Inkling 2 Small |
| Humanity's Last Exam (Artificial Analysis run) | 39.2% | 44.1% | Inkling 2 Small |
| HLE-Diamond (Artificial Analysis run) | 19.1% | 28.7% | Inkling 2 Small |
| CritPt v2, hard subset (Artificial Analysis run) | Not measured | 35.0% | Only Inkling 2 Small measured |
| GPQA Diamond (Epoch AI run) | 89.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| ARC-AGI | 94.5% | 96.5% | Inkling 2 Small |
| ARC-AGI-2 | 72.9% | 81.7% | Inkling 2 Small |
| SimpleBench | 66.7% | 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 | 1421 | DeepSeek V4.1 Flash |
| LMArena Text: expert | 1503 | 1478 | DeepSeek V4.1 Flash |
| LMArena Text: hard prompts in English | 1488 | 1424 | DeepSeek V4.1 Flash |
| LMArena Vision: diagrams | 1299 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Vision: homework | 1307 | Not measured | Only DeepSeek V4.1 Flash measured |
| GoBench | 1706 | Not measured | Only DeepSeek V4.1 Flash measured |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V4.1 Flash | Inkling 2 Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| 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 | 1479 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: mathematical work | 1479 | Not measured | Only DeepSeek V4.1 Flash measured |
| MathArena | 39.3% | 42.4% | Inkling 2 Small |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4.1 Flash | Inkling 2 Small | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | 83.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| MedCode (Vals AI) | 41.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| AA-Omniscience | Not measured | 16.1 | Only Inkling 2 Small measured |
| SimpleQA Verified | 42.9% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: science | 1468 | 1409 | DeepSeek V4.1 Flash |
| LMArena Text: medicine and healthcare | 1490 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: legal and government | 1447 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: business and finance | 1463 | 1415 | DeepSeek V4.1 Flash |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V4.1 Flash | Inkling 2 Small | Leader |
|---|---|---|---|
| Design Arena: websites | 1298 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: UI components | 1303 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: game dev | 1324 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: data viz | 1285 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: 3D | 1338 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: all code categories | 1309 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: SVG | 1231 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: ASCII art | 1259 | Not measured | Only DeepSeek V4.1 Flash measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index112
| Benchmark | DeepSeek V4.1 Flash | Inkling 2 Small | Leader |
|---|---|---|---|
| Vals Index | Not measured | 56.1% | Only Inkling 2 Small measured |
| Public Benefits Bench (Vals AI) | 64.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| SAGE (Vals AI) | 85.4% | 88.6% | Inkling 2 Small |
| MedScribe (Vals AI) | 85.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| Long context reasoning (AA-LCR) | 84.0% | 83.3% | DeepSeek V4.1 Flash |
| GDPval-AA | 1600 | 1630 | Inkling 2 Small |
| DTBench | 89.9% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMCA | 47.0% | Not measured | Only DeepSeek V4.1 Flash measured |
| Surface Evolver Bench | 46.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| Furniture assembly | 34.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text | 1464 | 1403 | DeepSeek V4.1 Flash |
| LMArena Text: instruction following | 1473 | 1408 | DeepSeek V4.1 Flash |
| LMArena Text: creative writing | 1438 | 1348 | DeepSeek V4.1 Flash |
| LMArena Vision | 1279 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: English | 1474 | 1418 | DeepSeek V4.1 Flash |
| LMArena Text: non-English | 1450 | 1390 | DeepSeek V4.1 Flash |
| LMArena Text: Chinese | 1505 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: German | 1460 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: Japanese | 1430 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: Korean | 1423 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: French | 1470 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: Spanish | 1456 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: Russian | 1469 | 1377 | DeepSeek V4.1 Flash |
| LMArena Text: Polish | 1453 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: multi-turn | 1462 | 1408 | DeepSeek V4.1 Flash |
| LMArena Text: longer queries | 1474 | 1403 | DeepSeek V4.1 Flash |
| LMArena Text: writing and language | 1449 | 1381 | DeepSeek V4.1 Flash |
| LMArena Text: entertainment and media | 1444 | 1359 | DeepSeek V4.1 Flash |
| LMArena Vision: English | 1290 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Vision: Chinese | 1345 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Vision: reading text | 1284 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Vision: humor | 1279 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Vision: creative writing | 1283 | Not measured | Only DeepSeek V4.1 Flash measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4.1 Flash | Inkling 2 Small | 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
Inkling 2 Small$0.0008Fits in one request
DeepSeek V4.1 Flash costs less
Repository review
50K input + 3K output tokens
DeepSeek V4.1 Flash$0.012Fits in one request
Inkling 2 Small$0.018Fits in one request
DeepSeek V4.1 Flash costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4.1 Flash$0.048Fits in one request
Inkling 2 Small$0.070Fits 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 | Thinking Machines Inkling 2 Small |
|---|---|---|
| Maker | DeepSeek | Thinking Machines |
| Weights | Open weights | Open weights |
| Released | September 10, 2026 | November 9, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.2025 | $0.30 |
| Output $/Mtok | $0.79 | $1.00 |
| Coding index | 56.6 | 48.9 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4.1 Flash better than Inkling 2 Small for coding?
Pick DeepSeek V4.1 Flash for coding: it scores 56.6 on the Vibe Coding Index against 48.9 for Inkling 2 Small. Pick Inkling 2 Small for work measured by LMArena WebDev or SciCode, where it leads.
Which is cheaper, DeepSeek V4.1 Flash or Inkling 2 Small?
DeepSeek V4.1 Flash costs $0.2025 per million input tokens and $0.79 per million output tokens; Inkling 2 Small costs $0.30 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, DeepSeek V4.1 Flash or Inkling 2 Small?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4.1 Flash vs Inkling 2 Small comparison based on?
43 benchmarks have a result for both models as of November 14, 2026. DeepSeek V4.1 Flash's coding index rests on 4 independent benchmarks and Inkling 2 Small's on 3. Where only one model has a result, the page says so instead of naming a winner.