# DeepSeek V4.1 Flash vs Inkling-Small

> DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 46.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-1-flash-vs-inkling-small
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Inkling-Small in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 45.1.
- The biggest single-benchmark swing is ProofBench: 54% for DeepSeek V4.1 Flash and 6% for Inkling-Small.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 524K.

## Snapshot

| | DeepSeek V4.1 Flash | Inkling-Small |
|---|---|---|
| Provider | DeepSeek | Thinking Machines Lab |
| Noometry Index | 52.8 | 46.5 |
| Rank | 38 | 63 |
| Context | 1M | 524K |
| Input $/M | $0.15 | $0.45 |
| Output $/M | $0.60 | $1.20 |
| Weights | Open | Open |

## Coding

- DeepSeek V4.1 Flash: 52.9 (#32)
- Inkling-Small: 43.6 (#85)

| Benchmark | DeepSeek V4.1 Flash | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1619 | 1409 |
| SciCode | 51.9% | 48.7% |
| LMArena Coding | 1506 | 1451 |
| ALE-Bench | 1,092 | — |

## Agentic & Tool Use

- DeepSeek V4.1 Flash: 31.2 (#69)
- Inkling-Small: —

| Benchmark | DeepSeek V4.1 Flash | Inkling-Small |
|---|---|---|
| APEX-Agents | 39.5% | — |
| GDP.pdf | 19.8% | — |

## Reasoning

- DeepSeek V4.1 Flash: 50.2 (#36)
- Inkling-Small: 38.6 (#63)

| Benchmark | DeepSeek V4.1 Flash | Inkling-Small |
|---|---|---|
| CritPt | 14.3% | 8.3% |
| LMArena Hard Prompts | 1483 | 1423 |
| Mystery Game Puzzles | 43% | 6% |
| Epoch Capabilities Index | 154.9 | 150.15 |
| ARC-AGI-2 | — | 40.1% |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | — | 84% |
| Chess Puzzles | — | 18% |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |

## Math

- DeepSeek V4.1 Flash: 66.7 (#25)
- Inkling-Small: 45.1 (#77)

| Benchmark | DeepSeek V4.1 Flash | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 67.4% | 46.3% |
| FrontierMath Tier 4 | 26.8% | 17.1% |
| OTIS Mock AIME 2024-2025 | 98.3% | 90% |
| ProofBench | 54% | 6% |
| LMArena Math | 1477 | 1459 |

## Knowledge

- DeepSeek V4.1 Flash: 57.9 (#38)
- Inkling-Small: 48.2 (#77)

| Benchmark | DeepSeek V4.1 Flash | Inkling-Small |
|---|---|---|
| GPQA Diamond | 89.8% | 88.5% |
| LMArena Expert | 1506 | 1442 |
| SimpleQA Verified | — | 19.1% |

## Multimodal

- DeepSeek V4.1 Flash: 39.1 (#61)
- Inkling-Small: 39.1 (#62)

| Benchmark | DeepSeek V4.1 Flash | Inkling-Small |
|---|---|---|
| LMArena Vision | 1277 | 1235 |
| Furniture Assembly | 34.2% | — |

## Multilingual

- DeepSeek V4.1 Flash: 55.0 (#35)
- Inkling-Small: 51.7 (#104)

| Benchmark | DeepSeek V4.1 Flash | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1448 | 1402 |
| LMArena Chinese | 1497 | 1465 |
| LMArena French | 1452 | 1436 |
| LMArena German | 1484 | 1405 |
| LMArena Japanese | 1412 | 1405 |
| LMArena Korean | 1452 | 1363 |
| LMArena Russian | 1471 | 1391 |
| LMArena Spanish | 1459 | 1428 |

## Instruction Following

- DeepSeek V4.1 Flash: 77.3 (#26)
- Inkling-Small: 73.8 (#114)

| Benchmark | DeepSeek V4.1 Flash | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1474 | 1399 |

## Long Context

- DeepSeek V4.1 Flash: 45.2 (#47)
- Inkling-Small: 42.7 (#118)

| Benchmark | DeepSeek V4.1 Flash | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1475 | 1401 |

## Writing & Preference

- DeepSeek V4.1 Flash: 65.4 (#48)
- Inkling-Small: 59.6 (#107)

| Benchmark | DeepSeek V4.1 Flash | Inkling-Small |
|---|---|---|
| LMArena Text | 1462 | 1414 |
| LMArena Creative Writing | 1435 | 1331 |
| EQ-Bench Creative Writing | 1540 | 1491 |
| LMArena Multi-Turn | 1457 | 1418 |

## FAQ

### Is DeepSeek V4.1 Flash better than Inkling-Small?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 46.5 on the Noometry Index.

### Which is cheaper, DeepSeek V4.1 Flash or Inkling-Small?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Is DeepSeek V4.1 Flash or Inkling-Small better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 43.6 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 524K.

### How many benchmarks do DeepSeek V4.1 Flash and Inkling-Small share?

29 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Inkling-Small has 33.