# Inkling-Small vs Qwen3 14B

> Inkling-Small is the stronger model overall, scoring 46.5 to 35.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/inkling-small-vs-qwen3-14b
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Inkling-Small scores higher in 5 categories and Qwen3 14B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 39.0 to 18.1.
- The biggest single-benchmark swing is GPQA Diamond: 88.5% for Inkling-Small and 63.8% for Qwen3 14B.
- Both cost about the same: $0.45 input and $1.20 output per million tokens.
- Inkling-Small accepts more context: 524K tokens versus 131K.

## Snapshot

| | Inkling-Small | Qwen3 14B |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 35.0 |
| Rank | 57 | 222 |
| Context | 524K | 131K |
| Input $/M | $0.45 | $0.35 |
| Output $/M | $1.20 | $1.40 |
| Weights | Open | Open |

## Coding

- Inkling-Small: 43.3 (#80)
- Qwen3 14B: 36.7 (#191)

| Benchmark | Inkling-Small | Qwen3 14B |
|---|---|---|
| SciCode | 48.7% | 31.6% |
| LMArena WebDev | 1408 | — |
| LMArena Coding | 1451 | — |

## Agentic & Tool Use

- Inkling-Small: —
- Qwen3 14B: 29.4 (#78)

| Benchmark | Inkling-Small | Qwen3 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41% |

## Reasoning

- Inkling-Small: 39.0 (#53)
- Qwen3 14B: 18.1 (#272)

| Benchmark | Inkling-Small | Qwen3 14B |
|---|---|---|
| CritPt | 8.3% | 0% |
| Chess Puzzles | 18% | 4% |
| Epoch Capabilities Index | 150.13 | 138.23 |
| ARC-AGI-2 | 40.1% | — |
| Kagi LLM Benchmark | — | 49.1% |
| ARC-AGI-1 | 84% | — |
| LMArena Hard Prompts | 1424 | — |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 64% |
| LMCA | — | 18.2% |

## Math

- Inkling-Small: 44.9 (#65)
- Qwen3 14B: 37.0 (#102)

| Benchmark | Inkling-Small | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 66.4% |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| LMArena Math | 1453 | — |

## Knowledge

- Inkling-Small: 48.3 (#71)
- Qwen3 14B: 39.2 (#124)

| Benchmark | Inkling-Small | Qwen3 14B |
|---|---|---|
| GPQA Diamond | 88.5% | 63.8% |
| SimpleQA Verified | 19.1% | — |
| Vectara Hallucination Rate | — | 5.4% |
| LMArena Expert | 1442 | — |

## Multimodal

- Inkling-Small: 38.4 (#59)
- Qwen3 14B: —

| Benchmark | Inkling-Small | Qwen3 14B |
|---|---|---|
| LMArena Vision | 1235 | — |

## Multilingual

- Inkling-Small: 51.7 (#102)
- Qwen3 14B: —

| Benchmark | Inkling-Small | Qwen3 14B |
|---|---|---|
| LMArena Non-English | 1400 | — |
| LMArena Chinese | 1458 | — |
| LMArena French | 1438 | — |
| LMArena German | 1412 | — |
| LMArena Japanese | 1399 | — |
| LMArena Korean | 1355 | — |
| LMArena Russian | 1392 | — |
| LMArena Spanish | 1426 | — |

## Instruction Following

- Inkling-Small: 73.9 (#112)
- Qwen3 14B: —

| Benchmark | Inkling-Small | Qwen3 14B |
|---|---|---|
| LMArena Instruction Following | 1397 | — |

## Long Context

- Inkling-Small: 42.7 (#113)
- Qwen3 14B: 38.0 (#201)

| Benchmark | Inkling-Small | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
| LMArena Longer Query | 1401 | — |

## Writing & Preference

- Inkling-Small: 59.8 (#102)
- Qwen3 14B: —

| Benchmark | Inkling-Small | Qwen3 14B |
|---|---|---|
| LMArena Text | 1413 | — |
| LMArena Creative Writing | 1330 | — |
| EQ-Bench Creative Writing | 1491 | — |
| LMArena Multi-Turn | 1420 | — |

## FAQ

### Is Inkling-Small better than Qwen3 14B?

Inkling-Small is the stronger model overall, scoring 46.5 to 35.0 on the Noometry Index.

### Which is cheaper, Inkling-Small or Qwen3 14B?

Qwen3 14B is cheaper. It lists at $0.35 per million input tokens and $1.40 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Is Inkling-Small or Qwen3 14B better for coding?

Inkling-Small scores higher on coding benchmarks: 43.3 versus 36.7 in the Noometry coding category.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 131K.

### How many benchmarks do Inkling-Small and Qwen3 14B share?

6 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen3 14B has 12.