# Inkling vs Qwen3.5 35B-A3B

> Inkling is the stronger model overall, scoring 44.1 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 3.7× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/inkling-vs-qwen3-5-35b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Inkling scores higher in 7 categories and Qwen3.5 35B-A3B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 24.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Inkling and 70% for Qwen3.5 35B-A3B.
- Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Qwen3.5 35B-A3B accepts more context: 262K tokens versus 66K.

## Snapshot

| | Inkling | Qwen3.5 35B-A3B |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 44.1 | 42.0 |
| Rank | 80 | 123 |
| Context | 66K | 262K |
| Input $/M | $1.87 | $0.25 |
| Output $/M | $4.68 | $2 |
| Weights | Open | Open |

## Coding

- Inkling: 34.5 (#234)
- Qwen3.5 35B-A3B: 33.8 (#251)

| Benchmark | Inkling | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena WebDev | 1413 | 1254 |
| SciCode | 47% | 29.3% |
| LMArena Coding | 1464 | 1410 |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |

## Agentic & Tool Use

- Inkling: 29.6 (#85)
- Qwen3.5 35B-A3B: —

| Benchmark | Inkling | Qwen3.5 35B-A3B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |

## Reasoning

- Inkling: 40.4 (#56)
- Qwen3.5 35B-A3B: 24.6 (#161)

| Benchmark | Inkling | Qwen3.5 35B-A3B |
|---|---|---|
| CritPt | 5.4% | 0.6% |
| Chess Puzzles | 21% | 10% |
| LMArena Hard Prompts | 1451 | 1400 |
| DTBench | 87.5% | 80% |
| LMCA | 37.6% | 29.5% |
| Epoch Capabilities Index | 148.54 | 142.52 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |

## Math

- Inkling: 31.3 (#225)
- Qwen3.5 35B-A3B: 39.9 (#97)

| Benchmark | Inkling | Qwen3.5 35B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 70% |
| LMArena Math | 1479 | 1404 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| MathArena Final-Answer Competitions | — | 56% |
| ProofBench | 0% | — |

## Knowledge

- Inkling: 55.1 (#49)
- Qwen3.5 35B-A3B: 47.8 (#79)

| Benchmark | Inkling | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 88.3% | 83.5% |
| LMArena Expert | 1465 | 1408 |
| SimpleQA Verified | 40.3% | — |
| Vectara Hallucination Rate | — | 10.5% |

## Multilingual

- Inkling: 54.0 (#52)
- Qwen3.5 35B-A3B: 50.0 (#127)

| Benchmark | Inkling | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1434 | 1378 |
| LMArena Chinese | 1490 | 1457 |
| LMArena French | 1458 | 1412 |
| LMArena German | 1446 | 1367 |
| LMArena Japanese | 1429 | 1325 |
| LMArena Korean | 1404 | 1356 |
| LMArena Russian | 1429 | 1376 |
| LMArena Spanish | 1448 | 1392 |

## Instruction Following

- Inkling: 75.1 (#71)
- Qwen3.5 35B-A3B: 72.8 (#128)

| Benchmark | Inkling | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1379 |

## Long Context

- Inkling: 43.8 (#86)
- Qwen3.5 35B-A3B: 42.4 (#127)

| Benchmark | Inkling | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1434 | 1389 |

## Writing & Preference

- Inkling: 65.2 (#51)
- Qwen3.5 35B-A3B: 57.9 (#124)

| Benchmark | Inkling | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1441 | 1395 |
| LMArena Creative Writing | 1387 | 1346 |
| LMArena Multi-Turn | 1436 | 1390 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |

## FAQ

### Is Inkling better than Qwen3.5 35B-A3B?

Inkling is the stronger model overall, scoring 44.1 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 3.7× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

### Which is cheaper, Inkling or Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Inkling lists at $1.87 and $4.68.

### Is Inkling or Qwen3.5 35B-A3B better for coding?

They score almost the same on coding (34.5 vs 33.8); test both on your own repository before choosing.

### Which has the bigger context window?

Qwen3.5 35B-A3B does, with 262K tokens against 66K.

### How many benchmarks do Inkling and Qwen3.5 35B-A3B share?

26 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Qwen3.5 35B-A3B has 28.