Model comparison
Inkling vs Qwen3.6 35B-A3B
Inkling is the stronger model overall, scoring 44.1 to 37.2 on the Noometry Index. Qwen3.6 35B-A3B costs 4.6× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 10 shared benchmarks.
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Inkling scores higher in 3 categories and Qwen3.6 35B-A3B in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.6 to 27.2.
- The biggest single-benchmark swing is DTBench: 87.5% for Inkling and 73.9% for Qwen3.6 35B-A3B.
- Qwen3.6 35B-A3B is cheaper at $0.25 / $1.49 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Qwen3.6 35B-A3B accepts more context: 262K tokens versus 66K.
Side by side
| Inkling | Qwen3.6 35B-A3B | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 44.1 | 37.2 |
| Released | 2026-07-15 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 66K | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $1.87 | $0.25 |
| Output $ / M tokens | $4.68 | $1.49 |
| Results tracked | 41 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 35B-A3B leads
Inkling: 34.1 (#229), Qwen3.6 35B-A3B: 36.7 (#190)
| Benchmark | Inkling | Qwen3.6 35B-A3B |
|---|---|---|
| SciCode | 47% | 35.8% |
| WeirdML | 32.3% | 34.5% |
| FrontierCode | 14% | — |
| LMArena WebDev | 1412 | — |
| FrontierSWE | 4.1% | — |
| LMArena Coding | 1463 | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Inkling leads
Inkling: 29.5 (#76), Qwen3.6 35B-A3B: 21.9 (#126)
| Benchmark | Inkling | Qwen3.6 35B-A3B |
|---|---|---|
| Terminal-Bench | — | 23% |
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.6 (#48), Qwen3.6 35B-A3B: 27.2 (#112)
| Benchmark | Inkling | Qwen3.6 35B-A3B |
|---|---|---|
| CritPt | 5.4% | 0.3% |
| Chess Puzzles | 21% | 26% |
| DTBench | 87.5% | 73.9% |
| LMCA | 37.6% | 29.7% |
| Epoch Capabilities Index | 148.6 | 143.92 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| NYT Connections (extended) | — | 41.6% |
| ARC-AGI-1 | 79.5% | — |
| LMArena Hard Prompts | 1452 | — |
| Mystery Game Puzzles | — | 22% |
| Surface Evolver Bench | — | 44.4% |
Math Qwen3.6 35B-A3B leads
Inkling: 31.2 (#198), Qwen3.6 35B-A3B: 37.9 (#90)
| Benchmark | Inkling | Qwen3.6 35B-A3B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 33.3% | 20.4% |
| OTIS Mock AIME 2024-2025 | 88.9% | 86.7% |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 0% | — |
| LMArena Math | 1482 | — |
Knowledge Inkling leads
Inkling: 55.2 (#44), Qwen3.6 35B-A3B: 51.4 (#63)
| Benchmark | Inkling | Qwen3.6 35B-A3B |
|---|---|---|
| GPQA Diamond | 88.3% | 84.8% |
| SimpleQA Verified | 40.3% | — |
| LMArena Expert | 1468 | — |
Multilingual Not comparable
Inkling: 54.2 (#49), Qwen3.6 35B-A3B: —
| Benchmark | Inkling | Qwen3.6 35B-A3B |
|---|---|---|
| LMArena Non-English | 1434 | — |
| LMArena Chinese | 1495 | — |
| LMArena French | 1453 | — |
| LMArena German | 1456 | — |
| LMArena Japanese | 1428 | — |
| LMArena Korean | 1401 | — |
| LMArena Russian | 1430 | — |
| LMArena Spanish | 1442 | — |
Instruction Following Not comparable
Inkling: 75.3 (#65), Qwen3.6 35B-A3B: —
| Benchmark | Inkling | Qwen3.6 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1427 | — |
Long Context Not comparable
Inkling: 43.9 (#79), Qwen3.6 35B-A3B: —
| Benchmark | Inkling | Qwen3.6 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1436 | — |
Writing & Preference Not comparable
Inkling: 65.5 (#48), Qwen3.6 35B-A3B: —
| Benchmark | Inkling | Qwen3.6 35B-A3B |
|---|---|---|
| LMArena Text | 1443 | — |
| LMArena Creative Writing | 1390 | — |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LMArena Multi-Turn | 1436 | — |
Frequently asked questions
Is Inkling better than Qwen3.6 35B-A3B?
Inkling is the stronger model overall, scoring 44.1 to 37.2 on the Noometry Index. Qwen3.6 35B-A3B costs 4.6× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Inkling or Qwen3.6 35B-A3B?
Qwen3.6 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $1.49 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Qwen3.6 35B-A3B better for coding?
Qwen3.6 35B-A3B scores higher on coding benchmarks: 36.7 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 35B-A3B does, with 262K tokens against 66K.
How many benchmarks do Inkling and Qwen3.6 35B-A3B share?
10 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Qwen3.6 35B-A3B has 14.