Model comparison
Inkling-Small vs Qwen3.5 27B
Inkling-Small is the stronger model overall, scoring 46.5 to 41.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Inkling-Small scores higher in 7 categories and Qwen3.5 27B in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 27.5.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.30 / $2.40 for Qwen3.5 27B.
- Inkling-Small accepts more context: 524K tokens versus 262K.
Side by side
| Inkling-Small | Qwen3.5 27B | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 41.9 |
| Released | 2026-07-15 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 524K | 262K |
| Max output | 1.05M | 66K |
| Input $ / M tokens | $0.45 | $0.30 |
| Output $ / M tokens | $1.20 | $2.40 |
| Results tracked | 33 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.6 (#85), Qwen3.5 27B: 38.9 (#168)
| Benchmark | Inkling-Small | Qwen3.5 27B |
|---|---|---|
| LMArena WebDev | 1409 | 1358 |
| LMArena Coding | 1451 | 1427 |
| SciCode | 48.7% | — |
| WeirdML | — | 39.5% |
| ALE-Bench | — | 349.45 |
Agentic & Tool Use Not comparable
Inkling-Small: —, Qwen3.5 27B: —
| Benchmark | Inkling-Small | Qwen3.5 27B |
|---|---|---|
| Vending-Bench 2 | — | 201.98 |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Qwen3.5 27B: 27.5 (#117)
| Benchmark | Inkling-Small | Qwen3.5 27B |
|---|---|---|
| LMArena Hard Prompts | 1423 | 1414 |
| ARC-AGI-2 | 40.1% | — |
| NYT Connections (extended) | — | 47.9% |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| Thematic Generalization | — | 45.5% |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 82.4% |
| LMCA | — | 34% |
| Epoch Capabilities Index | 150.15 | — |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Qwen3.5 27B: 38.8 (#127)
| Benchmark | Inkling-Small | Qwen3.5 27B |
|---|---|---|
| LMArena Math | 1459 | 1429 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | — | 56.7% |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Qwen3.5 27B: 38.0 (#150)
| Benchmark | Inkling-Small | Qwen3.5 27B |
|---|---|---|
| LMArena Expert | 1442 | 1428 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
| Vectara Hallucination Rate | — | 12.1% |
Multimodal Too close to call
Inkling-Small: 39.1 (#62), Qwen3.5 27B: 39.4 (#59)
| Benchmark | Inkling-Small | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | 1235 | 1241 |
Multilingual Too close to call
Inkling-Small: 51.7 (#104), Qwen3.5 27B: 50.8 (#115)
| Benchmark | Inkling-Small | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | 1402 | 1390 |
| LMArena Chinese | 1465 | 1478 |
| LMArena French | 1436 | 1410 |
| LMArena German | 1405 | 1393 |
| LMArena Japanese | 1405 | 1345 |
| LMArena Korean | 1363 | 1358 |
| LMArena Russian | 1391 | 1390 |
| LMArena Spanish | 1428 | 1407 |
Instruction Following Too close to call
Inkling-Small: 73.8 (#114), Qwen3.5 27B: 73.5 (#119)
| Benchmark | Inkling-Small | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | 1399 | 1393 |
Long Context Too close to call
Inkling-Small: 42.7 (#118), Qwen3.5 27B: 43.1 (#106)
| Benchmark | Inkling-Small | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | 1401 | 1413 |
Writing & Preference Too close to call
Inkling-Small: 59.6 (#107), Qwen3.5 27B: 59.3 (#111)
| Benchmark | Inkling-Small | Qwen3.5 27B |
|---|---|---|
| LMArena Text | 1414 | 1409 |
| LMArena Creative Writing | 1331 | 1362 |
| LMArena Multi-Turn | 1418 | 1410 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Qwen3.5 27B?
Inkling-Small is the stronger model overall, scoring 46.5 to 41.9 on the Noometry Index.
Which is cheaper, Inkling-Small or Qwen3.5 27B?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Qwen3.5 27B lists at $0.30 and $2.40.
Is Inkling-Small or Qwen3.5 27B better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 262K.
How many benchmarks do Inkling-Small and Qwen3.5 27B share?
19 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen3.5 27B has 28.