Model comparison
Inkling-Small vs Qwen3.5-Flash
Inkling-Small is the stronger model overall, scoring 46.5 to 42.5 on the Noometry Index. Qwen3.5-Flash costs 3.6× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Qwen3.5-Flash in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Inkling-Small leads 43.6 to 34.2.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 46.3% for Inkling-Small and 18.2% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Qwen3.5-Flash accepts more context: 1M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Inkling-Small | Qwen3.5-Flash | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 42.5 |
| Released | 2026-07-15 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 524K | 1M |
| Max output | 1.05M | 66K |
| Input $ / M tokens | $0.45 | $0.10 |
| Output $ / M tokens | $1.20 | $0.40 |
| Results tracked | 33 | 32 |
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-Flash: 34.2 (#242)
| Benchmark | Inkling-Small | Qwen3.5-Flash |
|---|---|---|
| LMArena WebDev | 1409 | 1244 |
| LMArena Coding | 1451 | 1412 |
| SciCode | 48.7% | — |
| ALE-Bench | — | 221.8 |
Agentic & Tool Use Not comparable
Inkling-Small: —, Qwen3.5-Flash: —
| Benchmark | Inkling-Small | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | — | 462.69 |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | Inkling-Small | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 18% | 21% |
| LMArena Hard Prompts | 1423 | 1403 |
| Mystery Game Puzzles | 6% | 20% |
| Epoch Capabilities Index | 150.15 | 143.98 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| DTBench | — | 82.9% |
| LMCA | — | 29.1% |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | Inkling-Small | Qwen3.5-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | 18.2% |
| OTIS Mock AIME 2024-2025 | 90% | 84.4% |
| LMArena Math | 1459 | 1407 |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | Inkling-Small | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 88.5% | 82.3% |
| SimpleQA Verified | 19.1% | 20.3% |
| LMArena Expert | 1442 | 1407 |
| Vectara Hallucination Rate | — | 10.5% |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), Qwen3.5-Flash: —
| Benchmark | Inkling-Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#104), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | Inkling-Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1402 | 1385 |
| LMArena Chinese | 1465 | 1446 |
| LMArena French | 1436 | 1412 |
| LMArena German | 1405 | 1390 |
| LMArena Japanese | 1405 | 1368 |
| LMArena Korean | 1363 | 1344 |
| LMArena Russian | 1391 | 1379 |
| LMArena Spanish | 1428 | 1400 |
Instruction Following Inkling-Small leads
Inkling-Small: 73.8 (#114), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | Inkling-Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1399 | 1374 |
Long Context Too close to call
Inkling-Small: 42.7 (#118), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | Inkling-Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1401 | 1392 |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.6 (#107), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | Inkling-Small | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1414 | 1397 |
| LMArena Creative Writing | 1331 | 1343 |
| LMArena Multi-Turn | 1418 | 1393 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Qwen3.5-Flash?
Inkling-Small is the stronger model overall, scoring 46.5 to 42.5 on the Noometry Index. Qwen3.5-Flash costs 3.6× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is Inkling-Small or Qwen3.5-Flash better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 524K.
How many benchmarks do Inkling-Small and Qwen3.5-Flash share?
25 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen3.5-Flash has 32.