Model comparison
Inkling-Small vs Qwen3.6 Flash
Inkling-Small is the stronger model overall, scoring 46.5 to 38.8 on the Noometry Index. Qwen3.6 Flash costs 1.5× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
Alibaba (Qwen)Summary
- They share 7 benchmarks with published results for both. Inkling-Small scores higher in 3 categories and Qwen3.6 Flash in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 29.0.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 46.3% for Inkling-Small and 22.5% for Qwen3.6 Flash.
- Qwen3.6 Flash is cheaper at $0.19 / $1.13 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Qwen3.6 Flash accepts more context: 1M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Inkling-Small | Qwen3.6 Flash | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 38.8 |
| Released | 2026-07-15 | 2026-04-27 |
| Weights | Open | Proprietary |
| Context window | 524K | 1M |
| Max output | 1.05M | 66K |
| Input $ / M tokens | $0.45 | $0.19 |
| Output $ / M tokens | $1.20 | $1.13 |
| Results tracked | 33 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Inkling-Small: 43.6 (#85), Qwen3.6 Flash: —
| Benchmark | Inkling-Small | Qwen3.6 Flash |
|---|---|---|
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
| LMArena Coding | 1451 | — |
| ALE-Bench | — | 326.4 |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Qwen3.6 Flash: 29.0 (#96)
| Benchmark | Inkling-Small | Qwen3.6 Flash |
|---|---|---|
| Chess Puzzles | 18% | 20% |
| Mystery Game Puzzles | 6% | 18% |
| Epoch Capabilities Index | 150.15 | 143.26 |
| ARC-AGI-2 | 40.1% | — |
| SimpleBench | — | 35.2% |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| LMArena Hard Prompts | 1423 | — |
| DTBench | — | 77.1% |
| LMCA | — | 31% |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Qwen3.6 Flash: 39.0 (#117)
| Benchmark | Inkling-Small | Qwen3.6 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | 22.5% |
| OTIS Mock AIME 2024-2025 | 90% | 84.4% |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| LMArena Math | 1459 | — |
| FrontierMath (Feb 2025 set) | — | 10.3% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Qwen3.6 Flash: 42.1 (#100)
| Benchmark | Inkling-Small | Qwen3.6 Flash |
|---|---|---|
| GPQA Diamond | 88.5% | 83.3% |
| SimpleQA Verified | 19.1% | 15.9% |
| LMArena Expert | 1442 | — |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), Qwen3.6 Flash: —
| Benchmark | Inkling-Small | Qwen3.6 Flash |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Not comparable
Inkling-Small: 51.7 (#104), Qwen3.6 Flash: —
| Benchmark | Inkling-Small | Qwen3.6 Flash |
|---|---|---|
| LMArena Non-English | 1402 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1436 | — |
| LMArena German | 1405 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1363 | — |
| LMArena Russian | 1391 | — |
| LMArena Spanish | 1428 | — |
Instruction Following Not comparable
Inkling-Small: 73.8 (#114), Qwen3.6 Flash: —
| Benchmark | Inkling-Small | Qwen3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1399 | — |
Long Context Not comparable
Inkling-Small: 42.7 (#118), Qwen3.6 Flash: —
| Benchmark | Inkling-Small | Qwen3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1401 | — |
Writing & Preference Not comparable
Inkling-Small: 59.6 (#107), Qwen3.6 Flash: —
| Benchmark | Inkling-Small | Qwen3.6 Flash |
|---|---|---|
| LMArena Text | 1414 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1491 | — |
| LMArena Multi-Turn | 1418 | — |
Frequently asked questions
Is Inkling-Small better than Qwen3.6 Flash?
Inkling-Small is the stronger model overall, scoring 46.5 to 38.8 on the Noometry Index. Qwen3.6 Flash costs 1.5× 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 Qwen3.6 Flash?
Qwen3.6 Flash is cheaper. It lists at $0.19 per million input tokens and $1.13 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Which has the bigger context window?
Qwen3.6 Flash does, with 1M tokens against 524K.
How many benchmarks do Inkling-Small and Qwen3.6 Flash share?
7 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen3.6 Flash has 13.