Model comparison
Inkling-Small vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 46.5 on the Noometry Index. Inkling-Small costs 1.8× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. Inkling-Small scores higher in 2 categories and Qwen3.6 Plus in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 29.3.
- The biggest single-benchmark swing is SimpleQA Verified: 19.1% for Inkling-Small and 44.1% for Qwen3.6 Plus.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus 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 Plus | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 47.5 |
| Released | 2026-07-15 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 524K | 1M |
| Max output | 1.05M | 66K |
| Input $ / M tokens | $0.45 | $0.50 |
| Output $ / M tokens | $1.20 | $3 |
| Results tracked | 33 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.6 (#85), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | Inkling-Small | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1409 | 1461 |
| SciCode | 48.7% | 40.7% |
| LMArena Coding | 1451 | 1467 |
| SWE-bench Verified | — | 57.9% |
| ALE-Bench | — | 670.15 |
Agentic & Tool Use Not comparable
Inkling-Small: —, Qwen3.6 Plus: —
| Benchmark | Inkling-Small | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | — | 5,115 |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | Inkling-Small | Qwen3.6 Plus |
|---|---|---|
| CritPt | 8.3% | 2.9% |
| Chess Puzzles | 18% | 17% |
| LMArena Hard Prompts | 1423 | 1449 |
| Mystery Game Puzzles | 6% | 12% |
| Epoch Capabilities Index | 150.15 | 147.65 |
| ARC-AGI-2 | 40.1% | — |
| NYT Connections (extended) | — | 60.3% |
| ARC-AGI-1 | 84% | — |
| Thematic Generalization | — | 59.5% |
| DTBench | — | 81.9% |
| LMCA | — | 33.1% |
Math Qwen3.6 Plus leads
Inkling-Small: 45.1 (#77), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | Inkling-Small | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | 38.2% |
| OTIS Mock AIME 2024-2025 | 90% | 93.3% |
| LMArena Math | 1459 | 1450 |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
Inkling-Small: 48.2 (#77), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | Inkling-Small | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 88.5% | 88.4% |
| SimpleQA Verified | 19.1% | 44.1% |
| LMArena Expert | 1442 | 1454 |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), Qwen3.6 Plus: —
| Benchmark | Inkling-Small | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Qwen3.6 Plus leads
Inkling-Small: 51.7 (#104), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | Inkling-Small | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1402 | 1424 |
| LMArena Chinese | 1465 | 1477 |
| LMArena French | 1436 | 1455 |
| LMArena German | 1405 | 1452 |
| LMArena Japanese | 1405 | 1389 |
| LMArena Korean | 1363 | 1379 |
| LMArena Russian | 1391 | 1434 |
| LMArena Spanish | 1428 | 1432 |
Instruction Following Qwen3.6 Plus leads
Inkling-Small: 73.8 (#114), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | Inkling-Small | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1399 | 1425 |
Long Context Qwen3.6 Plus leads
Inkling-Small: 42.7 (#118), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | Inkling-Small | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1401 | 1439 |
| CL-bench | — | 20.3% |
Writing & Preference Qwen3.6 Plus leads
Inkling-Small: 59.6 (#107), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | Inkling-Small | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1414 | 1437 |
| LMArena Creative Writing | 1331 | 1404 |
| LMArena Multi-Turn | 1418 | 1438 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 46.5 on the Noometry Index. Inkling-Small costs 1.8× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or Qwen3.6 Plus?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is Inkling-Small or Qwen3.6 Plus better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 524K.
How many benchmarks do Inkling-Small and Qwen3.6 Plus share?
27 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen3.6 Plus has 37.