Model comparison
Inkling vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 44.1 on the Noometry Index.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. Inkling scores higher in 4 categories and Qwen3.6 Plus in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Plus leads 51.8 to 31.3.
- The biggest single-benchmark swing is SciCode: 47% for Inkling and 40.7% for Qwen3.6 Plus.
- Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Qwen3.6 Plus accepts more context: 1M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Inkling | Qwen3.6 Plus | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 44.1 | 47.5 |
| Released | 2026-07-15 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 66K | 1M |
| Max output | 66K | 66K |
| Input $ / M tokens | $1.87 | $0.50 |
| Output $ / M tokens | $4.68 | $3 |
| Results tracked | 41 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Plus leads
Inkling: 34.5 (#234), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | Inkling | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1413 | 1461 |
| SciCode | 47% | 40.7% |
| LMArena Coding | 1464 | 1467 |
| ALE-Bench | 946 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Qwen3.6 Plus: —
| Benchmark | Inkling | Qwen3.6 Plus |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
| Vending-Bench 2 | — | 5,115 |
Reasoning Inkling leads
Inkling: 40.4 (#56), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | Inkling | Qwen3.6 Plus |
|---|---|---|
| CritPt | 5.4% | 2.9% |
| Chess Puzzles | 21% | 17% |
| LMArena Hard Prompts | 1451 | 1449 |
| DTBench | 87.5% | 81.9% |
| LMCA | 37.6% | 33.1% |
| Epoch Capabilities Index | 148.54 | 147.65 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| NYT Connections (extended) | — | 60.3% |
| ARC-AGI-1 | 79.5% | — |
| Thematic Generalization | — | 59.5% |
| Mystery Game Puzzles | — | 12% |
Math Qwen3.6 Plus leads
Inkling: 31.3 (#225), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | Inkling | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 33.3% | 38.2% |
| OTIS Mock AIME 2024-2025 | 88.9% | 93.3% |
| LMArena Math | 1479 | 1450 |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 0% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Too close to call
Inkling: 55.1 (#49), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | Inkling | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 88.3% | 88.4% |
| SimpleQA Verified | 40.3% | 44.1% |
| LMArena Expert | 1465 | 1454 |
Multilingual Too close to call
Inkling: 54.0 (#52), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | Inkling | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1434 | 1424 |
| LMArena Chinese | 1490 | 1477 |
| LMArena French | 1458 | 1455 |
| LMArena German | 1446 | 1452 |
| LMArena Japanese | 1429 | 1389 |
| LMArena Korean | 1404 | 1379 |
| LMArena Russian | 1429 | 1434 |
| LMArena Spanish | 1448 | 1432 |
Instruction Following Too close to call
Inkling: 75.1 (#71), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | Inkling | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1426 | 1425 |
Long Context Qwen3.6 Plus leads
Inkling: 43.8 (#86), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | Inkling | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1434 | 1439 |
| CL-bench | — | 20.3% |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | Inkling | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1441 | 1437 |
| LMArena Creative Writing | 1387 | 1404 |
| LMArena Multi-Turn | 1436 | 1438 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 44.1 on the Noometry Index.
Which is cheaper, Inkling or Qwen3.6 Plus?
Qwen3.6 Plus is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Qwen3.6 Plus better for coding?
Qwen3.6 Plus scores higher on coding benchmarks: 40.8 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 66K.
How many benchmarks do Inkling and Qwen3.6 Plus share?
29 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Qwen3.6 Plus has 37.