Model comparison
Inkling vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 44.1 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Inkling scores higher in 1 category and Qwen3.6 Max Preview in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Max Preview leads 54.1 to 31.3.
- The biggest single-benchmark swing is SimpleBench: 50% for Inkling and 63% for Qwen3.6 Max Preview.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview accepts more context: 262K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Inkling | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 44.1 | 51.5 |
| Released | 2026-07-15 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 66K | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $1.87 | $1.30 |
| Output $ / M tokens | $4.68 | $7.80 |
| Results tracked | 41 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Inkling: 34.5 (#234), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | Inkling | Qwen3.6 Max Preview |
|---|---|---|
| LMArena WebDev | 1413 | 1482 |
| LMArena Coding | 1464 | 1471 |
| SWE-bench Verified | — | 76.7% |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Qwen3.6 Max Preview: —
| Benchmark | Inkling | Qwen3.6 Max Preview |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Inkling: 40.4 (#56), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | Inkling | Qwen3.6 Max Preview |
|---|---|---|
| SimpleBench | 50% | 63% |
| Chess Puzzles | 21% | 20% |
| LMArena Hard Prompts | 1451 | 1457 |
| DTBench | 87.5% | 87.2% |
| LMCA | 37.6% | 42.5% |
| Epoch Capabilities Index | 148.54 | 149.24 |
| ARC-AGI-2 | 36.5% | — |
| NYT Connections (extended) | — | 74.1% |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Mystery Game Puzzles | — | 19% |
Math Qwen3.6 Max Preview leads
Inkling: 31.3 (#225), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | Inkling | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 91.1% |
| LMArena Math | 1479 | 1465 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 0% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Inkling: 55.1 (#49), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | Inkling | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 88.3% | 87.4% |
| SimpleQA Verified | 40.3% | 52% |
| LMArena Expert | 1465 | 1478 |
Multilingual Too close to call
Inkling: 54.0 (#52), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | Inkling | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1434 | 1437 |
| LMArena Chinese | 1490 | 1487 |
| LMArena French | 1458 | 1449 |
| LMArena Russian | 1429 | 1445 |
| LMArena Spanish | 1448 | 1454 |
| LMArena German | 1446 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1404 | — |
Instruction Following Too close to call
Inkling: 75.1 (#71), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | Inkling | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1426 | 1438 |
Long Context Too close to call
Inkling: 43.8 (#86), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | Inkling | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1434 | 1457 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | Inkling | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1441 | 1447 |
| LMArena Creative Writing | 1387 | 1435 |
| LMArena Multi-Turn | 1436 | 1456 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 44.1 on the Noometry Index.
Which is cheaper, Inkling or Qwen3.6 Max Preview?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Inkling or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Max Preview does, with 262K tokens against 66K.
How many benchmarks do Inkling and Qwen3.6 Max Preview share?
23 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Qwen3.6 Max Preview has 29.