Model comparison
Inkling-Small vs Qwen3.7 Plus
Inkling-Small is the stronger model overall, scoring 46.5 to 45.3 on the Noometry Index.
Last verified . 26 shared benchmarks.
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. Inkling-Small scores higher in 1 category and Qwen3.7 Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Inkling-Small leads 43.6 to 36.6.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 46.3% for Inkling-Small and 34.4% for Qwen3.7 Plus.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 Plus accepts more context: 1M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Inkling-Small | Qwen3.7 Plus | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 45.3 |
| Released | 2026-07-15 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 524K | 1M |
| Max output | 1.05M | 131K |
| Input $ / M tokens | $0.45 | $0.40 |
| Output $ / M tokens | $1.20 | $1.60 |
| 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), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | Inkling-Small | Qwen3.7 Plus |
|---|---|---|
| SciCode | 48.7% | 45.5% |
| LMArena Coding | 1451 | 1473 |
| FrontierCode | — | 10.2% |
| LMArena WebDev | 1409 | — |
Agentic & Tool Use Not comparable
Inkling-Small: —, Qwen3.7 Plus: 21.4 (#138)
| Benchmark | Inkling-Small | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
Reasoning Too close to call
Inkling-Small: 38.6 (#63), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | Inkling-Small | Qwen3.7 Plus |
|---|---|---|
| CritPt | 8.3% | 9.1% |
| Chess Puzzles | 18% | 24% |
| LMArena Hard Prompts | 1423 | 1460 |
| Mystery Game Puzzles | 6% | 17% |
| Epoch Capabilities Index | 150.15 | 147.37 |
| ARC-AGI-2 | 40.1% | — |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | 84% | — |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
Math Qwen3.7 Plus leads
Inkling-Small: 45.1 (#77), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | Inkling-Small | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | 34.4% |
| OTIS Mock AIME 2024-2025 | 90% | 93.3% |
| LMArena Math | 1459 | 1466 |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
Knowledge Qwen3.7 Plus leads
Inkling-Small: 48.2 (#77), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | Inkling-Small | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 88.5% | 87.9% |
| LMArena Expert | 1442 | 1467 |
| SimpleQA Verified | 19.1% | — |
Multimodal Qwen3.7 Plus leads
Inkling-Small: 39.1 (#62), Qwen3.7 Plus: 41.8 (#33)
| Benchmark | Inkling-Small | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1235 | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
Inkling-Small: 51.7 (#104), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | Inkling-Small | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1402 | 1445 |
| LMArena Chinese | 1465 | 1510 |
| LMArena French | 1436 | 1473 |
| LMArena German | 1405 | 1471 |
| LMArena Japanese | 1405 | 1413 |
| LMArena Korean | 1363 | 1415 |
| LMArena Russian | 1391 | 1457 |
| LMArena Spanish | 1428 | 1457 |
Instruction Following Qwen3.7 Plus leads
Inkling-Small: 73.8 (#114), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | Inkling-Small | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1399 | 1440 |
Long Context Qwen3.7 Plus leads
Inkling-Small: 42.7 (#118), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | Inkling-Small | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1401 | 1455 |
Writing & Preference Qwen3.7 Plus leads
Inkling-Small: 59.6 (#107), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | Inkling-Small | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1414 | 1455 |
| LMArena Creative Writing | 1331 | 1439 |
| LMArena Multi-Turn | 1418 | 1460 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Qwen3.7 Plus?
Inkling-Small is the stronger model overall, scoring 46.5 to 45.3 on the Noometry Index.
Which is cheaper, Inkling-Small or Qwen3.7 Plus?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is Inkling-Small or Qwen3.7 Plus better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 36.6 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 524K.
How many benchmarks do Inkling-Small and Qwen3.7 Plus share?
26 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen3.7 Plus has 32.