Model comparison
Inkling-Small vs Qwen1.5-32B
Inkling-Small is the stronger model overall, scoring 46.5 to 30.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.3 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 88.5% for Inkling-Small and 30.7% for Qwen1.5-32B.
Side by side
| Inkling-Small | Qwen1.5-32B | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 30.0 |
| Released | 2026-07-15 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 524K | — |
| Max output | 1.05M | — |
| Input $ / M tokens | $0.45 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.3 (#80), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Inkling-Small | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1451 | 1155 |
| LMArena WebDev | 1408 | — |
| SciCode | 48.7% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning Inkling-Small leads
Inkling-Small: 39.0 (#53), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Inkling-Small | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1131 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| Mystery Game Puzzles | 6% | — |
| Epoch Capabilities Index | 150.13 | — |
Math Inkling-Small leads
Inkling-Small: 44.9 (#65), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Inkling-Small | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1453 | 1155 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
Knowledge Inkling-Small leads
Inkling-Small: 48.3 (#71), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Inkling-Small | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 88.5% | 30.7% |
| LMArena Expert | 1442 | 1126 |
| SimpleQA Verified | 19.1% | — |
| MMLU | — | 74.4% |
Multimodal Not comparable
Inkling-Small: 38.4 (#59), Qwen1.5-32B: —
| Benchmark | Inkling-Small | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#102), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Inkling-Small | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1400 | 1106 |
| LMArena Chinese | 1458 | 1176 |
| LMArena French | 1438 | 1100 |
| LMArena German | 1412 | 1058 |
| LMArena Japanese | 1399 | 1027 |
| LMArena Korean | 1355 | 1007 |
| LMArena Russian | 1392 | 1073 |
| LMArena Spanish | 1426 | 1089 |
Instruction Following Inkling-Small leads
Inkling-Small: 73.9 (#112), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Inkling-Small | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1397 | 1116 |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#113), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Inkling-Small | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1401 | 1146 |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.8 (#102), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Inkling-Small | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1413 | 1137 |
| LMArena Creative Writing | 1330 | 1083 |
| LMArena Multi-Turn | 1420 | 1140 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Qwen1.5-32B?
Inkling-Small is the stronger model overall, scoring 46.5 to 30.0 on the Noometry Index.
Is Inkling-Small or Qwen1.5-32B better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 31.1 in the Noometry coding category.
How many benchmarks do Inkling-Small and Qwen1.5-32B share?
18 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen1.5-32B has 21.