Model comparison
Inkling-Small vs Qwen2.5-Coder-32B
Inkling-Small is the stronger model overall, scoring 46.5 to 33.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Inkling-Small leads 43.6 to 22.6.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- Inkling-Small accepts more context: 524K tokens versus 33K.
Side by side
| Inkling-Small | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 33.4 |
| Released | 2026-07-15 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 524K | 33K |
| Max output | 1.05M | 29K |
| Input $ / M tokens | $0.45 | $0.66 |
| Output $ / M tokens | $1.20 | $1 |
| Results tracked | 33 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.6 (#85), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Inkling-Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1451 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Inkling-Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1423 | 1251 |
| Epoch Capabilities Index | 150.15 | 119.49 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| LiveBench Reasoning | — | 42.1% |
| Mystery Game Puzzles | 6% | — |
| LiveBench Data Analysis | — | 49.9% |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Inkling-Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1459 | 1251 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Inkling-Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1442 | 1221 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), Qwen2.5-Coder-32B: —
| Benchmark | Inkling-Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#104), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Inkling-Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1402 | 1205 |
| LMArena Chinese | 1465 | 1222 |
| LMArena Russian | 1391 | 1228 |
| LMArena French | 1436 | — |
| LMArena German | 1405 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1363 | — |
| LMArena Spanish | 1428 | — |
Instruction Following Inkling-Small leads
Inkling-Small: 73.8 (#114), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Inkling-Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1399 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#118), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Inkling-Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1401 | 1251 |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.6 (#107), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Inkling-Small | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1414 | 1230 |
| LMArena Creative Writing | 1331 | 1174 |
| LMArena Multi-Turn | 1418 | 1222 |
| EQ-Bench Creative Writing | 1491 | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Inkling-Small better than Qwen2.5-Coder-32B?
Inkling-Small is the stronger model overall, scoring 46.5 to 33.4 on the Noometry Index.
Which is cheaper, Inkling-Small or Qwen2.5-Coder-32B?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.
Is Inkling-Small or Qwen2.5-Coder-32B better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 33K.
How many benchmarks do Inkling-Small and Qwen2.5-Coder-32B share?
13 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen2.5-Coder-32B has 31.