Model comparison
Inkling-Small vs Qwen3.5 122B-A10B
Inkling-Small is the stronger model overall, scoring 46.5 to 41.6 on the Noometry Index.
Last verified . 22 shared benchmarks.
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Inkling-Small scores higher in 4 categories and Qwen3.5 122B-A10B in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 39.0 to 26.4.
- The biggest single-benchmark swing is SciCode: 48.7% for Inkling-Small and 35.6% for Qwen3.5 122B-A10B.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
- Inkling-Small accepts more context: 524K tokens versus 262K.
Side by side
| Inkling-Small | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 41.6 |
| Released | 2026-07-15 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 524K | 262K |
| Max output | 1.05M | 66K |
| Input $ / M tokens | $0.45 | $0.40 |
| Output $ / M tokens | $1.20 | $3.20 |
| Results tracked | 33 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.3 (#80), Qwen3.5 122B-A10B: 38.8 (#155)
| Benchmark | Inkling-Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena WebDev | 1408 | 1360 |
| SciCode | 48.7% | 35.6% |
| LMArena Coding | 1451 | 1436 |
Reasoning Inkling-Small leads
Inkling-Small: 39.0 (#53), Qwen3.5 122B-A10B: 26.4 (#121)
| Benchmark | Inkling-Small | Qwen3.5 122B-A10B |
|---|---|---|
| CritPt | 8.3% | 0.9% |
| LMArena Hard Prompts | 1424 | 1421 |
| Mystery Game Puzzles | 6% | 17% |
| ARC-AGI-2 | 40.1% | — |
| NYT Connections (extended) | — | 51.7% |
| ARC-AGI-1 | 84% | — |
| Chess Puzzles | 18% | — |
| Thematic Generalization | — | 51.2% |
| DTBench | — | 84.3% |
| LMCA | — | 32.2% |
| Epoch Capabilities Index | 150.13 | — |
Math Inkling-Small leads
Inkling-Small: 44.9 (#65), Qwen3.5 122B-A10B: 36.4 (#114)
| Benchmark | Inkling-Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1453 | 1432 |
| 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), Qwen3.5 122B-A10B: 38.2 (#138)
| Benchmark | Inkling-Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Expert | 1442 | 1431 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
| Vectara Hallucination Rate | — | 11.2% |
Multimodal Too close to call
Inkling-Small: 38.4 (#59), Qwen3.5 122B-A10B: 39.0 (#52)
| Benchmark | Inkling-Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | 1235 | 1245 |
Multilingual Too close to call
Inkling-Small: 51.7 (#102), Qwen3.5 122B-A10B: 51.8 (#101)
| Benchmark | Inkling-Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1400 | 1400 |
| LMArena Chinese | 1458 | 1462 |
| LMArena French | 1438 | 1442 |
| LMArena German | 1412 | 1425 |
| LMArena Japanese | 1399 | 1364 |
| LMArena Korean | 1355 | 1353 |
| LMArena Russian | 1392 | 1400 |
| LMArena Spanish | 1426 | 1423 |
Instruction Following Too close to call
Inkling-Small: 73.9 (#112), Qwen3.5 122B-A10B: 74.0 (#109)
| Benchmark | Inkling-Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1397 | 1399 |
Long Context Too close to call
Inkling-Small: 42.7 (#113), Qwen3.5 122B-A10B: 43.0 (#105)
| Benchmark | Inkling-Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1401 | 1410 |
Writing & Preference Too close to call
Inkling-Small: 59.8 (#102), Qwen3.5 122B-A10B: 60.2 (#98)
| Benchmark | Inkling-Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1413 | 1417 |
| LMArena Creative Writing | 1330 | 1369 |
| LMArena Multi-Turn | 1420 | 1416 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Qwen3.5 122B-A10B?
Inkling-Small is the stronger model overall, scoring 46.5 to 41.6 on the Noometry Index.
Which is cheaper, Inkling-Small or Qwen3.5 122B-A10B?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.
Is Inkling-Small or Qwen3.5 122B-A10B better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 38.8 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 262K.
How many benchmarks do Inkling-Small and Qwen3.5 122B-A10B share?
22 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen3.5 122B-A10B has 27.