Model comparison
Inkling-Small vs Qwen3-4B
Inkling-Small is the stronger model overall, scoring 46.5 to 31.9 on the Noometry Index.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Inkling-Small scores higher in 3 categories and Qwen3-4B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 19.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 90% for Inkling-Small and 52.2% for Qwen3-4B.
Side by side
| Inkling-Small | Qwen3-4B | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 46.5 | 31.9 |
| Released | 2026-07-15 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 524K | — |
| Max output | 1.05M | — |
| Input $ / M tokens | $0.45 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Inkling-Small: 43.6 (#85), Qwen3-4B: —
| Benchmark | Inkling-Small | Qwen3-4B |
|---|---|---|
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
| LMArena Coding | 1451 | — |
Agentic & Tool Use Not comparable
Inkling-Small: —, Qwen3-4B: 27.6 (#100)
| Benchmark | Inkling-Small | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Qwen3-4B: 19.2 (#268)
| Benchmark | Inkling-Small | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 18% | 4% |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| LMArena Hard Prompts | 1423 | — |
| Mystery Game Puzzles | 6% | — |
| Epoch Capabilities Index | 150.15 | — |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Qwen3-4B: 29.7 (#240)
| Benchmark | Inkling-Small | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 52.2% |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | — | 38.5% |
| ProofBench | 6% | — |
| LMArena Math | 1459 | — |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Qwen3-4B: 33.0 (#208)
| Benchmark | Inkling-Small | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 88.5% | 52.3% |
| SimpleQA Verified | 19.1% | — |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1442 | — |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), Qwen3-4B: —
| Benchmark | Inkling-Small | Qwen3-4B |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Not comparable
Inkling-Small: 51.7 (#104), Qwen3-4B: —
| Benchmark | Inkling-Small | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1402 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1436 | — |
| LMArena German | 1405 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1363 | — |
| LMArena Russian | 1391 | — |
| LMArena Spanish | 1428 | — |
Instruction Following Not comparable
Inkling-Small: 73.8 (#114), Qwen3-4B: —
| Benchmark | Inkling-Small | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1399 | — |
Long Context Not comparable
Inkling-Small: 42.7 (#118), Qwen3-4B: —
| Benchmark | Inkling-Small | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1401 | — |
Writing & Preference Not comparable
Inkling-Small: 59.6 (#107), Qwen3-4B: —
| Benchmark | Inkling-Small | Qwen3-4B |
|---|---|---|
| LMArena Text | 1414 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1491 | — |
| LMArena Multi-Turn | 1418 | — |
Frequently asked questions
Is Inkling-Small better than Qwen3-4B?
Inkling-Small is the stronger model overall, scoring 46.5 to 31.9 on the Noometry Index.
How many benchmarks do Inkling-Small and Qwen3-4B share?
3 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Qwen3-4B has 6.