Model comparison
Inkling vs Qwen3-4B
Inkling is the stronger model overall, scoring 44.1 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 scores higher in 4 categories and Qwen3-4B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 33.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Inkling and 52.2% for Qwen3-4B.
Side by side
| Inkling | Qwen3-4B | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 44.1 | 31.9 |
| Released | 2026-07-15 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 66K | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.87 | — |
| Output $ / M tokens | $4.68 | — |
| Results tracked | 41 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Inkling: 34.5 (#234), Qwen3-4B: —
| Benchmark | Inkling | Qwen3-4B |
|---|---|---|
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| LMArena Coding | 1464 | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Inkling leads
Inkling: 29.6 (#85), Qwen3-4B: 27.6 (#100)
| Benchmark | Inkling | Qwen3-4B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| Berkeley Function Calling Leaderboard | — | 35.7% |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Qwen3-4B: 19.2 (#268)
| Benchmark | Inkling | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 21% | 4% |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| LMArena Hard Prompts | 1451 | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.54 | — |
Math Inkling leads
Inkling: 31.3 (#225), Qwen3-4B: 29.7 (#240)
| Benchmark | Inkling | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 52.2% |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| MathArena Final-Answer Competitions | — | 38.5% |
| ProofBench | 0% | — |
| LMArena Math | 1479 | — |
Knowledge Inkling leads
Inkling: 55.1 (#49), Qwen3-4B: 33.0 (#208)
| Benchmark | Inkling | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 88.3% | 52.3% |
| SimpleQA Verified | 40.3% | — |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1465 | — |
Multilingual Not comparable
Inkling: 54.0 (#52), Qwen3-4B: —
| Benchmark | Inkling | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1434 | — |
| LMArena Chinese | 1490 | — |
| LMArena French | 1458 | — |
| LMArena German | 1446 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1404 | — |
| LMArena Russian | 1429 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Not comparable
Inkling: 75.1 (#71), Qwen3-4B: —
| Benchmark | Inkling | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1426 | — |
Long Context Not comparable
Inkling: 43.8 (#86), Qwen3-4B: —
| Benchmark | Inkling | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1434 | — |
Writing & Preference Not comparable
Inkling: 65.2 (#51), Qwen3-4B: —
| Benchmark | Inkling | Qwen3-4B |
|---|---|---|
| LMArena Text | 1441 | — |
| LMArena Creative Writing | 1387 | — |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LMArena Multi-Turn | 1436 | — |
Frequently asked questions
Is Inkling better than Qwen3-4B?
Inkling is the stronger model overall, scoring 44.1 to 31.9 on the Noometry Index.
How many benchmarks do Inkling and Qwen3-4B share?
3 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Qwen3-4B has 6.