Model comparison
Qwen3-30B-A3B vs Qwen3-4B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 31.9 on the Noometry Index.
Last verified . 5 shared benchmarks.
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. Qwen3-30B-A3B 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 Qwen3-30B-A3B leads 41.8 to 33.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 70.3% for Qwen3-30B-A3B and 52.2% for Qwen3-4B.
Side by side
| Qwen3-30B-A3B | Qwen3-4B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 38.9 | 31.9 |
| Released | 2025-04-28 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 41K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.12 | — |
| Output $ / M tokens | $0.50 | — |
| Results tracked | 32 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen3-30B-A3B: 37.5 (#194), Qwen3-4B: —
| Benchmark | Qwen3-30B-A3B | Qwen3-4B |
|---|---|---|
| SciCode | 33.3% | — |
| WeirdML | 29.8% | — |
| LMArena Coding | 1416 | — |
Agentic & Tool Use Qwen3-30B-A3B leads
Qwen3-30B-A3B: 29.8 (#82), Qwen3-4B: 27.6 (#100)
| Benchmark | Qwen3-30B-A3B | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41.4% | 35.7% |
Reasoning Qwen3-30B-A3B leads
Qwen3-30B-A3B: 22.2 (#204), Qwen3-4B: 19.2 (#268)
| Benchmark | Qwen3-30B-A3B | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 8% | 4% |
| Kagi LLM Benchmark | 54.9% | — |
| CritPt | 0.3% | — |
| LMArena Hard Prompts | 1398 | — |
| DTBench | 69.3% | — |
| LMCA | 22.4% | — |
| Epoch Capabilities Index | 139.63 | — |
Math Qwen3-30B-A3B leads
Qwen3-30B-A3B: 37.4 (#157), Qwen3-4B: 29.7 (#240)
| Benchmark | Qwen3-30B-A3B | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | 47.8% | 38.5% |
| OTIS Mock AIME 2024-2025 | 70.3% | 52.2% |
| LMArena Math | 1394 | — |
Knowledge Qwen3-30B-A3B leads
Qwen3-30B-A3B: 41.8 (#105), Qwen3-4B: 33.0 (#208)
| Benchmark | Qwen3-30B-A3B | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 70.1% | 52.3% |
| Confabulations | 12.3% | — |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1396 | — |
Multilingual Not comparable
Qwen3-30B-A3B: 49.5 (#132), Qwen3-4B: —
| Benchmark | Qwen3-30B-A3B | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1372 | — |
| LMArena Chinese | 1433 | — |
| LMArena French | 1418 | — |
| LMArena German | 1380 | — |
| LMArena Japanese | 1337 | — |
| LMArena Korean | 1331 | — |
| LMArena Russian | 1370 | — |
| LMArena Spanish | 1404 | — |
Instruction Following Not comparable
Qwen3-30B-A3B: 72.0 (#142), Qwen3-4B: —
| Benchmark | Qwen3-30B-A3B | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1363 | — |
Long Context Not comparable
Qwen3-30B-A3B: 31.0 (#283), Qwen3-4B: —
| Benchmark | Qwen3-30B-A3B | Qwen3-4B |
|---|---|---|
| Fiction.LiveBench | 40.6% | — |
| LMArena Longer Query | 1379 | — |
Writing & Preference Not comparable
Qwen3-30B-A3B: 55.6 (#143), Qwen3-4B: —
| Benchmark | Qwen3-30B-A3B | Qwen3-4B |
|---|---|---|
| LMArena Text | 1384 | — |
| LMArena Creative Writing | 1317 | — |
| Short-Story Creative Writing | 75.3% | — |
| LMArena Multi-Turn | 1378 | — |
Frequently asked questions
Is Qwen3-30B-A3B better than Qwen3-4B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 31.9 on the Noometry Index.
How many benchmarks do Qwen3-30B-A3B and Qwen3-4B share?
5 benchmarks have published results for both models. Qwen3-30B-A3B has 32 scored results on Noometry and Qwen3-4B has 6.