Model comparison
Gemma 3 4B vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 28.1 on the Noometry Index. Gemma 3 4B costs 4.3× less per token, which makes it the better buy when Qwen3-30B-A3B's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Gemma 3 4B scores higher in 1 category and Qwen3-30B-A3B in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-30B-A3B leads 41.8 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 70.3% for Qwen3-30B-A3B.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.12 / $0.50 for Qwen3-30B-A3B.
- Gemma 3 4B accepts more context: 131K tokens versus 41K.
Side by side
| Gemma 3 4B | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 28.1 | 38.9 |
| Released | 2025-03-12 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 131K | 41K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.04 | $0.12 |
| Output $ / M tokens | $0.08 | $0.50 |
| Results tracked | 22 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Gemma 3 4B: 35.9 (#215), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Gemma 3 4B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1230 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
Agentic & Tool Use Qwen3-30B-A3B leads
Gemma 3 4B: 20.9 (#142), Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Gemma 3 4B | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | 41.4% |
Reasoning Qwen3-30B-A3B leads
Gemma 3 4B: 13.2 (#335), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Gemma 3 4B | Qwen3-30B-A3B |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | 54.9% |
| Chess Puzzles | 0% | 8% |
| LMArena Hard Prompts | 1253 | 1398 |
| DTBench | 50.9% | 69.3% |
| LMCA | 2.8% | 22.4% |
| Epoch Capabilities Index | 116.02 | 139.63 |
| CritPt | — | 0.3% |
Math Qwen3-30B-A3B leads
Gemma 3 4B: 16.8 (#292), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Gemma 3 4B | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 70.3% |
| LMArena Math | 1239 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
Knowledge Qwen3-30B-A3B leads
Gemma 3 4B: 11.8 (#299), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Gemma 3 4B | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 23.2% | 70.1% |
| LMArena Expert | 1223 | 1396 |
| Confabulations | — | 12.3% |
| Vectara Hallucination Rate | 6.4% | — |
Multilingual Qwen3-30B-A3B leads
Gemma 3 4B: 42.5 (#194), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Gemma 3 4B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1273 | 1372 |
| LMArena German | 1281 | 1380 |
| LMArena Russian | 1294 | 1370 |
| LMArena Chinese | — | 1433 |
| LMArena French | — | 1418 |
| LMArena Japanese | — | 1337 |
| LMArena Korean | — | 1331 |
| LMArena Spanish | — | 1404 |
Instruction Following Qwen3-30B-A3B leads
Gemma 3 4B: 65.2 (#225), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Gemma 3 4B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1239 | 1363 |
Long Context Gemma 3 4B leads
Gemma 3 4B: 38.7 (#194), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Gemma 3 4B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1273 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
Gemma 3 4B: 42.0 (#239), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Gemma 3 4B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1291 | 1384 |
| LMArena Creative Writing | 1271 | 1317 |
| LMArena Multi-Turn | 1255 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 28.1 on the Noometry Index. Gemma 3 4B costs 4.3× less per token, which makes it the better buy when Qwen3-30B-A3B's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 4B or Qwen3-30B-A3B?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Qwen3-30B-A3B lists at $0.12 and $0.50.
Is Gemma 3 4B or Qwen3-30B-A3B better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
Gemma 3 4B does, with 131K tokens against 41K.
How many benchmarks do Gemma 3 4B and Qwen3-30B-A3B share?
20 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Qwen3-30B-A3B has 32.