Model comparison
Gemma 2B vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Qwen3-30B-A3B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3-30B-A3B leads 55.6 to 24.0.
Side by side
| Gemma 2B | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.6 | 38.9 |
| Released | 2024-02-21 | 2025-04-28 |
| Weights | Open | Open |
| Context window | — | 41K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.12 |
| Output $ / M tokens | — | $0.50 |
| Results tracked | 23 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Gemma 2B: 29.4 (#305), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Gemma 2B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1010 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Gemma 2B | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning Qwen3-30B-A3B leads
Gemma 2B: 18.8 (#275), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Gemma 2B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1398 |
| Epoch Capabilities Index | 94.2 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| BIG-Bench Hard | 35.2% | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Qwen3-30B-A3B leads
Gemma 2B: 30.0 (#239), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Gemma 2B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1009 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Gemma 2B | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
| LMArena Expert | — | 1396 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Qwen3-30B-A3B leads
Gemma 2B: 23.0 (#294), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Gemma 2B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 958 | 1372 |
| LMArena Chinese | 986 | 1433 |
| LMArena Russian | 937 | 1370 |
| LMArena French | — | 1418 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1337 |
| LMArena Korean | — | 1331 |
| LMArena Spanish | — | 1404 |
Instruction Following Qwen3-30B-A3B leads
Gemma 2B: 48.5 (#302), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Gemma 2B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 970 | 1363 |
Long Context Qwen3-30B-A3B leads
Gemma 2B: 29.9 (#291), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Gemma 2B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 981 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
Gemma 2B: 24.0 (#308), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Gemma 2B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1002 | 1384 |
| LMArena Creative Writing | 987 | 1317 |
| LMArena Multi-Turn | 945 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
Frequently asked questions
Is Gemma 2B better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 29.6 on the Noometry Index.
Is Gemma 2B or Qwen3-30B-A3B better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and Qwen3-30B-A3B share?
12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Qwen3-30B-A3B has 32.