Model comparison
Gemma 3 4B vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 28.1 on the Noometry Index. Gemma 3 4B costs 24× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Qwen3 235B-A22B in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.6 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 86.7% for Qwen3 235B-A22B.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
Side by side
| Gemma 3 4B | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 28.1 | 43.5 |
| Released | 2025-03-12 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.04 | $0.70 |
| Output $ / M tokens | $0.08 | $2.80 |
| Results tracked | 22 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Gemma 3 4B: 35.9 (#215), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Gemma 3 4B | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1230 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
Agentic & Tool Use Qwen3 235B-A22B leads
Gemma 3 4B: 20.9 (#142), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Gemma 3 4B | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Qwen3 235B-A22B leads
Gemma 3 4B: 13.2 (#335), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Gemma 3 4B | Qwen3 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | 69.4% |
| Chess Puzzles | 0% | 12% |
| LMArena Hard Prompts | 1253 | 1433 |
| DTBench | 50.9% | 80.3% |
| LMCA | 2.8% | 29.3% |
| Epoch Capabilities Index | 116.02 | 143.85 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Mystery Game Puzzles | — | 9% |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
Gemma 3 4B: 16.8 (#292), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Gemma 3 4B | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 86.7% |
| LMArena Math | 1239 | 1432 |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Gemma 3 4B: 11.8 (#299), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Gemma 3 4B | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 23.2% | 80.1% |
| Vectara Hallucination Rate | 6.4% | 9.3% |
| LMArena Expert | 1223 | 1463 |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| GPQA (HELM) | — | 72.7% |
Multilingual Qwen3 235B-A22B leads
Gemma 3 4B: 42.5 (#194), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Gemma 3 4B | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1273 | 1409 |
| LMArena German | 1281 | 1433 |
| LMArena Russian | 1294 | 1411 |
| LMArena Chinese | — | 1481 |
| LMArena French | — | 1445 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1391 |
| LMArena Spanish | — | 1430 |
Instruction Following Qwen3 235B-A22B leads
Gemma 3 4B: 65.2 (#225), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Gemma 3 4B | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1239 | 1408 |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
Gemma 3 4B: 38.7 (#194), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Gemma 3 4B | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1273 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Gemma 3 4B: 42.0 (#239), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Gemma 3 4B | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1291 | 1419 |
| LMArena Creative Writing | 1271 | 1384 |
| EQ-Bench Creative Writing | 1068 | 1366 |
| LMArena Multi-Turn | 1255 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
Frequently asked questions
Is Gemma 3 4B better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 28.1 on the Noometry Index. Gemma 3 4B costs 24× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 4B or Qwen3 235B-A22B?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is Gemma 3 4B or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Gemma 3 4B and Qwen3 235B-A22B share?
22 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Qwen3 235B-A22B has 49.