Model comparison
Gemma 3 4B vs Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 14× less per token, which makes it the better buy when Qwen3.5 35B-A3B's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Gemma 3 4B scores higher in 1 category and Qwen3.5 35B-A3B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.8 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 70% for Qwen3.5 35B-A3B.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.25 / $2 for Qwen3.5 35B-A3B.
- Qwen3.5 35B-A3B accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 3 4B | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 28.1 | 42.0 |
| Released | 2025-03-12 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 4K | 66K |
| Input $ / M tokens | $0.04 | $0.25 |
| Output $ / M tokens | $0.08 | $2 |
| Results tracked | 22 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Gemma 3 4B: 35.9 (#215), Qwen3.5 35B-A3B: 33.8 (#251)
| Benchmark | Gemma 3 4B | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Coding | 1230 | 1410 |
| LMArena WebDev | — | 1254 |
| SciCode | — | 29.3% |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Qwen3.5 35B-A3B: —
| Benchmark | Gemma 3 4B | Qwen3.5 35B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Qwen3.5 35B-A3B leads
Gemma 3 4B: 13.2 (#335), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | Gemma 3 4B | Qwen3.5 35B-A3B |
|---|---|---|
| Chess Puzzles | 0% | 10% |
| LMArena Hard Prompts | 1253 | 1400 |
| DTBench | 50.9% | 80% |
| LMCA | 2.8% | 29.5% |
| Epoch Capabilities Index | 116.02 | 142.52 |
| Kagi LLM Benchmark | 25.2% | — |
| CritPt | — | 0.6% |
Math Qwen3.5 35B-A3B leads
Gemma 3 4B: 16.8 (#292), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | Gemma 3 4B | Qwen3.5 35B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 70% |
| LMArena Math | 1239 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
Knowledge Qwen3.5 35B-A3B leads
Gemma 3 4B: 11.8 (#299), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | Gemma 3 4B | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 23.2% | 83.5% |
| Vectara Hallucination Rate | 6.4% | 10.5% |
| LMArena Expert | 1223 | 1408 |
Multilingual Qwen3.5 35B-A3B leads
Gemma 3 4B: 42.5 (#194), Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | Gemma 3 4B | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1273 | 1378 |
| LMArena German | 1281 | 1367 |
| LMArena Russian | 1294 | 1376 |
| LMArena Chinese | — | 1457 |
| LMArena French | — | 1412 |
| LMArena Japanese | — | 1325 |
| LMArena Korean | — | 1356 |
| LMArena Spanish | — | 1392 |
Instruction Following Qwen3.5 35B-A3B leads
Gemma 3 4B: 65.2 (#225), Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | Gemma 3 4B | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1239 | 1379 |
Long Context Qwen3.5 35B-A3B leads
Gemma 3 4B: 38.7 (#194), Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | Gemma 3 4B | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1273 | 1389 |
Writing & Preference Qwen3.5 35B-A3B leads
Gemma 3 4B: 42.0 (#239), Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | Gemma 3 4B | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1291 | 1395 |
| LMArena Creative Writing | 1271 | 1346 |
| LMArena Multi-Turn | 1255 | 1390 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 14× less per token, which makes it the better buy when Qwen3.5 35B-A3B's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 4B or Qwen3.5 35B-A3B?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Qwen3.5 35B-A3B lists at $0.25 and $2.
Is Gemma 3 4B or Qwen3.5 35B-A3B better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 35B-A3B does, with 262K tokens against 131K.
How many benchmarks do Gemma 3 4B and Qwen3.5 35B-A3B share?
19 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Qwen3.5 35B-A3B has 28.