Model comparison
Gemma 3 4B vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 28.1 on the Noometry Index. Gemma 3 4B costs 14× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Qwen3.7 Plus in 9 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 93.3% for Qwen3.7 Plus.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 Plus accepts more context: 1M tokens versus 131K.
- Gemma 3 4B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 4B | Qwen3.7 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 28.1 | 45.3 |
| Released | 2025-03-12 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.04 | $0.40 |
| Output $ / M tokens | $0.08 | $1.60 |
| Results tracked | 22 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 3 4B: 35.9 (#215), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | Gemma 3 4B | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1230 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
Agentic & Tool Use Too close to call
Gemma 3 4B: 20.9 (#142), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | Gemma 3 4B | Qwen3.7 Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
Gemma 3 4B: 13.2 (#335), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | Gemma 3 4B | Qwen3.7 Plus |
|---|---|---|
| Chess Puzzles | 0% | 24% |
| LMArena Hard Prompts | 1253 | 1460 |
| DTBench | 50.9% | 84% |
| LMCA | 2.8% | 37.6% |
| Epoch Capabilities Index | 116.02 | 147.37 |
| Kagi LLM Benchmark | 25.2% | — |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Mystery Game Puzzles | — | 17% |
Math Qwen3.7 Plus leads
Gemma 3 4B: 16.8 (#292), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | Gemma 3 4B | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 93.3% |
| LMArena Math | 1239 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
Knowledge Qwen3.7 Plus leads
Gemma 3 4B: 11.8 (#299), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | Gemma 3 4B | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 23.2% | 87.9% |
| LMArena Expert | 1223 | 1467 |
| Vectara Hallucination Rate | 6.4% | — |
Multimodal Not comparable
Gemma 3 4B: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | Gemma 3 4B | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
Gemma 3 4B: 42.5 (#194), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | Gemma 3 4B | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1273 | 1445 |
| LMArena German | 1281 | 1471 |
| LMArena Russian | 1294 | 1457 |
| LMArena Chinese | — | 1510 |
| LMArena French | — | 1473 |
| LMArena Japanese | — | 1413 |
| LMArena Korean | — | 1415 |
| LMArena Spanish | — | 1457 |
Instruction Following Qwen3.7 Plus leads
Gemma 3 4B: 65.2 (#225), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | Gemma 3 4B | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1239 | 1440 |
Long Context Qwen3.7 Plus leads
Gemma 3 4B: 38.7 (#194), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | Gemma 3 4B | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1273 | 1455 |
Writing & Preference Qwen3.7 Plus leads
Gemma 3 4B: 42.0 (#239), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | Gemma 3 4B | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1291 | 1455 |
| LMArena Creative Writing | 1271 | 1439 |
| LMArena Multi-Turn | 1255 | 1460 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 28.1 on the Noometry Index. Gemma 3 4B costs 14× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 4B or Qwen3.7 Plus?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is Gemma 3 4B or Qwen3.7 Plus better for coding?
They score almost the same on coding (35.9 vs 36.6); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 131K.
How many benchmarks do Gemma 3 4B and Qwen3.7 Plus share?
18 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Qwen3.7 Plus has 32.