Model comparison
Gemma 3 4B vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 28.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Gemma 3 4B scores higher in 1 category and Qwen2.5 Plus 1127 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5 Plus 1127 leads 35.5 to 11.8.
- Gemma 3 4B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 4B | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 28.1 | 38.8 |
| Released | 2025-03-12 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 Plus 1127 leads
Gemma 3 4B: 35.9 (#215), Qwen2.5 Plus 1127: 38.5 (#175)
| Benchmark | Gemma 3 4B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1230 | 1314 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Qwen2.5 Plus 1127: —
| Benchmark | Gemma 3 4B | Qwen2.5 Plus 1127 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Qwen2.5 Plus 1127 leads
Gemma 3 4B: 13.2 (#335), Qwen2.5 Plus 1127: 25.9 (#141)
| Benchmark | Gemma 3 4B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1299 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Qwen2.5 Plus 1127 leads
Gemma 3 4B: 16.8 (#292), Qwen2.5 Plus 1127: 36.1 (#174)
| Benchmark | Gemma 3 4B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1239 | 1298 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
Knowledge Qwen2.5 Plus 1127 leads
Gemma 3 4B: 11.8 (#299), Qwen2.5 Plus 1127: 35.5 (#183)
| Benchmark | Gemma 3 4B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1223 | 1289 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
Multilingual Too close to call
Gemma 3 4B: 42.5 (#194), Qwen2.5 Plus 1127: 41.9 (#201)
| Benchmark | Gemma 3 4B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1273 | 1265 |
| LMArena German | 1281 | 1231 |
| LMArena Russian | 1294 | 1271 |
| LMArena Chinese | — | 1314 |
| LMArena Japanese | — | 1207 |
Instruction Following Qwen2.5 Plus 1127 leads
Gemma 3 4B: 65.2 (#225), Qwen2.5 Plus 1127: 67.2 (#199)
| Benchmark | Gemma 3 4B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1239 | 1275 |
Long Context Too close to call
Gemma 3 4B: 38.7 (#194), Qwen2.5 Plus 1127: 39.2 (#184)
| Benchmark | Gemma 3 4B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1273 | 1292 |
Writing & Preference Qwen2.5 Plus 1127 leads
Gemma 3 4B: 42.0 (#239), Qwen2.5 Plus 1127: 49.4 (#192)
| Benchmark | Gemma 3 4B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1291 | 1299 |
| LMArena Creative Writing | 1271 | 1262 |
| LMArena Multi-Turn | 1255 | 1299 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 28.1 on the Noometry Index.
Is Gemma 3 4B or Qwen2.5 Plus 1127 better for coding?
Qwen2.5 Plus 1127 scores higher on coding benchmarks: 38.5 versus 35.9 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Qwen2.5 Plus 1127 share?
12 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Qwen2.5 Plus 1127 has 14.