Model comparison
Gemma 3 27B vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 30.8 on the Noometry Index. Gemma 3 27B costs 6.0× less per token, which makes it the better buy when Qwen Plus'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 27B scores higher in 4 categories and Qwen Plus in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen Plus leads 38.9 to 22.5.
- The biggest single-benchmark swing is DTBench: 52.5% for Gemma 3 27B and 81.1% for Qwen Plus.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 131K.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 27B | Qwen Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 30.8 | 37.1 |
| Released | 2025-03-11 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 8K | 33K |
| Input $ / M tokens | $0.08 | $0.40 |
| Output $ / M tokens | $0.16 | $1.20 |
| Results tracked | 43 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Gemma 3 27B: 22.5 (#334), Qwen Plus: 38.9 (#167)
| Benchmark | Gemma 3 27B | Qwen Plus |
|---|---|---|
| LMArena Coding | 1322 | 1328 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), Qwen Plus: —
| Benchmark | Gemma 3 27B | Qwen Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Qwen Plus leads
Gemma 3 27B: 16.7 (#301), Qwen Plus: 28.4 (#107)
| Benchmark | Gemma 3 27B | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 40.4% | 63.3% |
| LMArena Hard Prompts | 1340 | 1317 |
| DTBench | 52.5% | 81.1% |
| LMCA | 12.3% | 24% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| LiveBench Data Analysis | 51.5% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Gemma 3 27B leads
Gemma 3 27B: 25.9 (#265), Qwen Plus: 23.3 (#271)
| Benchmark | Gemma 3 27B | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 17.8% |
| LMArena Math | 1312 | 1326 |
| MATH Level 5 | 74% | 65.3% |
| LiveBench Math | 55.4% | — |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Qwen Plus leads
Gemma 3 27B: 25.5 (#261), Qwen Plus: 27.4 (#251)
| Benchmark | Gemma 3 27B | Qwen Plus |
|---|---|---|
| GPQA Diamond | 47.7% | 48.1% |
| LMArena Expert | 1304 | 1328 |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Qwen Plus: —
| Benchmark | Gemma 3 27B | Qwen Plus |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Qwen Plus: 45.1 (#175)
| Benchmark | Gemma 3 27B | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1334 | 1310 |
| LMArena Chinese | 1346 | 1347 |
| LMArena Japanese | 1287 | 1251 |
| LMArena Russian | 1349 | 1323 |
| LMArena French | 1368 | — |
| LMArena German | 1362 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1349 | — |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Qwen Plus: 68.8 (#181)
| Benchmark | Gemma 3 27B | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1321 | 1303 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Qwen Plus leads
Gemma 3 27B: 27.6 (#293), Qwen Plus: 40.3 (#158)
| Benchmark | Gemma 3 27B | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1333 | 1324 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Too close to call
Gemma 3 27B: 52.5 (#168), Qwen Plus: 52.2 (#176)
| Benchmark | Gemma 3 27B | Qwen Plus |
|---|---|---|
| LMArena Text | 1358 | 1326 |
| LMArena Creative Writing | 1346 | 1293 |
| LMArena Multi-Turn | 1345 | 1336 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 30.8 on the Noometry Index. Gemma 3 27B costs 6.0× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or Qwen Plus?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is Gemma 3 27B or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 131K.
How many benchmarks do Gemma 3 27B and Qwen Plus share?
19 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Qwen Plus has 20.