Model comparison
Gemma 3 27B vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 30.8 on the Noometry Index.
Last verified . 16 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Gemma 3 27B scores higher in 3 categories and Qwen1.5-14B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 33.6.
Side by side
| Gemma 3 27B | Qwen1.5-14B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 30.8 | 32.7 |
| Released | 2025-03-11 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.08 | — |
| Output $ / M tokens | $0.16 | — |
| Results tracked | 43 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Gemma 3 27B: 22.5 (#334), Qwen1.5-14B: 33.1 (#263)
| Benchmark | Gemma 3 27B | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1322 | 1138 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), Qwen1.5-14B: —
| Benchmark | Gemma 3 27B | Qwen1.5-14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Qwen1.5-14B leads
Gemma 3 27B: 16.7 (#301), Qwen1.5-14B: 21.4 (#223)
| Benchmark | Gemma 3 27B | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1113 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Qwen1.5-14B leads
Gemma 3 27B: 25.9 (#265), Qwen1.5-14B: 32.4 (#215)
| Benchmark | Gemma 3 27B | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1312 | 1125 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Qwen1.5-14B leads
Gemma 3 27B: 25.5 (#261), Qwen1.5-14B: 29.8 (#232)
| Benchmark | Gemma 3 27B | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1304 | 1094 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
| MMLU | — | 68.6% |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Qwen1.5-14B: —
| Benchmark | Gemma 3 27B | Qwen1.5-14B |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Qwen1.5-14B: 30.7 (#262)
| Benchmark | Gemma 3 27B | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1334 | 1095 |
| LMArena Chinese | 1346 | 1147 |
| LMArena French | 1368 | 1116 |
| LMArena German | 1362 | 1043 |
| LMArena Japanese | 1287 | 1019 |
| LMArena Russian | 1349 | 1046 |
| LMArena Spanish | 1349 | 1085 |
| LMArena Korean | 1308 | — |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Qwen1.5-14B: 56.8 (#271)
| Benchmark | Gemma 3 27B | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1102 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Qwen1.5-14B leads
Gemma 3 27B: 27.6 (#293), Qwen1.5-14B: 33.7 (#257)
| Benchmark | Gemma 3 27B | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1333 | 1113 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Gemma 3 27B leads
Gemma 3 27B: 52.5 (#168), Qwen1.5-14B: 33.6 (#276)
| Benchmark | Gemma 3 27B | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1358 | 1128 |
| LMArena Creative Writing | 1346 | 1091 |
| LMArena Multi-Turn | 1345 | 1110 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 30.8 on the Noometry Index.
Is Gemma 3 27B or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 33.1 versus 22.5 in the Noometry coding category.
How many benchmarks do Gemma 3 27B and Qwen1.5-14B share?
16 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Qwen1.5-14B has 17.