Model comparison
Gemma 2 27B vs Qwen3.5 27B
Qwen3.5 27B is the stronger model overall, scoring 41.4 to 29.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Qwen3.5 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 27B leads 36.8 to 10.0.
- The biggest single-benchmark swing is DTBench: 48% for Gemma 2 27B and 82.4% for Qwen3.5 27B.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $0.30 / $2.40 for Qwen3.5 27B.
- Qwen3.5 27B accepts more context: 262K tokens versus 8K.
Side by side
| Gemma 2 27B | Qwen3.5 27B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.2 | 41.4 |
| Released | 2024-06-24 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 8K | 262K |
| Max output | 2K | 66K |
| Input $ / M tokens | $0.65 | $0.30 |
| Output $ / M tokens | $0.65 | $2.40 |
| Results tracked | 34 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 27B leads
Gemma 2 27B: 33.5 (#243), Qwen3.5 27B: 38.6 (#159)
| Benchmark | Gemma 2 27B | Qwen3.5 27B |
|---|---|---|
| LMArena Coding | 1211 | 1427 |
| LMArena WebDev | — | 1357 |
| WeirdML | — | 39.5% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | — | 349.45 |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, Qwen3.5 27B: —
| Benchmark | Gemma 2 27B | Qwen3.5 27B |
|---|---|---|
| Vending-Bench 2 | — | 201.98 |
Reasoning Qwen3.5 27B leads
Gemma 2 27B: 14.8 (#313), Qwen3.5 27B: 26.6 (#116)
| Benchmark | Gemma 2 27B | Qwen3.5 27B |
|---|---|---|
| LMArena Hard Prompts | 1199 | 1414 |
| DTBench | 48% | 82.4% |
| LMCA | 7.1% | 34% |
| NYT Connections (extended) | — | 47.9% |
| Thematic Generalization | — | 45.5% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 47.9% | — |
| Epoch Capabilities Index | 122.06 | — |
| LiveBench | 38.2% | — |
Math Qwen3.5 27B leads
Gemma 2 27B: 10.0 (#306), Qwen3.5 27B: 36.8 (#103)
| Benchmark | Gemma 2 27B | Qwen3.5 27B |
|---|---|---|
| LMArena Math | 1212 | 1428 |
| MathArena Final-Answer Competitions | — | 56.7% |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
Knowledge Qwen3.5 27B leads
Gemma 2 27B: 18.9 (#275), Qwen3.5 27B: 37.4 (#149)
| Benchmark | Gemma 2 27B | Qwen3.5 27B |
|---|---|---|
| LMArena Expert | 1172 | 1428 |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| Vectara Hallucination Rate | — | 12.1% |
| MMLU | 75.7% | — |
Multimodal Not comparable
Gemma 2 27B: —, Qwen3.5 27B: 38.7 (#56)
| Benchmark | Gemma 2 27B | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | — | 1240 |
Multilingual Qwen3.5 27B leads
Gemma 2 27B: 38.8 (#221), Qwen3.5 27B: 51.0 (#112)
| Benchmark | Gemma 2 27B | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | 1217 | 1390 |
| LMArena Chinese | 1221 | 1478 |
| LMArena French | 1246 | 1409 |
| LMArena German | 1209 | 1393 |
| LMArena Japanese | 1175 | 1345 |
| LMArena Korean | 1174 | 1359 |
| LMArena Russian | 1234 | 1389 |
| LMArena Spanish | 1228 | 1408 |
Instruction Following Qwen3.5 27B leads
Gemma 2 27B: 60.7 (#244), Qwen3.5 27B: 73.7 (#114)
| Benchmark | Gemma 2 27B | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | 1206 | 1393 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Qwen3.5 27B leads
Gemma 2 27B: 37.3 (#213), Qwen3.5 27B: 43.1 (#103)
| Benchmark | Gemma 2 27B | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | 1231 | 1413 |
Writing & Preference Qwen3.5 27B leads
Gemma 2 27B: 44.4 (#220), Qwen3.5 27B: 59.5 (#106)
| Benchmark | Gemma 2 27B | Qwen3.5 27B |
|---|---|---|
| LMArena Text | 1231 | 1409 |
| LMArena Creative Writing | 1241 | 1362 |
| LMArena Multi-Turn | 1224 | 1410 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Qwen3.5 27B?
Qwen3.5 27B is the stronger model overall, scoring 41.4 to 29.2 on the Noometry Index.
Which is cheaper, Gemma 2 27B or Qwen3.5 27B?
Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Qwen3.5 27B lists at $0.30 and $2.40.
Is Gemma 2 27B or Qwen3.5 27B better for coding?
Qwen3.5 27B scores higher on coding benchmarks: 38.6 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 27B does, with 262K tokens against 8K.
How many benchmarks do Gemma 2 27B and Qwen3.5 27B share?
19 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Qwen3.5 27B has 28.