Model comparison
Gemma 2 9B vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 25.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.8 to 32.1.
Side by side
| Gemma 2 9B | Qwen3.8 27B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 25.9 | 46.0 |
| Released | 2024-06-24 | 2026-08-14 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.99 |
| Output $ / M tokens | — | $1.49 |
| Results tracked | 35 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Gemma 2 9B: 29.4 (#304), Qwen3.8 27B: 50.5 (#44)
| Benchmark | Gemma 2 9B | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1173 | 1482 |
| LMArena WebDev | — | 1593 |
| SciCode | — | 46.6% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, Qwen3.8 27B: 32.9 (#57)
| Benchmark | Gemma 2 9B | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
Reasoning Qwen3.8 27B leads
Gemma 2 9B: 15.9 (#309), Qwen3.8 27B: 41.0 (#54)
| Benchmark | Gemma 2 9B | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1460 |
| Epoch Capabilities Index | 119.83 | 149.38 |
| ARC-AGI-2 | — | 42.4% |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 5.4% |
| LiveBench Reasoning | 15.2% | — |
| DTBench | — | 88% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Qwen3.8 27B leads
Gemma 2 9B: 9.9 (#318), Qwen3.8 27B: 37.1 (#161)
| Benchmark | Gemma 2 9B | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1183 | 1456 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| ProofBench | — | 16% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge Qwen3.8 27B leads
Gemma 2 9B: 9.7 (#305), Qwen3.8 27B: 41.6 (#109)
| Benchmark | Gemma 2 9B | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1147 | 1482 |
| GPQA Diamond | 27.5% | — |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multimodal Not comparable
Gemma 2 9B: —, Qwen3.8 27B: 41.3 (#37)
| Benchmark | Gemma 2 9B | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |
Multilingual Qwen3.8 27B leads
Gemma 2 9B: 36.6 (#238), Qwen3.8 27B: 53.7 (#60)
| Benchmark | Gemma 2 9B | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1188 | 1430 |
| LMArena Chinese | 1185 | 1504 |
| LMArena French | 1190 | 1465 |
| LMArena German | 1186 | 1438 |
| LMArena Japanese | 1144 | 1384 |
| LMArena Korean | 1137 | 1393 |
| LMArena Russian | 1200 | 1415 |
| LMArena Spanish | 1200 | 1448 |
Instruction Following Qwen3.8 27B leads
Gemma 2 9B: 57.6 (#269), Qwen3.8 27B: 75.8 (#53)
| Benchmark | Gemma 2 9B | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1178 | 1439 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Qwen3.8 27B leads
Gemma 2 9B: 36.3 (#233), Qwen3.8 27B: 44.3 (#70)
| Benchmark | Gemma 2 9B | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1197 | 1450 |
Writing & Preference Qwen3.8 27B leads
Gemma 2 9B: 32.1 (#281), Qwen3.8 27B: 65.8 (#43)
| Benchmark | Gemma 2 9B | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1207 | 1441 |
| LMArena Creative Writing | 1206 | 1384 |
| EQ-Bench Creative Writing | 841 | 1671 |
| LMArena Multi-Turn | 1193 | 1441 |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Qwen3.8 27B share?
19 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Qwen3.8 27B has 31.