Model comparison
Gemma 2B vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Qwen3.8 27B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.8 to 24.0.
Side by side
| Gemma 2B | Qwen3.8 27B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.6 | 46.0 |
| Released | 2024-02-21 | 2026-08-14 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.99 |
| Output $ / M tokens | — | $1.49 |
| Results tracked | 23 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Gemma 2B: 29.4 (#305), Qwen3.8 27B: 50.5 (#44)
| Benchmark | Gemma 2B | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1010 | 1482 |
| LMArena WebDev | — | 1593 |
| SciCode | — | 46.6% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, Qwen3.8 27B: 32.9 (#57)
| Benchmark | Gemma 2B | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
Reasoning Qwen3.8 27B leads
Gemma 2B: 18.8 (#275), Qwen3.8 27B: 41.0 (#54)
| Benchmark | Gemma 2B | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1460 |
| Epoch Capabilities Index | 94.2 | 149.38 |
| ARC-AGI-2 | — | 42.4% |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| BIG-Bench Hard | 35.2% | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Qwen3.8 27B leads
Gemma 2B: 30.0 (#239), Qwen3.8 27B: 37.1 (#161)
| Benchmark | Gemma 2B | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1009 | 1456 |
| ProofBench | — | 16% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Qwen3.8 27B: 41.6 (#109)
| Benchmark | Gemma 2B | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | — | 1482 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multimodal Not comparable
Gemma 2B: —, Qwen3.8 27B: 41.3 (#37)
| Benchmark | Gemma 2B | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |
Multilingual Qwen3.8 27B leads
Gemma 2B: 23.0 (#294), Qwen3.8 27B: 53.7 (#60)
| Benchmark | Gemma 2B | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 958 | 1430 |
| LMArena Chinese | 986 | 1504 |
| LMArena Russian | 937 | 1415 |
| LMArena French | — | 1465 |
| LMArena German | — | 1438 |
| LMArena Japanese | — | 1384 |
| LMArena Korean | — | 1393 |
| LMArena Spanish | — | 1448 |
Instruction Following Qwen3.8 27B leads
Gemma 2B: 48.5 (#302), Qwen3.8 27B: 75.8 (#53)
| Benchmark | Gemma 2B | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 970 | 1439 |
Long Context Qwen3.8 27B leads
Gemma 2B: 29.9 (#291), Qwen3.8 27B: 44.3 (#70)
| Benchmark | Gemma 2B | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 981 | 1450 |
Writing & Preference Qwen3.8 27B leads
Gemma 2B: 24.0 (#308), Qwen3.8 27B: 65.8 (#43)
| Benchmark | Gemma 2B | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1002 | 1441 |
| LMArena Creative Writing | 987 | 1384 |
| LMArena Multi-Turn | 945 | 1441 |
| EQ-Bench Creative Writing | — | 1671 |
Frequently asked questions
Is Gemma 2B better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 29.6 on the Noometry Index.
Is Gemma 2B 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 2B and Qwen3.8 27B share?
12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Qwen3.8 27B has 31.