Model comparison
Gemma 3 12B vs Qwen2.5 72B Instruct
Gemma 3 12B and Qwen2.5 72B Instruct score almost the same on the Noometry Index (32.1 vs 31.9), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Gemma 3 12B scores higher in 6 categories and Qwen2.5 72B Instruct in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen2.5 72B Instruct leads 22.3 to 15.7.
- The biggest single-benchmark swing is DTBench: 48.8% for Gemma 3 12B and 62.9% for Qwen2.5 72B Instruct.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
Side by side
| Gemma 3 12B | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 32.1 | 31.9 |
| Released | 2025-03-12 | 2024-09 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.05 | $1.40 |
| Output $ / M tokens | $0.15 | $5.60 |
| Results tracked | 24 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 72B Instruct leads
Gemma 3 12B: 31.7 (#280), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Gemma 3 12B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1281 | 1292 |
| SciCode | 17.4% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Gemma 3 12B leads
Gemma 3 12B: 25.5 (#108), Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Gemma 3 12B | Qwen2.5 72B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Gemma 3 12B: 15.7 (#313), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Gemma 3 12B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1271 |
| DTBench | 48.8% | 62.9% |
| LMCA | 4.5% | 13.4% |
| Epoch Capabilities Index | 123.5 | 129 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Gemma 3 12B leads
Gemma 3 12B: 22.3 (#279), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Gemma 3 12B | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 8.1% |
| LMArena Math | 1307 | 1283 |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge Too close to call
Gemma 3 12B: 26.5 (#257), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Gemma 3 12B | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 39.5% | 49.1% |
| LMArena Expert | 1248 | 1245 |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 4.4% | — |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
Gemma 3 12B: —, Qwen2.5 72B Instruct: —
| Benchmark | Gemma 3 12B | Qwen2.5 72B Instruct |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.7 (#165), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Gemma 3 12B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1318 | 1252 |
| LMArena German | 1370 | 1234 |
| LMArena Russian | 1335 | 1264 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1280 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Spanish | — | 1256 |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.6 (#186), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Gemma 3 12B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1299 | 1254 |
| IFEval | — | 80.6% |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#162), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Gemma 3 12B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1317 | 1282 |
Writing & Preference Too close to call
Gemma 3 12B: 47.5 (#209), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Gemma 3 12B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1334 | 1269 |
| LMArena Creative Writing | 1331 | 1221 |
| LMArena Multi-Turn | 1334 | 1272 |
| EQ-Bench Creative Writing | 1126 | — |
| WildBench | — | 80.2% |
Frequently asked questions
Is Gemma 3 12B better than Qwen2.5 72B Instruct?
Gemma 3 12B and Qwen2.5 72B Instruct score almost the same on the Noometry Index (32.1 vs 31.9), so choose on price, context window or the category you care about most.
Which is cheaper, Gemma 3 12B or Qwen2.5 72B Instruct?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Gemma 3 12B or Qwen2.5 72B Instruct better for coding?
Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 31.7 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Gemma 3 12B and Qwen2.5 72B Instruct share?
17 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen2.5 72B Instruct has 43.