Model comparison
Gemma 3 12B vs Qwen3-Next 80B-A3B Instruct
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 32.1 on the Noometry Index. Gemma 3 12B costs 12× less per token, which makes it the better buy when Qwen3-Next 80B-A3B Instruct's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Gemma 3 12B scores higher in 1 category and Qwen3-Next 80B-A3B Instruct in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-Next 80B-A3B Instruct leads 38.8 to 22.3.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.50 / $2 for Qwen3-Next 80B-A3B Instruct.
Side by side
| Gemma 3 12B | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 32.1 | 43.0 |
| Released | 2025-03-12 | 2025-09 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 8K | 33K |
| Input $ / M tokens | $0.05 | $0.50 |
| Output $ / M tokens | $0.15 | $2 |
| Results tracked | 24 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Next 80B-A3B Instruct leads
Gemma 3 12B: 31.7 (#280), Qwen3-Next 80B-A3B Instruct: 42.5 (#98)
| Benchmark | Gemma 3 12B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1281 | 1440 |
| SciCode | 17.4% | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.5 (#108), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | Gemma 3 12B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Qwen3-Next 80B-A3B Instruct leads
Gemma 3 12B: 15.7 (#313), Qwen3-Next 80B-A3B Instruct: 31.1 (#81)
| Benchmark | Gemma 3 12B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1428 |
| Kagi LLM Benchmark | — | 66.7% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |
Math Qwen3-Next 80B-A3B Instruct leads
Gemma 3 12B: 22.3 (#279), Qwen3-Next 80B-A3B Instruct: 38.8 (#126)
| Benchmark | Gemma 3 12B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1307 | 1440 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| Omni-MATH | — | 46.7% |
Knowledge Qwen3-Next 80B-A3B Instruct leads
Gemma 3 12B: 26.5 (#257), Qwen3-Next 80B-A3B Instruct: 41.8 (#106)
| Benchmark | Gemma 3 12B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Vectara Hallucination Rate | 4.4% | 9.3% |
| LMArena Expert | 1248 | 1417 |
| GPQA Diamond | 39.5% | — |
| MMLU-Pro | — | 78.6% |
| GPQA (HELM) | — | 63% |
Multimodal Not comparable
Gemma 3 12B: —, Qwen3-Next 80B-A3B Instruct: —
| Benchmark | Gemma 3 12B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Qwen3-Next 80B-A3B Instruct leads
Gemma 3 12B: 45.7 (#165), Qwen3-Next 80B-A3B Instruct: 52.1 (#93)
| Benchmark | Gemma 3 12B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1318 | 1407 |
| LMArena German | 1370 | 1417 |
| LMArena Russian | 1335 | 1404 |
| LMArena Chinese | — | 1460 |
| LMArena French | — | 1413 |
| LMArena Japanese | — | 1395 |
| LMArena Korean | — | 1364 |
| LMArena Spanish | — | 1435 |
Instruction Following Qwen3-Next 80B-A3B Instruct leads
Gemma 3 12B: 68.6 (#186), Qwen3-Next 80B-A3B Instruct: 70.8 (#159)
| Benchmark | Gemma 3 12B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1299 | 1389 |
| IFEval | — | 81% |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#162), Qwen3-Next 80B-A3B Instruct: 37.0 (#223)
| Benchmark | Gemma 3 12B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Longer Query | 1317 | 1403 |
| Fiction.LiveBench | — | 55.6% |
Writing & Preference Qwen3-Next 80B-A3B Instruct leads
Gemma 3 12B: 47.5 (#209), Qwen3-Next 80B-A3B Instruct: 58.0 (#121)
| Benchmark | Gemma 3 12B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1334 | 1417 |
| LMArena Creative Writing | 1331 | 1334 |
| LMArena Multi-Turn | 1334 | 1416 |
| EQ-Bench Creative Writing | 1126 | — |
| WildBench | — | 80.7% |
Frequently asked questions
Is Gemma 3 12B better than Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 32.1 on the Noometry Index. Gemma 3 12B costs 12× less per token, which makes it the better buy when Qwen3-Next 80B-A3B Instruct's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 12B or Qwen3-Next 80B-A3B Instruct?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Qwen3-Next 80B-A3B Instruct lists at $0.50 and $2.
Is Gemma 3 12B or Qwen3-Next 80B-A3B Instruct better for coding?
Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 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 Qwen3-Next 80B-A3B Instruct share?
13 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.