Model comparison
Gemma 3 12B vs Magistral Medium
Magistral Medium is the stronger model overall, scoring 35.2 to 32.1 on the Noometry Index. Gemma 3 12B costs 37× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Google
Mistral AISummary
- They share 14 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and Magistral Medium in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 35.1 to 22.3.
- The biggest single-benchmark swing is SciCode: 17.4% for Gemma 3 12B and 39.2% for Magistral Medium.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 3 12B | Magistral Medium | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 32.1 | 35.2 |
| Released | 2025-03-12 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 8K | 16K |
| Input $ / M tokens | $0.05 | $2 |
| Output $ / M tokens | $0.15 | $5 |
| Results tracked | 24 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Gemma 3 12B: 31.7 (#280), Magistral Medium: 39.1 (#161)
| Benchmark | Gemma 3 12B | Magistral Medium |
|---|---|---|
| SciCode | 17.4% | 39.2% |
| LMArena Coding | 1281 | 1319 |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.5 (#108), Magistral Medium: —
| Benchmark | Gemma 3 12B | Magistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Gemma 3 12B leads
Gemma 3 12B: 15.7 (#313), Magistral Medium: 8.6 (#348)
| Benchmark | Gemma 3 12B | Magistral Medium |
|---|---|---|
| CritPt | 0% | 0.3% |
| LMArena Hard Prompts | 1309 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |
Math Magistral Medium leads
Gemma 3 12B: 22.3 (#279), Magistral Medium: 35.1 (#189)
| Benchmark | Gemma 3 12B | Magistral Medium |
|---|---|---|
| LMArena Math | 1307 | 1250 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
Knowledge Magistral Medium leads
Gemma 3 12B: 26.5 (#257), Magistral Medium: 33.5 (#202)
| Benchmark | Gemma 3 12B | Magistral Medium |
|---|---|---|
| LMArena Expert | 1248 | 1223 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, Magistral Medium: —
| Benchmark | Gemma 3 12B | Magistral Medium |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.7 (#165), Magistral Medium: 39.6 (#224)
| Benchmark | Gemma 3 12B | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1318 | 1232 |
| LMArena German | 1370 | 1248 |
| LMArena Russian | 1335 | 1224 |
| LMArena Chinese | — | 1227 |
| LMArena French | — | 1267 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1125 |
| LMArena Spanish | — | 1271 |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.6 (#186), Magistral Medium: 66.0 (#211)
| Benchmark | Gemma 3 12B | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1299 | 1254 |
Long Context Too close to call
Gemma 3 12B: 40.0 (#162), Magistral Medium: 39.3 (#183)
| Benchmark | Gemma 3 12B | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1317 | 1295 |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.5 (#209), Magistral Medium: 46.3 (#219)
| Benchmark | Gemma 3 12B | Magistral Medium |
|---|---|---|
| LMArena Text | 1334 | 1255 |
| LMArena Creative Writing | 1331 | 1245 |
| LMArena Multi-Turn | 1334 | 1275 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Magistral Medium?
Magistral Medium is the stronger model overall, scoring 35.2 to 32.1 on the Noometry Index. Gemma 3 12B costs 37× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 12B or Magistral Medium?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Magistral Medium lists at $2 and $5.
Is Gemma 3 12B or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 31.7 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 131K.
How many benchmarks do Gemma 3 12B and Magistral Medium share?
14 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Magistral Medium has 22.