Model comparison
Gemma 3 27B vs Magistral Medium
Magistral Medium is the stronger model overall, scoring 35.2 to 30.8 on the Noometry Index. Gemma 3 27B costs 28× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Google
Mistral AISummary
- They share 20 benchmarks with published results for both. Gemma 3 27B scores higher in 4 categories and Magistral Medium in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Magistral Medium leads 39.1 to 22.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 40.4% for Gemma 3 27B and 16.2% for Magistral Medium.
- Gemma 3 27B is cheaper at $0.08 / $0.16 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 27B | Magistral Medium | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.8 | 35.2 |
| Released | 2025-03-11 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 8K | 16K |
| Input $ / M tokens | $0.08 | $2 |
| Output $ / M tokens | $0.16 | $5 |
| Results tracked | 43 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Gemma 3 27B: 22.5 (#334), Magistral Medium: 39.1 (#161)
| Benchmark | Gemma 3 27B | Magistral Medium |
|---|---|---|
| SciCode | 21.2% | 39.2% |
| LMArena Coding | 1322 | 1319 |
| Aider Polyglot | 4.9% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), Magistral Medium: —
| Benchmark | Gemma 3 27B | Magistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Gemma 3 27B leads
Gemma 3 27B: 16.7 (#301), Magistral Medium: 8.6 (#348)
| Benchmark | Gemma 3 27B | Magistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 40.4% | 16.2% |
| CritPt | 0% | 0.3% |
| LMArena Hard Prompts | 1340 | 1267 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 6.1% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Magistral Medium leads
Gemma 3 27B: 25.9 (#265), Magistral Medium: 35.1 (#189)
| Benchmark | Gemma 3 27B | Magistral Medium |
|---|---|---|
| LMArena Math | 1312 | 1250 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Magistral Medium leads
Gemma 3 27B: 25.5 (#261), Magistral Medium: 33.5 (#202)
| Benchmark | Gemma 3 27B | Magistral Medium |
|---|---|---|
| LMArena Expert | 1304 | 1223 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Magistral Medium: —
| Benchmark | Gemma 3 27B | Magistral Medium |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Magistral Medium: 39.6 (#224)
| Benchmark | Gemma 3 27B | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1334 | 1232 |
| LMArena Chinese | 1346 | 1227 |
| LMArena French | 1368 | 1267 |
| LMArena German | 1362 | 1248 |
| LMArena Japanese | 1287 | 1175 |
| LMArena Korean | 1308 | 1125 |
| LMArena Russian | 1349 | 1224 |
| LMArena Spanish | 1349 | 1271 |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Magistral Medium: 66.0 (#211)
| Benchmark | Gemma 3 27B | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1321 | 1254 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Magistral Medium leads
Gemma 3 27B: 27.6 (#293), Magistral Medium: 39.3 (#183)
| Benchmark | Gemma 3 27B | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1333 | 1295 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Gemma 3 27B leads
Gemma 3 27B: 52.5 (#168), Magistral Medium: 46.3 (#219)
| Benchmark | Gemma 3 27B | Magistral Medium |
|---|---|---|
| LMArena Text | 1358 | 1255 |
| LMArena Creative Writing | 1346 | 1245 |
| LMArena Multi-Turn | 1345 | 1275 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Magistral Medium?
Magistral Medium is the stronger model overall, scoring 35.2 to 30.8 on the Noometry Index. Gemma 3 27B costs 28× 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 27B or Magistral Medium?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Magistral Medium lists at $2 and $5.
Is Gemma 3 27B or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 22.5 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 27B and Magistral Medium share?
20 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Magistral Medium has 22.