Model comparison
Gemma 3 4B vs Magistral Medium
Magistral Medium is the stronger model overall, scoring 35.2 to 28.1 on the Noometry Index. Gemma 3 4B costs 55× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Google
Mistral AISummary
- They share 13 benchmarks with published results for both. Gemma 3 4B scores higher in 2 categories and Magistral Medium in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Magistral Medium leads 33.5 to 11.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 25.2% for Gemma 3 4B and 16.2% for Magistral Medium.
- Gemma 3 4B is cheaper at $0.04 / $0.08 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 4B | Magistral Medium | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 28.1 | 35.2 |
| Released | 2025-03-12 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.04 | $2 |
| Output $ / M tokens | $0.08 | $5 |
| Results tracked | 22 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Gemma 3 4B: 35.9 (#215), Magistral Medium: 39.1 (#161)
| Benchmark | Gemma 3 4B | Magistral Medium |
|---|---|---|
| LMArena Coding | 1230 | 1319 |
| SciCode | — | 39.2% |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Magistral Medium: —
| Benchmark | Gemma 3 4B | Magistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Gemma 3 4B leads
Gemma 3 4B: 13.2 (#335), Magistral Medium: 8.6 (#348)
| Benchmark | Gemma 3 4B | Magistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | 16.2% |
| LMArena Hard Prompts | 1253 | 1267 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Magistral Medium leads
Gemma 3 4B: 16.8 (#292), Magistral Medium: 35.1 (#189)
| Benchmark | Gemma 3 4B | Magistral Medium |
|---|---|---|
| LMArena Math | 1239 | 1250 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
Knowledge Magistral Medium leads
Gemma 3 4B: 11.8 (#299), Magistral Medium: 33.5 (#202)
| Benchmark | Gemma 3 4B | Magistral Medium |
|---|---|---|
| LMArena Expert | 1223 | 1223 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
Multilingual Gemma 3 4B leads
Gemma 3 4B: 42.5 (#194), Magistral Medium: 39.6 (#224)
| Benchmark | Gemma 3 4B | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1273 | 1232 |
| LMArena German | 1281 | 1248 |
| LMArena Russian | 1294 | 1224 |
| LMArena Chinese | — | 1227 |
| LMArena French | — | 1267 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1125 |
| LMArena Spanish | — | 1271 |
Instruction Following Too close to call
Gemma 3 4B: 65.2 (#225), Magistral Medium: 66.0 (#211)
| Benchmark | Gemma 3 4B | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1239 | 1254 |
Long Context Too close to call
Gemma 3 4B: 38.7 (#194), Magistral Medium: 39.3 (#183)
| Benchmark | Gemma 3 4B | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1273 | 1295 |
Writing & Preference Magistral Medium leads
Gemma 3 4B: 42.0 (#239), Magistral Medium: 46.3 (#219)
| Benchmark | Gemma 3 4B | Magistral Medium |
|---|---|---|
| LMArena Text | 1291 | 1255 |
| LMArena Creative Writing | 1271 | 1245 |
| LMArena Multi-Turn | 1255 | 1275 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Magistral Medium?
Magistral Medium is the stronger model overall, scoring 35.2 to 28.1 on the Noometry Index. Gemma 3 4B costs 55× 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 4B or Magistral Medium?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Magistral Medium lists at $2 and $5.
Is Gemma 3 4B or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 35.9 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 4B and Magistral Medium share?
13 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Magistral Medium has 22.