Model comparison
Gemma 3 4B vs Mistral
Mistral is the stronger model overall, scoring 29.9 to 28.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
Mistral AISummary
- They share 12 benchmarks with published results for both. Gemma 3 4B scores higher in 5 categories and Mistral in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 3 4B leads 65.2 to 52.6.
- Gemma 3 4B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 4B | Mistral | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 28.1 | 29.9 |
| Released | 2025-03-12 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Gemma 3 4B: 35.9 (#215), Mistral: 33.8 (#250)
| Benchmark | Gemma 3 4B | Mistral |
|---|---|---|
| LMArena Coding | 1230 | 1162 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Mistral: —
| Benchmark | Gemma 3 4B | Mistral |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Mistral leads
Gemma 3 4B: 13.2 (#335), Mistral: 22.2 (#200)
| Benchmark | Gemma 3 4B | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1149 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Mistral leads
Gemma 3 4B: 16.8 (#292), Mistral: 22.3 (#278)
| Benchmark | Gemma 3 4B | Mistral |
|---|---|---|
| LMArena Math | 1239 | 1180 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| Omni-MATH | — | 7.2% |
Knowledge Mistral leads
Gemma 3 4B: 11.8 (#299), Mistral: 16.6 (#288)
| Benchmark | Gemma 3 4B | Mistral |
|---|---|---|
| LMArena Expert | 1223 | 1125 |
| GPQA Diamond | 23.2% | — |
| MMLU-Pro | — | 27.7% |
| Vectara Hallucination Rate | 6.4% | — |
| GPQA (HELM) | — | 30.3% |
Multilingual Gemma 3 4B leads
Gemma 3 4B: 42.5 (#194), Mistral: 32.8 (#254)
| Benchmark | Gemma 3 4B | Mistral |
|---|---|---|
| LMArena Non-English | 1273 | 1129 |
| LMArena German | 1281 | 1155 |
| LMArena Russian | 1294 | 1168 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1180 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Spanish | — | 1143 |
Instruction Following Gemma 3 4B leads
Gemma 3 4B: 65.2 (#225), Mistral: 52.6 (#288)
| Benchmark | Gemma 3 4B | Mistral |
|---|---|---|
| LMArena Instruction Following | 1239 | 1152 |
| IFEval | — | 56.8% |
Long Context Gemma 3 4B leads
Gemma 3 4B: 38.7 (#194), Mistral: 35.0 (#245)
| Benchmark | Gemma 3 4B | Mistral |
|---|---|---|
| LMArena Longer Query | 1273 | 1153 |
Writing & Preference Gemma 3 4B leads
Gemma 3 4B: 42.0 (#239), Mistral: 37.0 (#260)
| Benchmark | Gemma 3 4B | Mistral |
|---|---|---|
| LMArena Text | 1291 | 1165 |
| LMArena Creative Writing | 1271 | 1158 |
| LMArena Multi-Turn | 1255 | 1147 |
| EQ-Bench Creative Writing | 1068 | — |
| WildBench | — | 66% |
Frequently asked questions
Is Gemma 3 4B better than Mistral?
Mistral is the stronger model overall, scoring 29.9 to 28.1 on the Noometry Index.
Is Gemma 3 4B or Mistral better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 33.8 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Mistral share?
12 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Mistral has 22.