Model comparison
Gemma 3 4B vs Ministral 3B
Gemma 3 4B is the stronger model overall, scoring 28.1 to 26.2 on the Noometry Index.
Last verified . 5 shared benchmarks.
Google
Mistral AISummary
- They share 5 benchmarks with published results for both. Gemma 3 4B scores higher in 1 category and Ministral 3B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Ministral 3B leads 26.6 to 16.8.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.10 / $0.10 for Ministral 3B.
Side by side
| Gemma 3 4B | Ministral 3B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 28.1 | 26.2 |
| Released | 2025-03-12 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 4K | 262K |
| Input $ / M tokens | $0.04 | $0.10 |
| Output $ / M tokens | $0.08 | $0.10 |
| Results tracked | 22 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemma 3 4B: 35.9 (#215), Ministral 3B: —
| Benchmark | Gemma 3 4B | Ministral 3B |
|---|---|---|
| LMArena Coding | 1230 | — |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Ministral 3B: —
| Benchmark | Gemma 3 4B | Ministral 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Ministral 3B leads
Gemma 3 4B: 13.2 (#335), Ministral 3B: 18.4 (#282)
| Benchmark | Gemma 3 4B | Ministral 3B |
|---|---|---|
| DTBench | 50.9% | 51.7% |
| LMCA | 2.8% | 5.5% |
| Epoch Capabilities Index | 116.02 | 118.1 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1253 | — |
Math Ministral 3B leads
Gemma 3 4B: 16.8 (#292), Ministral 3B: 26.6 (#258)
| Benchmark | Gemma 3 4B | Ministral 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| LMArena Math | 1239 | — |
| MATH Level 5 | — | 14.4% |
Knowledge Gemma 3 4B leads
Gemma 3 4B: 11.8 (#299), Ministral 3B: 10.4 (#302)
| Benchmark | Gemma 3 4B | Ministral 3B |
|---|---|---|
| GPQA Diamond | 23.2% | 25.3% |
| Vectara Hallucination Rate | 6.4% | 7.3% |
| LMArena Expert | 1223 | — |
Multilingual Not comparable
Gemma 3 4B: 42.5 (#194), Ministral 3B: —
| Benchmark | Gemma 3 4B | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |
Instruction Following Not comparable
Gemma 3 4B: 65.2 (#225), Ministral 3B: —
| Benchmark | Gemma 3 4B | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1239 | — |
Long Context Not comparable
Gemma 3 4B: 38.7 (#194), Ministral 3B: —
| Benchmark | Gemma 3 4B | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1273 | — |
Writing & Preference Not comparable
Gemma 3 4B: 42.0 (#239), Ministral 3B: —
| Benchmark | Gemma 3 4B | Ministral 3B |
|---|---|---|
| LMArena Text | 1291 | — |
| LMArena Creative Writing | 1271 | — |
| EQ-Bench Creative Writing | 1068 | — |
| LMArena Multi-Turn | 1255 | — |
Frequently asked questions
Is Gemma 3 4B better than Ministral 3B?
Gemma 3 4B is the stronger model overall, scoring 28.1 to 26.2 on the Noometry Index.
Which is cheaper, Gemma 3 4B or Ministral 3B?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Ministral 3B lists at $0.10 and $0.10.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Gemma 3 4B and Ministral 3B share?
5 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Ministral 3B has 6.