Model comparison
Magistral Small vs Mistral Small 3
Mistral Small 3 is the stronger model overall, scoring 31.2 to 30.2 on the Noometry Index.
Last verified . 4 shared benchmarks.
Mistral AISummary
- They share 4 benchmarks with published results for both. Magistral Small scores higher in 3 categories and Mistral Small 3 in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mistral Small 3 leads 18.9 to 6.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 30% for Magistral Small and 6.7% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
- Magistral Small accepts more context: 128K tokens versus 33K.
Side by side
| Magistral Small | Mistral Small 3 | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 30.2 | 31.2 |
| Released | 2025-06-10 | 2025-01-30 |
| Weights | Open | Open |
| Context window | 128K | 33K |
| Max output | 40K | 16K |
| Input $ / M tokens | $0.50 | $0.05 |
| Output $ / M tokens | $1.50 | $0.08 |
| Results tracked | 10 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Small leads
Magistral Small: 38.4 (#176), Mistral Small 3: 36.5 (#207)
| Benchmark | Magistral Small | Mistral Small 3 |
|---|---|---|
| SciCode | 35.2% | — |
| BigCodeBench Instruct | — | 45.3% |
| LMArena Coding | — | 1246 |
| BigCodeBench Complete | — | 50.4% |
Reasoning Mistral Small 3 leads
Magistral Small: 6.8 (#350), Mistral Small 3: 18.9 (#273)
| Benchmark | Magistral Small | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 3% | 0% |
| Epoch Capabilities Index | 133.19 | 127.07 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| ARC-AGI-1 | 5% | — |
| CritPt | 0.3% | — |
| LMArena Hard Prompts | — | 1233 |
| DTBench | 61.3% | — |
Math Magistral Small leads
Magistral Small: 26.2 (#261), Mistral Small 3: 16.3 (#295)
| Benchmark | Magistral Small | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | 6.7% |
| LMArena Math | — | 1240 |
Knowledge Magistral Small leads
Magistral Small: 30.9 (#223), Mistral Small 3: 25.1 (#263)
| Benchmark | Magistral Small | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 56.1% | 47.3% |
| Confabulations | — | 25.2% |
| LMArena Expert | — | 1202 |
Multilingual Not comparable
Magistral Small: —, Mistral Small 3: 37.3 (#236)
| Benchmark | Magistral Small | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | — | 1198 |
| LMArena Chinese | — | 1204 |
| LMArena French | — | 1203 |
| LMArena German | — | 1211 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1216 |
Instruction Following Not comparable
Magistral Small: —, Mistral Small 3: 63.7 (#229)
| Benchmark | Magistral Small | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | — | 1214 |
Long Context Not comparable
Magistral Small: —, Mistral Small 3: 37.8 (#211)
| Benchmark | Magistral Small | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | — | 1246 |
Writing & Preference Not comparable
Magistral Small: —, Mistral Small 3: 32.2 (#280)
| Benchmark | Magistral Small | Mistral Small 3 |
|---|---|---|
| LMArena Text | — | 1234 |
| LMArena Creative Writing | — | 1195 |
| EQ-Bench Creative Writing | — | 707 |
| LMArena Multi-Turn | — | 1217 |
Frequently asked questions
Is Magistral Small better than Mistral Small 3?
Mistral Small 3 is the stronger model overall, scoring 31.2 to 30.2 on the Noometry Index.
Which is cheaper, Magistral Small or Mistral Small 3?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Magistral Small lists at $0.50 and $1.50.
Is Magistral Small or Mistral Small 3 better for coding?
Magistral Small scores higher on coding benchmarks: 38.4 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Magistral Small does, with 128K tokens against 33K.
How many benchmarks do Magistral Small and Mistral Small 3 share?
4 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Mistral Small 3 has 24.