Model comparison
Magistral Small vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 30.2 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Magistral Small scores higher in 1 category and Mistral Large 3 in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 3 leads 38.7 to 26.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 6.3% for Magistral Small and 50.9% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
- Mistral Large 3 accepts more context: 262K tokens versus 128K.
Side by side
| Magistral Small | Mistral Large 3 | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 30.2 | 39.1 |
| Released | 2025-06-10 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 40K | 8K |
| Input $ / M tokens | $0.50 | $0.25 |
| Output $ / M tokens | $1.50 | $0.75 |
| 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 Large 3: 34.4 (#237)
| Benchmark | Magistral Small | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | — | 1230 |
| SciCode | 35.2% | — |
| LMArena Coding | — | 1448 |
Reasoning Mistral Large 3 leads
Magistral Small: 6.8 (#350), Mistral Large 3: 15.2 (#319)
| Benchmark | Magistral Small | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 6.3% | 50.9% |
| ARC-AGI-2 | 0% | — |
| NYT Connections (extended) | — | 7.5% |
| ARC-AGI-1 | 5% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 3% | — |
| Thematic Generalization | — | 23% |
| LMArena Hard Prompts | — | 1429 |
| DTBench | 61.3% | — |
| Epoch Capabilities Index | 133.19 | — |
Math Mistral Large 3 leads
Magistral Small: 26.2 (#261), Mistral Large 3: 38.7 (#129)
| Benchmark | Magistral Small | Mistral Large 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | — |
| LMArena Math | — | 1414 |
Knowledge Mistral Large 3 leads
Magistral Small: 30.9 (#223), Mistral Large 3: 36.0 (#177)
| Benchmark | Magistral Small | Mistral Large 3 |
|---|---|---|
| GPQA Diamond | 56.1% | — |
| Vectara Hallucination Rate | — | 14.5% |
| LMArena Expert | — | 1421 |
Multimodal Not comparable
Magistral Small: —, Mistral Large 3: 38.2 (#66)
| Benchmark | Magistral Small | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Not comparable
Magistral Small: —, Mistral Large 3: 52.5 (#84)
| Benchmark | Magistral Small | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | — | 1413 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1455 |
| LMArena German | — | 1437 |
| LMArena Japanese | — | 1394 |
| LMArena Korean | — | 1384 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1440 |
Instruction Following Not comparable
Magistral Small: —, Mistral Large 3: 74.0 (#108)
| Benchmark | Magistral Small | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | — | 1403 |
Long Context Not comparable
Magistral Small: —, Mistral Large 3: 43.1 (#105)
| Benchmark | Magistral Small | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | — | 1413 |
Writing & Preference Not comparable
Magistral Small: —, Mistral Large 3: 60.0 (#101)
| Benchmark | Magistral Small | Mistral Large 3 |
|---|---|---|
| LMArena Text | — | 1428 |
| LMArena Creative Writing | — | 1386 |
| EQ-Bench Creative Writing | — | 1412 |
| LMArena Multi-Turn | — | 1429 |
Frequently asked questions
Is Magistral Small better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 30.2 on the Noometry Index.
Which is cheaper, Magistral Small or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Magistral Small lists at $0.50 and $1.50.
Is Magistral Small or Mistral Large 3 better for coding?
Magistral Small scores higher on coding benchmarks: 38.4 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 128K.
How many benchmarks do Magistral Small and Mistral Large 3 share?
1 benchmark has published results for both models. Magistral Small has 10 scored results on Noometry and Mistral Large 3 has 24.