Model comparison
Magistral Small vs Pixtral Large
Pixtral Large is the stronger model overall, scoring 32.2 to 30.2 on the Noometry Index. Magistral Small costs 4.0× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in reasoning, where Pixtral Large leads 21.7 to 6.8.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $2 / $6 for Pixtral Large.
Side by side
| Magistral Small | Pixtral Large | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 30.2 | 32.2 |
| Released | 2025-06-10 | 2024-11-01 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 40K | 128K |
| Input $ / M tokens | $0.50 | $2 |
| Output $ / M tokens | $1.50 | $6 |
| Results tracked | 10 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Magistral Small: 38.4 (#176), Pixtral Large: —
| Benchmark | Magistral Small | Pixtral Large |
|---|---|---|
| SciCode | 35.2% | — |
Reasoning Pixtral Large leads
Magistral Small: 6.8 (#350), Pixtral Large: 21.7 (#218)
| Benchmark | Magistral Small | Pixtral Large |
|---|---|---|
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| ARC-AGI-1 | 5% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 3% | — |
| EnigmaEval | — | 0.8% |
| DTBench | 61.3% | — |
| Epoch Capabilities Index | 133.19 | — |
Math Not comparable
Magistral Small: 26.2 (#261), Pixtral Large: —
| Benchmark | Magistral Small | Pixtral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | — |
Knowledge Not comparable
Magistral Small: 30.9 (#223), Pixtral Large: —
| Benchmark | Magistral Small | Pixtral Large |
|---|---|---|
| GPQA Diamond | 56.1% | — |
Multimodal Not comparable
Magistral Small: —, Pixtral Large: 30.6 (#111)
| Benchmark | Magistral Small | Pixtral Large |
|---|---|---|
| LMArena Vision | — | 1089 |
Writing & Preference Not comparable
Magistral Small: —, Pixtral Large: 32.9 (#278)
| Benchmark | Magistral Small | Pixtral Large |
|---|---|---|
| EQ-Bench Creative Writing | — | 988 |
Frequently asked questions
Is Magistral Small better than Pixtral Large?
Pixtral Large is the stronger model overall, scoring 32.2 to 30.2 on the Noometry Index. Magistral Small costs 4.0× less per token, which makes it the better buy when Pixtral Large's lead doesn't matter for your workload.
Which is cheaper, Magistral Small or Pixtral Large?
Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Pixtral Large lists at $2 and $6.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Magistral Small and Pixtral Large share?
0 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Pixtral Large has 3.