Compare / head-to-head
Magistral Medium 1.2vsMagistral Small 1.2
Magistral Medium 1.2 leads 4 of 4 shared benchmarks. Both offer a 128K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
4 – 0
Magistral Medium 1.2 leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 128K tokens
Providers
Mistral AI
same provider
Magistral Medium 1.2
Mistral AI · released 2025-09-17
textvision
- Context
- 128K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 4 · 3 core
Magistral Small 1.2
Mistral AI · released 2025-09-17
textvision
- Context
- 128K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 4 · 3 core
Quality
Benchmark matrix
4 shared · 0 only Magistral Medium 1.2 · 0 only Magistral Small 1.2| Benchmark | Magistral Medium 1.2 | Magistral Small 1.2 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| GPQA Diamond | 76.26% ↗ | 70.07% ↗ | +6.2 pt | Magistral Medium 1.2 |
| AIME24 (pass@1) | 91.82% ↗ | 86.14% ↗ | +5.7 pt | Magistral Medium 1.2 |
| AIME25 (pass@1) | 83.48% ↗ | 77.34% ↗ | +6.1 pt | Magistral Medium 1.2 |
| LiveCodeBench (v5) | 75% ↗ | 70.88% ↗ | +4.1 pt | Magistral Medium 1.2 |
| Only Magistral Medium 1.2 reports · 0 | ||||
| Magistral Medium 1.2 reports nothing Magistral Small 1.2 does not. | ||||
| Only Magistral Small 1.2 reports · 0 | ||||
| Magistral Small 1.2 reports nothing Magistral Medium 1.2 does not. | ||||
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Magistral Medium 1.2 minus Magistral Small 1.2 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Magistral Medium 1.2 | Magistral Small 1.2 | Edge |
|---|---|---|---|
| Context window | 128K tokens | 128K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-09-17 | 2025-09-17 | — |
| Cited benchmark scores | 4 | 4 | — |
Reliability
Mistral AI status
Live from /statusMore matchups
Magistral Medium 1.2 vs …
Models sharing the most benchmarksMore matchups
Magistral Small 1.2 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Magistral Medium 1.2 and Magistral Small 1.2 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.