Magistral Medium vs Magistral Small
Change modelsMagistral MediumMistral
Magistral SmallMistral
IndexAll categories, out of 100.
33.7 ±4.1 best
31.4 ±4.3
GapIndex points below the top.
Top
−2.3 · no clear gap
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
1255
—
ReleasedMonth of release.
2025-06
2025-06
Input / 1MUS dollars per 1M input tokens.
—
—
Output / 1MUS dollars per 1M output tokens.
—
—
1K chats2K tokens in, 500 out, each.
—
—
1K documents20K tokens in, 1K out, each.
—
—
1K agent tasks200K tokens in, 20K out, each.
—
—
ContextMaximum tokens in one request.
40K
128K best
AgenticMulti-step tasks with tools.
30.6 best
24.8
CodingCode writing and repair.
39.2 best
36.3
ReasoningLogic problems and puzzles.
28.4 best
28.2
MultimodalTasks with images and text.
39.2
40.0 best
KnowledgeFacts and expert knowledge.
35.2 best
31.0
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
12.5 best
12.2
MathMath problems.
41.8 best
41.3
Benchmarks
29 sharedOnly Magistral Medium: 2
Magistral Medium
Magistral Small