Exaone 4.0 32B vs Magistral Small
Change modelsExaone 4.0 32BLG AI Research
Magistral SmallMistral
IndexAll categories, out of 100.
32.4 ±8.7 best
31.4 ±4.3
GapIndex points below the top.
Top
−1.0 · no clear gap
CoverageIndex weight that has results.
70%
95% best
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2025-07
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.
128K
128K
AgenticMulti-step tasks with tools.
5.5
24.8 best
CodingCode writing and repair.
—
36.3
ReasoningLogic problems and puzzles.
36.8 best
28.2
MultimodalTasks with images and text.
—
40.0
KnowledgeFacts and expert knowledge.
37.2 best
31.0
MultilingualTasks in many languages.
33.3
—
InstructionTasks with strict prompt rules.
20.3 best
12.2
MathMath problems.
45.3 best
41.3
Benchmarks
6 sharedOnly Exaone 4.0 32B: 9Only Magistral Small: 23
Exaone 4.0 32B
Magistral Small