Exaone 4.0 32B vs Granite 4.2 3B
Change modelsExaone 4.0 32BLG AI Research
IndexAll categories, out of 100.
32.4 ±8.7
33.2 ±5.8 best
GapIndex points below the top.
−0.8 · no clear gap
Top
CoverageIndex weight that has results.
70%
85% best
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
—
1293
ReleasedMonth of release.
2025-07
2026-08
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
33.3 best
CodingCode writing and repair.
—
34.9
ReasoningLogic problems and puzzles.
36.8 best
30.4
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
37.2 best
27.8
MultilingualTasks in many languages.
33.3
—
InstructionTasks with strict prompt rules.
20.3
58.5 best
MathMath problems.
45.3 best
34.3
Benchmarks
5 sharedOnly Exaone 4.0 32B: 10Only Granite 4.2 3B: 12
Exaone 4.0 32B
Granite 4.2 3B