Granite-4.0-350M vs Granite-4.0-H-350M
Change modelsIndexAll categories, out of 100.
11.9 ±5.7
12.7 ±6.9 best
GapIndex points below the top.
−0.8 · no clear gap
Top
CoverageIndex weight that has results.
90% best
80%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2025-10
2025-10
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.
32K
32K
AgenticMulti-step tasks with tools.
11.5
12.5 best
CodingCode writing and repair.
5.0
5.0
ReasoningLogic problems and puzzles.
22.1
22.1
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
11.2
11.5 best
MultilingualTasks in many languages.
5.0
5.0
InstructionTasks with strict prompt rules.
5.0
5.2 best
MathMath problems.
9.1
—
Benchmarks
13 sharedOnly Granite-4.0-350M: 2
Granite-4.0-350M
Granite-4.0-H-350M