Granite-4.0-H-1B vs MiniCPM5-1B
Change modelsMiniCPM5-1BOpenBMB
IndexAll categories, out of 100.
16.3 ±6.9 best
15.5 ±7.0
GapIndex points below the top.
Top
−0.8 · no clear gap
CoverageIndex weight that has results.
80% best
75%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2025-10
2026-05
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
131K best
AgenticMulti-step tasks with tools.
15.8 best
8.5
CodingCode writing and repair.
14.3 best
11.9
ReasoningLogic problems and puzzles.
24.5
—
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
11.1 best
9.2
MultilingualTasks in many languages.
5.0
5.0
InstructionTasks with strict prompt rules.
17.4
28.9 best
MathMath problems.
—
21.9
Benchmarks
3 sharedOnly Granite-4.0-H-1B: 10Only MiniCPM5-1B: 15
Granite-4.0-H-1B
MiniCPM5-1B