Devstral Small vs Gemma 4 E4B
Change modelsDevstral SmallMistral
Gemma 4 E4BGoogle
IndexAll categories, out of 100.
28.2 ±8.2
28.2 ±5.2
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
75%
90% best
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2025-05
2026-04
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.
21.6
25.3 best
CodingCode writing and repair.
35.7 best
27.4
ReasoningLogic problems and puzzles.
28.5
30.9 best
MultimodalTasks with images and text.
—
32.8
KnowledgeFacts and expert knowledge.
24.2
30.2 best
MultilingualTasks in many languages.
—
8.8
InstructionTasks with strict prompt rules.
21.4
30.3 best
MathMath problems.
—
—
Benchmarks
6 sharedOnly Devstral Small: 2Only Gemma 4 E4B: 18
Devstral Small
Gemma 4 E4B