Grok 3 [Beta] vs Grok 4
Change models
Grok 4xAI
IndexAll categories, out of 100.
39.3 ±8.5
50.0 ±4.0 best
GapIndex points below the top.
−10.7
Top
CoverageIndex weight that has results.
60%
95% best
SpeedOutput tokens per second.
—
78/s
EloLMArena rating and rank.
—
1411
ReleasedMonth of release.
2025-02
2025-07
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.
—
48.0
CodingCode writing and repair.
34.9
50.9 best
ReasoningLogic problems and puzzles.
34.4
47.3 best
MultimodalTasks with images and text.
—
49.6
KnowledgeFacts and expert knowledge.
47.1
55.8 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
39.2
MathMath problems.
38.2
50.5 best
Benchmarks
15 sharedOnly Grok 3 [Beta]: 11Only Grok 4: 25
Grok 3 [Beta]
Grok 4