Grok 2 vs Grok 3 Mini

Change models
IndexAll categories, out of 100.
29.1 ±9.4
44.3 ±9.7 best
GapIndex points below the top.
−15.2
Top
CoverageIndex weight that has results.
55%
60% best
SpeedOutput tokens per second.
—
65/s
EloLMArena rating and rank.
1305
1370 best
ReleasedMonth of release.
2024-08
2025-02
Input / 1MUS dollars per 1M input tokens.
—
$0.30
Output / 1MUS dollars per 1M output tokens.
—
$0.50
1K chats2K tokens in, 500 out, each.
—
$0.85
1K documents20K tokens in, 1K out, each.
—
$6.50
1K agent tasks200K tokens in, 20K out, each.
—
$70.00
ContextMaximum tokens in one request.
—
128K
AgenticMulti-step tasks with tools.
—
—
CodingCode writing and repair.
25.2
51.4 best
ReasoningLogic problems and puzzles.
—
37.0
MultimodalTasks with images and text.
33.5
—
KnowledgeFacts and expert knowledge.
34.0
48.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
25.0
43.9 best

Benchmarks

6 shared
Only Grok 2: 13Only Grok 3 Mini: 7
Grok 2
Grok 3 Mini
53.8%139 / 217
75.5% best106 / 217
11.5%153 / 200
77.8% best90 / 200
56.0%118 / 141
80.3% best65 / 141
63.5%39 / 88
88.1% best18 / 88
0.7%62 / 69
5.9% best43 / 69
0.0%33 / 64
0.0%33 / 64