Grok 4.1 Fast vs Magistral Medium

Change models
IndexAll categories, out of 100.
33.6 ±8.9
33.9 ±4.1 best
GapIndex points below the top.
−0.3 · no clear gap
Top
CoverageIndex weight that has results.
65%
95% best
SpeedOutput tokens per second.
138/s
—
EloLMArena rating and rank.
—
1255
ReleasedMonth of release.
2025-11
2025-06
Input / 1MUS dollars per 1M input tokens.
$0.20
—
Output / 1MUS dollars per 1M output tokens.
$0.50
—
1K chats2K tokens in, 500 out, each.
$0.65
—
1K documents20K tokens in, 1K out, each.
$4.50
—
1K agent tasks200K tokens in, 20K out, each.
$50.00
—
ContextMaximum tokens in one request.
1M best
40K
AgenticMulti-step tasks with tools.
41.1 best
31.1
CodingCode writing and repair.
—
38.9
ReasoningLogic problems and puzzles.
32.8 best
28.7
MultimodalTasks with images and text.
18.5
39.0 best
KnowledgeFacts and expert knowledge.
33.0
35.6 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
23.8 best
13.6
MathMath problems.
—
41.5

Benchmarks

7 shared
Only Grok 4.1 Fast: 3Only Magistral Medium: 24
Grok 4.1 Fast
Magistral Medium
5.1%168 / 216
9.8% best141 / 216
31.3% best173 / 211
0.0%198 / 211
0.0%145 / 207
0.3% best132 / 207
63.7%141 / 193
67.9% best132 / 193
17.2%148 / 170
20.3% best130 / 170
63.7% best78 / 143
23.1%119 / 143
36.5% best113 / 140
25.1%134 / 140