Grok 4.6 vs Grok 4.7

Change models
IndexAll categories, out of 100.
67.8 ±3.7
69.1 ±3.7 best
GapIndex points below the top.
−1.3 · no clear gap
Top
CoverageIndex weight that has results.
85%
85%
SpeedOutput tokens per second.
56/s best
51/s
EloLMArena rating and rank.
1430 best
1398
ReleasedMonth of release.
2026-08
2026-09
Input / 1MUS dollars per 1M input tokens.
$2.00
$2.00
Output / 1MUS dollars per 1M output tokens.
$6.00
$6.00
Batch output / 1MBatch price per 1M output tokens.
$4.80
$4.80
1K chats2K tokens in, 500 out, each.
$7.00
$7.00
1K documents20K tokens in, 1K out, each.
$46.00
$46.00
1K agent tasks200K tokens in, 20K out, each.
$520.00
$520.00
ContextMaximum tokens in one request.
500K
500K
AgenticMulti-step tasks with tools.
68.4
71.9 best
CodingCode writing and repair.
67.7
69.9 best
ReasoningLogic problems and puzzles.
66.1 best
64.5
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
65.7
66.5 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
72.0
78.9 best
MathMath problems.
65.3 best
61.8

Benchmarks

63 shared
Only Grok 4.6: 21Only Grok 4.7: 21
Grok 4.6
Grok 4.7
42.9%34 / 222
43.1% best32 / 222
80.3% best40 / 217
76.7%84 / 217
93.2% best21 / 217
92.7%25 / 217
17.1%42 / 214
17.7% best37 / 214
99.2% best19 / 200
98.1%31 / 200
48.2% best27 / 164
42.7%42 / 164
86.3% best14 / 149
84.4%33 / 149
55.9%16 / 133
60.7% best8 / 133
67.1% best31 / 131
61.4%36 / 131
87.0%45 / 126
89.5% best37 / 126
76.2%41 / 123
86.2% best13 / 123
68.3% best28 / 122
60.0%39 / 122
96.3% best26 / 116
95.1%32 / 116
56.5%24 / 114
57.4% best19 / 114
MedScribeHealthcare
86.5%22 / 109
89.4% best7 / 109
MedCodeHealthcare
44.7%40 / 106
49.6% best21 / 106
48.9%32 / 91
56.0% best23 / 91
Chess PuzzlesReasoning
33.0%48 / 90
41.0% best34 / 90
66.0% best35 / 90
53.0%53 / 90
48.1% best12 / 90
47.1%16 / 90