Gemini 3.7 Flash vs Grok 4.6

Change models
IndexAll categories, out of 100.
67.2 ±2.2 best
66.6 ±3.7
GapIndex points below the top.
Top
−0.6 · no clear gap
CoverageIndex weight that has results.
100% best
85%
SpeedOutput tokens per second.
96/s best
66/s
EloLMArena rating and rank.
1489 best
1430
ReleasedMonth of release.
2026-08
2026-08
Input / 1MUS dollars per 1M input tokens.
$0.75 best
$2.00
Output / 1MUS dollars per 1M output tokens.
$3.75 best
$6.00
Batch output / 1MBatch price per 1M output tokens.
$1.88 best
$4.80
1K chats2K tokens in, 500 out, each.
$3.38 best
$7.00
1K documents20K tokens in, 1K out, each.
$18.75 best
$46.00
1K agent tasks200K tokens in, 20K out, each.
$225.00 best
$520.00
ContextMaximum tokens in one request.
1.05M best
500K
AgenticMulti-step tasks with tools.
63.6
67.2 best
CodingCode writing and repair.
65.7
66.6 best
ReasoningLogic problems and puzzles.
67.3 best
64.8
MultimodalTasks with images and text.
67.4
—
KnowledgeFacts and expert knowledge.
70.1 best
64.8
MultilingualTasks in many languages.
71.9
—
InstructionTasks with strict prompt rules.
86.0 best
70.6
MathMath problems.
65.7 best
64.3

Benchmarks

66 shared
Only Gemini 3.7 Flash: 28Only Grok 4.6: 18
Gemini 3.7 Flash
Grok 4.6
94.8% best11 / 220
93.2%24 / 220
47.9% best18 / 216
42.9%34 / 216
81.7% best33 / 211
80.3%40 / 211
14.3%51 / 207
17.1% best41 / 207
97.2%37 / 203
99.2% best22 / 203
94.5%4 / 193
94.9% best3 / 193
55.3% best15 / 170
48.2%31 / 170
87.3% best6 / 149
86.3%14 / 149
TaxEval v2Finance
74.7% best31 / 143
71.1%83 / 143
88.7% best5 / 142
88.2%7 / 142
84.6% best17 / 137
67.1%34 / 137
93.9%5 / 135
94.7% best3 / 135
MMLU ProKnowledge
90.1% best6 / 135
89.4%11 / 135
95.5% best20 / 132
87.0%49 / 132
44.6%40 / 132
55.9% best16 / 132
70.4%55 / 130
76.2% best47 / 130
85.3% best21 / 127
68.3%31 / 127
96.6% best26 / 116
96.3%28 / 116
57.2% best21 / 113
56.5%24 / 113
MedScribeHealthcare
83.9%42 / 111
86.5% best23 / 111