Gemini 3.6 Flash vs Grok 4.5

Change models
IndexAll categories, out of 100.
63.7 ±2.6
63.7 ±2.9
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
100% best
95%
SpeedOutput tokens per second.
121/s best
53/s
EloLMArena rating and rank.
1479 best
1448
ReleasedMonth of release.
2026-07
2026-07
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
—
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.
59.7
61.6 best
CodingCode writing and repair.
62.0
65.8 best
ReasoningLogic problems and puzzles.
62.1
63.3 best
MultimodalTasks with images and text.
68.5 best
47.7
KnowledgeFacts and expert knowledge.
67.9 best
65.8
MultilingualTasks in many languages.
70.1
—
InstructionTasks with strict prompt rules.
79.1 best
71.3
MathMath problems.
60.7
61.8 best

Benchmarks

51 shared
Only Gemini 3.6 Flash: 15Only Grok 4.5: 23
Gemini 3.6 Flash
Grok 4.5
40.8%44 / 222
42.7% best36 / 222
80.0% best43 / 217
79.3%52 / 217
94.1% best12 / 217
93.4%18 / 217
10.6%63 / 214
15.4% best48 / 214
94.2%48 / 200
97.8% best33 / 200
92.8%14 / 199
93.1% best12 / 199
50.0%20 / 164
51.6% best16 / 164
86.7% best12 / 149
86.0%17 / 149
TaxEval v2Finance
74.9% best26 / 143
71.7%74 / 143
88.1% best8 / 142
87.4%15 / 142
93.4% best7 / 135
92.9%12 / 135
MMLU ProKnowledge
89.3% best12 / 135
89.2%14 / 135
39.2%46 / 133
44.2% best41 / 133
60.4% best40 / 131
52.6%50 / 131
CorpFin v2Finance
63.3%44 / 131
67.4% best12 / 131
91.2% best32 / 126
85.7%50 / 126
64.0%56 / 123
69.0% best51 / 123
65.3% best30 / 122
58.2%43 / 122
96.0% best28 / 116
94.8%35 / 116
53.4%39 / 114
55.0% best29 / 114