Claude Opus 4.7 vs Grok 4.5

Change models
IndexAll categories, out of 100.
62.6 ±2.7
62.7 ±2.9 best
GapIndex points below the top.
−0.1 · no clear gap
Top
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
46/s
47/s best
EloLMArena rating and rank.
1483 best
1448
ReleasedMonth of release.
2026-04
2026-07
Input / 1MUS dollars per 1M input tokens.
$5.00
$2.00 best
Output / 1MUS dollars per 1M output tokens.
$25.00
$6.00 best
Batch output / 1MBatch price per 1M output tokens.
$12.50
—
1K chats2K tokens in, 500 out, each.
$22.50
$7.00 best
1K documents20K tokens in, 1K out, each.
$125.00
$46.00 best
1K agent tasks200K tokens in, 20K out, each.
$1,500.00
$520.00 best
ContextMaximum tokens in one request.
1M best
500K
AgenticMulti-step tasks with tools.
61.3 best
60.6
CodingCode writing and repair.
63.8
64.4 best
ReasoningLogic problems and puzzles.
61.9
62.4 best
MultimodalTasks with images and text.
60.8 best
47.3
KnowledgeFacts and expert knowledge.
64.5
64.9 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
52.2
70.0 best
MathMath problems.
63.2 best
60.9

Benchmarks

47 shared
Only Claude Opus 4.7: 38Only Grok 4.5: 27
Claude Opus 4.7
Grok 4.5
86.4%70 / 220
93.4% best21 / 220
42.3%39 / 216
42.7% best36 / 216
78.7%61 / 211
79.3% best52 / 211
12.0%56 / 207
15.4% best47 / 207
86.7%72 / 203
97.8% best36 / 203
91.4%26 / 193
93.1% best12 / 193
48.9%27 / 170
51.6% best19 / 170
85.3%22 / 149
86.0% best17 / 149
TaxEval v2Finance
75.3% best19 / 143
71.7%74 / 143
85.1%35 / 142
87.4% best15 / 142
90.2%25 / 135
92.9% best12 / 135
MMLU ProKnowledge
89.9% best8 / 135
89.2%14 / 135
42.6%43 / 132
44.2% best41 / 132
CorpFin v2Finance
66.1%21 / 131
67.4% best12 / 131
71.0% best54 / 130
69.0%58 / 130
MedScribeHealthcare
83.0%50 / 111
86.9% best20 / 111
78.8%32 / 109
80.4% best22 / 109
MedCodeHealthcare
54.9% best7 / 108
43.3%47 / 108
38.5% best44 / 98
38.0%49 / 98
70.3% best3 / 97
61.8%59 / 97