Claude Opus 5 vs Claude Sonnet 5.5

Change models
Claude Opus 5Anthropic
IndexAll categories, out of 100.
73.8 ±1.9
77.2 ±2.6 best
GapIndex points below the top.
−3.4
Top
CoverageIndex weight that has results.
100% best
95%
SpeedOutput tokens per second.
48/s
107/s best
EloLMArena rating and rank.
1502 best
1469
ReleasedMonth of release.
2026-07
2026-09
Input / 1MUS dollars per 1M input tokens.
$5.00
$2.00 best
Output / 1MUS dollars per 1M output tokens.
$25.00
$10.00 best
Batch output / 1MBatch price per 1M output tokens.
$12.50
$5.00 best
1K chats2K tokens in, 500 out, each.
$22.50
$9.00 best
1K documents20K tokens in, 1K out, each.
$125.00
$50.00 best
1K agent tasks200K tokens in, 20K out, each.
$1,500.00
$600.00 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
71.6
77.5 best
CodingCode writing and repair.
74.8
80.8 best
ReasoningLogic problems and puzzles.
75.4
77.8 best
MultimodalTasks with images and text.
72.5
74.4 best
KnowledgeFacts and expert knowledge.
73.1 best
71.3
MultilingualTasks in many languages.
63.6
—
InstructionTasks with strict prompt rules.
55.6 best
41.5
MathMath problems.
74.8
76.1 best

Benchmarks

98 shared
Only Claude Opus 5: 52Only Claude Sonnet 5.5: 30
Claude Opus 5
Claude Sonnet 5.5
54.9%7 / 222
55.0% best6 / 222
79.3%52 / 217
82.7% best23 / 217
93.9%14 / 217
95.6% best4 / 217
29.1%13 / 214
31.4% best7 / 214
98.9%22 / 200
100.0% best1 / 200
60.9% best7 / 164
51.5%17 / 164
61.1%7 / 133
66.9% best4 / 133
90.4% best8 / 131
83.9%17 / 131
97.5% best5 / 126
96.5%11 / 126
88.4%11 / 123
92.4% best2 / 123
97.1% best6 / 122
90.1%16 / 122
99.0% best2 / 116
97.8%14 / 116
56.4%26 / 114
61.0% best6 / 114
MedScribeHealthcare
91.0%4 / 109
91.1% best3 / 109
MedCodeHealthcare
63.6% best1 / 106
52.9%12 / 106
59.9% best19 / 91
46.5%39 / 91
Chess PuzzlesReasoning
43.0%31 / 90
59.0% best10 / 90
85.6%15 / 90
88.8% best10 / 90
55.3% best2 / 90
48.1%12 / 90
79.2%7 / 83
81.3% best3 / 83