Claude Opus 5 vs Claude Opus 5.5

Change models
Claude Opus 5Anthropic
IndexAll categories, out of 100.
73.8 ±1.9
78.6 ±2.4 best
GapIndex points below the top.
−4.8
Top
CoverageIndex weight that has results.
100% best
95%
SpeedOutput tokens per second.
48/s
76/s best
EloLMArena rating and rank.
1502
1513 best
ReleasedMonth of release.
2026-07
2026-09
Input / 1MUS dollars per 1M input tokens.
$5.00
$4.00 best
Output / 1MUS dollars per 1M output tokens.
$25.00
$20.00 best
Batch output / 1MBatch price per 1M output tokens.
$12.50
$10.00 best
1K chats2K tokens in, 500 out, each.
$22.50
$18.00 best
1K documents20K tokens in, 1K out, each.
$125.00
$100.00 best
1K agent tasks200K tokens in, 20K out, each.
$1,500.00
$1,200.00 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
71.6
74.1 best
CodingCode writing and repair.
74.8
81.8 best
ReasoningLogic problems and puzzles.
75.4
80.8 best
MultimodalTasks with images and text.
72.5
74.1 best
KnowledgeFacts and expert knowledge.
73.1
79.2 best
MultilingualTasks in many languages.
63.6
—
InstructionTasks with strict prompt rules.
55.6
59.6 best
MathMath problems.
74.8
77.7 best

Benchmarks

107 shared
Only Claude Opus 5: 43Only Claude Opus 5.5: 50
Claude Opus 5
Claude Opus 5.5
54.9%7 / 222
61.4% best2 / 222
79.3%52 / 217
84.7% best6 / 217
93.9% best14 / 217
90.6%38 / 217
29.1%13 / 214
31.7% best4 / 214
98.9%22 / 200
100.0% best1 / 200
60.9%7 / 164
65.5% best3 / 164
61.1%7 / 133
68.3% best1 / 133
90.4%8 / 131
91.7% best6 / 131
97.5%5 / 126
97.5%5 / 126
88.4%11 / 123
90.3% best6 / 123
97.1%6 / 122
97.9% best3 / 122
99.0% best2 / 116
98.3%8 / 116
56.4%26 / 114
66.9% best2 / 114
84.7%6 / 113
87.7% best1 / 113
MedScribeHealthcare
91.0%4 / 109
91.4% best1 / 109
MedCodeHealthcare
63.6% best1 / 106
49.8%19 / 106
59.9%19 / 91
72.2% best7 / 91
Chess PuzzlesReasoning
43.0%31 / 90
67.0% best5 / 90
85.6%15 / 90
91.2% best4 / 90
55.3% best2 / 90
50.5%7 / 90