Claude Opus 4.1 vs Claude Sonnet 4 Thinking

Change models
IndexAll categories, out of 100.
47.1 ±5.0 best
46.5 ±8.2
GapIndex points below the top.
Top
−0.6 · no clear gap
CoverageIndex weight that has results.
90% best
75%
SpeedOutput tokens per second.
14/s
—
EloLMArena rating and rank.
1418
—
ReleasedMonth of release.
2025-08
—
Input / 1MUS dollars per 1M input tokens.
$15.00
—
Output / 1MUS dollars per 1M output tokens.
$75.00
—
Batch output / 1MBatch price per 1M output tokens.
$37.50
—
1K chats2K tokens in, 500 out, each.
$67.50
—
1K documents20K tokens in, 1K out, each.
$375.00
—
1K agent tasks200K tokens in, 20K out, each.
$4,500.00
—
ContextMaximum tokens in one request.
200K
—
AgenticMulti-step tasks with tools.
49.3
50.3 best
CodingCode writing and repair.
47.8 best
41.5
ReasoningLogic problems and puzzles.
54.6
—
MultimodalTasks with images and text.
50.6
52.2 best
KnowledgeFacts and expert knowledge.
49.1 best
47.8
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
41.5
45.5 best

Benchmarks

14 shared
Only Claude Opus 4.1: 12Only Claude Sonnet 4 Thinking: 2
Claude Opus 4.1
Claude Sonnet 4 Thinking
83.5% best54 / 149
82.1%75 / 149
TaxEval v2Finance
71.5%78 / 143
72.0% best69 / 143
64.6% best101 / 142
62.4%104 / 142
70.0%94 / 135
75.0% best82 / 135
MMLU ProKnowledge
87.2% best32 / 135
83.9%68 / 135
MedScribeHealthcare
71.8% best94 / 111
69.4%98 / 111
MedCodeHealthcare
41.4% best54 / 108
35.0%79 / 108
61.1% best63 / 97
49.9%84 / 97
AIMEMath
44.2%65 / 95
76.3% best51 / 95
MedQAHealthcare
92.5%30 / 95
92.7% best28 / 95
MMMU ProMultimodal
73.7%58 / 92
74.9% best57 / 92
MGSMMultilingual
94.2% best5 / 74
90.9%31 / 74
IOI v1Coding
12.5% best32 / 61
4.6%46 / 61
93.0%17 / 59
93.8% best15 / 59