Inference
EN

Claude Opus 5 vs Kimi K3.1 Pro

Change models
Claude Opus 5Anthropic
Kimi K3.1 ProMoonshot AISmartest open
IndexAll categories, out of 100.
73.8 ±1.9
75.7 ±4.7 best
GapIndex points below the top.
−1.9 · no clear gap
Top
CoverageIndex weight that has results.
100% best
80%
SpeedOutput tokens per second.
48/s best
43/s
EloLMArena rating and rank.
1502
—
ReleasedMonth of release.
2026-07
2026-10
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
$6.00 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
1.05M best
AgenticMulti-step tasks with tools.
71.6
76.7 best
CodingCode writing and repair.
74.8 best
71.9
ReasoningLogic problems and puzzles.
75.4
77.7 best
MultimodalTasks with images and text.
72.5 best
72.0
KnowledgeFacts and expert knowledge.
73.1 best
71.0
MultilingualTasks in many languages.
63.6
—
InstructionTasks with strict prompt rules.
55.6
—
MathMath problems.
74.8
—

Benchmarks

23 shared
Only Claude Opus 5: 127Only Kimi K3.1 Pro: 40
Claude Opus 5
Kimi K3.1 Pro
Artificial Analysis Humanity's Last ExamKnowledge
54.9% best7 / 222
52.5%11 / 222
Artificial Analysis Long Context ReasoningReasoning
79.3%52 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
29.1% best13 / 214
24.6%22 / 214
Artificial Analysis Omniscience AccuracyKnowledge
60.9% best7 / 164
48.9%23 / 164
GDPval-AA normalizedAgentic
61.1%7 / 133
67.3% best3 / 133
Artificial Analysis SciCodeCoding
56.4%26 / 114
60.8% best9 / 114
Artificial Analysis MMMU-ProMultimodal
84.7% best6 / 113
83.9%9 / 113
Humanity's Last ExamKnowledge
64.7%4 / 77
70.0% best2 / 77
BrowseCompAgentic
90.8%8 / 63
92.1% best3 / 63
DeepSWEAgentic
68.8%24 / 59
75.5% best5 / 59
Humanity's Last Exam without toolsKnowledge
56.3% best6 / 53
51.1%8 / 53
MazeBench: visual spatial reasoning in a 3D open worldAgentic
12.0% best7 / 48
2.0%15 / 48
Humanity's Last Exam with toolsAgentic
64.7%3 / 36
70.0% best1 / 36
FrontierCode 2.0Coding
26.7% best13 / 27
19.6%22 / 27
Artificial Analysis AnalystAgentAgentic
53.8% best5 / 26
38.8%23 / 26
Bug Hunt BenchCoding
27.0%15 / 25
36.0% best11 / 25
OSWorld 2.0Agentic
70.6%3 / 25
79.6% best1 / 25
Artificial Analysis DeepsecBench-AAAgentic
25.9%8 / 21
36.7% best3 / 21
OfficeQA ProMultimodal
66.9%5 / 16
67.4% best4 / 16
OSWorld 2.1 (all 108 tasks)Agentic
74.0%8 / 11
79.6% best4 / 11