Inference
EN

Claude Sonnet 5.5 vs Kimi K3.1 Pro

Change models
Claude Sonnet 5.5Anthropic
Kimi K3.1 ProMoonshot AISmartest open
IndexAll categories, out of 100.
77.2 ±2.6 best
75.7 ±4.7
GapIndex points below the top.
Top
−1.5 · no clear gap
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
107/s best
43/s
EloLMArena rating and rank.
1469
—
ReleasedMonth of release.
2026-09
2026-10
Input / 1MUS dollars per 1M input tokens.
$2.00
$2.00
Output / 1MUS dollars per 1M output tokens.
$10.00
$10.00
Batch output / 1MBatch price per 1M output tokens.
$5.00 best
$6.00
1K chats2K tokens in, 500 out, each.
$9.00
$9.00
1K documents20K tokens in, 1K out, each.
$50.00
$50.00
1K agent tasks200K tokens in, 20K out, each.
$600.00
$600.00
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
77.5 best
76.7
CodingCode writing and repair.
80.8 best
71.9
ReasoningLogic problems and puzzles.
77.8 best
77.7
MultimodalTasks with images and text.
74.4 best
72.0
KnowledgeFacts and expert knowledge.
71.3 best
71.0
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
41.5
—
MathMath problems.
76.1
—

Benchmarks

24 shared
Only Claude Sonnet 5.5: 104Only Kimi K3.1 Pro: 39
Claude Sonnet 5.5
Kimi K3.1 Pro
Artificial Analysis Humanity's Last ExamKnowledge
55.0% best6 / 222
52.5%11 / 222
Artificial Analysis Long Context ReasoningReasoning
82.7%23 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
31.4% best7 / 214
24.6%22 / 214
Artificial Analysis Omniscience AccuracyKnowledge
51.5% best17 / 164
48.9%23 / 164
GDPval-AA normalizedAgentic
66.9%4 / 133
67.3% best3 / 133
Artificial Analysis SciCodeCoding
61.0% best6 / 114
60.8%9 / 114
DeepSWEAgentic
71.0%21 / 59
75.5% best5 / 59
Humanity's Last Exam without toolsKnowledge
56.9% best5 / 53
51.1%8 / 53
MazeBench: visual spatial reasoning in a 3D open worldAgentic
8.0% best11 / 48
2.0%15 / 48
Humanity's Last Exam with toolsAgentic
64.5%4 / 36
70.0% best1 / 36
FrontierCode 2.0Coding
41.0% best4 / 27
19.6%22 / 27
Artificial Analysis AnalystAgentAgentic
57.5% best2 / 26
38.8%23 / 26
Bug Hunt BenchCoding
51.3% best2 / 25
36.0%11 / 25
Artificial Analysis AutomationBenchAgentic
71.8%5 / 23
73.3% best4 / 23
Artificial Analysis GDP.pdfAgentic
25.8%10 / 22
31.4% best2 / 22
Artificial Analysis Terminal-Bench v4.0Agentic
63.6%3 / 22
67.2% best1 / 22
Medical Long Context Reasoning (MLCR-AA)Reasoning
41.7% best2 / 22
38.3%4 / 22
Multimodal Knowledge Agent BenchmarkAgentic
52.0% best4 / 19
43.9%9 / 19
OfficeQA ProMultimodal
65.6%8 / 16
67.4% best4 / 16
OSWorld 2.1 (all 108 tasks)Agentic
80.1% best3 / 11
79.6%4 / 11