Inference
EN

Kimi K3.1 Pro vs MiMo-V2.6-Pro

Change models
Kimi K3.1 ProMoonshot AISmartest open
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
75.7 ±4.7 best
70.2 ±4.7
GapIndex points below the top.
Top
−5.5 · no clear gap
CoverageIndex weight that has results.
80%
80%
SpeedOutput tokens per second.
43/s best
31/s
EloLMArena rating and rank.
—
1492
ReleasedMonth of release.
2026-10
2026-09
Input / 1MUS dollars per 1M input tokens.
$2.00
$0.435 best
Output / 1MUS dollars per 1M output tokens.
$10.00
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$6.00
—
1K chats2K tokens in, 500 out, each.
$9.00
$1.31 best
1K documents20K tokens in, 1K out, each.
$50.00
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$600.00
$104.40 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
76.7 best
72.1
CodingCode writing and repair.
71.9 best
66.6
ReasoningLogic problems and puzzles.
77.7 best
68.3
MultimodalTasks with images and text.
72.0
—
KnowledgeFacts and expert knowledge.
71.0 best
64.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
—
71.3

Benchmarks

20 shared
Only Kimi K3.1 Pro: 43Only MiMo-V2.6-Pro: 38
Kimi K3.1 Pro
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
52.5% best11 / 222
49.4%14 / 222
Artificial Analysis Long Context ReasoningReasoning
86.3%3 / 217
86.3%3 / 217
Critical Physics TasksReasoning
24.6%22 / 214
26.6% best19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
48.9% best23 / 164
34.8%67 / 164
GDPval-AA normalizedAgentic
67.3% best3 / 133
59.2%9 / 133
Artificial Analysis SciCodeCoding
60.8%9 / 114
60.9% best8 / 114
DeepSWEAgentic
75.5% best5 / 59
71.9%18 / 59
Artificial Analysis AnalystAgentAgentic
38.8% best23 / 26
37.5%26 / 26
Bug Hunt BenchCoding
36.0% best11 / 25
22.7%18 / 25
Artificial Analysis AutomationBenchAgentic
73.3% best4 / 23
58.6%15 / 23
ExploitGymAgentic
20.7% best13 / 23
17.8%14 / 23
Artificial Analysis GDP.pdfAgentic
31.4% best2 / 22
19.2%18 / 22
Artificial Analysis Terminal-Bench v4.0Agentic
67.2% best1 / 22
34.8%14 / 22
Medical Long Context Reasoning (MLCR-AA)Reasoning
38.3% best4 / 22
12.8%21 / 22
Agents' Last ExamAgentic
43.2% best6 / 21
31.6%12 / 21
Artificial Analysis DeepsecBench-AAAgentic
36.7% best3 / 21
26.2%7 / 21
Artificial Analysis CWE-Bench-AAAgentic
60.8%6 / 19
63.3% best4 / 19
Artificial Analysis Cyber IndexAgentic
64.1% best1 / 19
56.1%3 / 19
Artificial Analysis CyberGym-E2E-AAAgentic
94.7% best1 / 19
78.6%3 / 19
Multimodal Knowledge Agent BenchmarkAgentic
43.9% best9 / 19
37.3%13 / 19