Inference
EN

Grok 4.7 vs Kimi K3.1 Pro

Change models
Grok 4.7xAI
Kimi K3.1 ProMoonshot AISmartest open
IndexAll categories, out of 100.
69.1 ±3.7
75.7 ±4.7 best
GapIndex points below the top.
−6.6
Top
CoverageIndex weight that has results.
85% best
80%
SpeedOutput tokens per second.
51/s best
43/s
EloLMArena rating and rank.
1398
—
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.
$6.00 best
$10.00
Batch output / 1MBatch price per 1M output tokens.
$4.80 best
$6.00
1K chats2K tokens in, 500 out, each.
$7.00 best
$9.00
1K documents20K tokens in, 1K out, each.
$46.00 best
$50.00
1K agent tasks200K tokens in, 20K out, each.
$520.00 best
$600.00
ContextMaximum tokens in one request.
500K
1.05M best
AgenticMulti-step tasks with tools.
71.9
76.7 best
CodingCode writing and repair.
69.9
71.9 best
ReasoningLogic problems and puzzles.
64.5
77.7 best
MultimodalTasks with images and text.
—
72.0
KnowledgeFacts and expert knowledge.
66.5
71.0 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
78.9
—
MathMath problems.
61.8
—

Benchmarks

21 shared
Only Grok 4.7: 63Only Kimi K3.1 Pro: 42
Grok 4.7
Kimi K3.1 Pro
Artificial Analysis Humanity's Last ExamKnowledge
43.1%32 / 222
52.5% best11 / 222
Artificial Analysis Long Context ReasoningReasoning
76.7%84 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
17.7%37 / 214
24.6% best22 / 214
Artificial Analysis Omniscience AccuracyKnowledge
42.7%42 / 164
48.9% best23 / 164
GDPval-AA normalizedAgentic
60.7%8 / 133
67.3% best3 / 133
Artificial Analysis SciCodeCoding
57.4%19 / 114
60.8% best9 / 114
DeepSWEAgentic
71.0%21 / 59
75.5% best5 / 59
MazeBench: visual spatial reasoning in a 3D open worldAgentic
1.0%16 / 48
2.0% best15 / 48
FrontierCode 2.0Coding
28.6% best10 / 27
19.6%22 / 27
Artificial Analysis AnalystAgentAgentic
52.5% best7 / 26
38.8%23 / 26
Bug Hunt BenchCoding
29.0%14 / 25
36.0% best11 / 25
Artificial Analysis AutomationBenchAgentic
65.6%9 / 23
73.3% best4 / 23
Artificial Analysis GDP.pdfAgentic
20.0%17 / 22
31.4% best2 / 22
Artificial Analysis Terminal-Bench v4.0Agentic
25.8%16 / 22
67.2% best1 / 22
Medical Long Context Reasoning (MLCR-AA)Reasoning
20.0%15 / 22
38.3% best4 / 22
Artificial Analysis DeepsecBench-AAAgentic
26.9%5 / 21
36.7% best3 / 21
Artificial Analysis CWE-Bench-AAAgentic
68.3% best1 / 19
60.8%6 / 19
Artificial Analysis Cyber IndexAgentic
56.4%2 / 19
64.1% best1 / 19
Artificial Analysis CyberGym-E2E-AAAgentic
74.0%6 / 19
94.7% best1 / 19
Multimodal Knowledge Agent BenchmarkAgentic
40.1%12 / 19
43.9% best9 / 19