Inference
EN

Grok 4.7 vs MiMo-V2.6-Pro

Change models
Grok 4.7xAI
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
69.1 ±3.7
70.2 ±4.7 best
GapIndex points below the top.
−1.1 · no clear gap
Top
CoverageIndex weight that has results.
85% best
80%
SpeedOutput tokens per second.
51/s best
31/s
EloLMArena rating and rank.
1398
1492 best
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$2.00
$0.435 best
Output / 1MUS dollars per 1M output tokens.
$6.00
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$4.80
—
1K chats2K tokens in, 500 out, each.
$7.00
$1.31 best
1K documents20K tokens in, 1K out, each.
$46.00
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$520.00
$104.40 best
ContextMaximum tokens in one request.
500K
1.05M best
AgenticMulti-step tasks with tools.
71.9
72.1 best
CodingCode writing and repair.
69.9 best
66.6
ReasoningLogic problems and puzzles.
64.5
68.3 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
66.5 best
64.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
78.9
—
MathMath problems.
61.8
71.3 best

Benchmarks

48 shared
Only Grok 4.7: 36Only MiMo-V2.6-Pro: 10
Grok 4.7
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
43.1%32 / 222
49.4% best14 / 222
Artificial Analysis Long Context ReasoningReasoning
76.7%84 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
17.7%37 / 214
26.6% best19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
42.7% best42 / 164
34.8%67 / 164
GDPval-AA normalizedAgentic
60.7% best8 / 133
59.2%9 / 133
Vibe Code Bench v1.1Coding
86.2% best13 / 123
85.2%16 / 123
Artificial Analysis SciCodeCoding
57.4%19 / 114
60.9% best8 / 114
MedScribeHealthcare
89.4% best7 / 109
88.3%13 / 109
MedCodeHealthcare
49.6% best21 / 106
45.0%39 / 106
Legal Research BenchLegal
47.1%16 / 90
47.1%16 / 90
Tax Agent BenchFinance
35.8% best16 / 82
32.4%22 / 82
LiveBench Data AnalysisReasoning
76.9% best30 / 80
72.3%49 / 80
LiveBench ReasoningReasoning
82.7% best51 / 80
79.6%59 / 80
Finance Agent (v2)Finance
52.3%36 / 79
57.3% best16 / 79
Code MigrationCoding
44.8% best19 / 77
43.0%26 / 77
EMBFinance
67.0% best20 / 75
62.9%30 / 75
Terminal-Bench 2.1 · Vals AIAgentic
73.4% best22 / 75
67.8%32 / 75
ProgramBenchCoding
0.5%19 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
28.8%25 / 61
31.3% best24 / 61
DeepSWEAgentic
71.0%21 / 59
71.9% best18 / 59