Inference
EN

Gemini 4 Argon vs MiMo-V2.6-Pro

Change models
Gemini 4 ArgonGoogle
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
78.5 ±4.3 best
70.2 ±4.7
GapIndex points below the top.
Top
−8.3
CoverageIndex weight that has results.
80%
80%
SpeedOutput tokens per second.
28/s
31/s best
EloLMArena rating and rank.
1530 best
1492
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.
$10.00
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$5.00
—
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.
77.3 best
72.1
CodingCode writing and repair.
76.7 best
66.6
ReasoningLogic problems and puzzles.
79.8 best
68.3
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
76.5 best
64.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
75.9 best
71.3

Benchmarks

45 shared
Only Gemini 4 Argon: 41Only MiMo-V2.6-Pro: 13
Gemini 4 Argon
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
57.1% best4 / 222
49.4%14 / 222
Artificial Analysis Long Context ReasoningReasoning
79.7%45 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
27.1% best17 / 214
26.6%19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
48.3% best26 / 164
34.8%67 / 164
GDPval-AA normalizedAgentic
56.2%14 / 133
59.2% best9 / 133
Vibe Code Bench v1.1Coding
91.9% best3 / 123
85.2%16 / 123
Artificial Analysis SciCodeCoding
61.8% best5 / 114
60.9%8 / 114
MedScribeHealthcare
87.4%17 / 109
88.3% best13 / 109
MedCodeHealthcare
58.8% best3 / 106
45.0%39 / 106
Legal Research BenchLegal
54.8% best5 / 90
47.1%16 / 90
Tax Agent BenchFinance
49.2% best4 / 82
32.4%22 / 82
LiveBench Data AnalysisReasoning
85.2% best1 / 80
72.3%49 / 80
LiveBench ReasoningReasoning
95.1% best1 / 80
79.6%59 / 80
Finance Agent (v2)Finance
65.4% best1 / 79
57.3%16 / 79
Code MigrationCoding
68.2% best2 / 77
43.0%26 / 77
EMBFinance
75.2% best4 / 75
62.9%30 / 75
Terminal-Bench 2.1 · Vals AIAgentic
57.7%43 / 75
67.8% best32 / 75
ProgramBenchCoding
2.5% best8 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
57.6% best8 / 61
31.3%24 / 61
DeepSWEAgentic
77.9% best3 / 59
71.9%18 / 59