Inference
EN

Gemini 4 Argon vs MiniMax M3.1 Flash

Change models
Gemini 4 ArgonGoogle
MiniMax M3.1 FlashMiniMax
IndexAll categories, out of 100.
78.5 ±4.3 best
69.3 ±5.4
GapIndex points below the top.
Top
−9.2
CoverageIndex weight that has results.
80%
80%
SpeedOutput tokens per second.
28/s
100/s best
EloLMArena rating and rank.
1530
—
ReleasedMonth of release.
2026-09
2026-10
Input / 1MUS dollars per 1M input tokens.
$2.00
$0.15 best
Output / 1MUS dollars per 1M output tokens.
$10.00
$0.60 best
Batch output / 1MBatch price per 1M output tokens.
$5.00
—
1K chats2K tokens in, 500 out, each.
$9.00
$0.60 best
1K documents20K tokens in, 1K out, each.
$50.00
$3.60 best
1K agent tasks200K tokens in, 20K out, each.
$600.00
$42.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
77.3 best
71.8
CodingCode writing and repair.
76.7 best
69.4
ReasoningLogic problems and puzzles.
79.8 best
67.9
MultimodalTasks with images and text.
—
58.1
KnowledgeFacts and expert knowledge.
76.5 best
68.9
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
75.9
—

Benchmarks

27 shared
Only Gemini 4 Argon: 59Only MiniMax M3.1 Flash: 9
Gemini 4 Argon
MiniMax M3.1 Flash
Artificial Analysis Humanity's Last ExamKnowledge
57.1% best4 / 222
48.0%17 / 222
Artificial Analysis Long Context ReasoningReasoning
79.7%45 / 217
79.7%45 / 217
Critical Physics TasksReasoning
27.1% best17 / 214
22.3%25 / 214
Artificial Analysis Omniscience AccuracyKnowledge
48.3% best26 / 164
45.1%37 / 164
GDPval-AA normalizedAgentic
56.2% best14 / 133
47.9%31 / 133
Vibe Code Bench v1.1Coding
91.9% best3 / 123
73.9%45 / 123
Artificial Analysis SciCodeCoding
61.8% best5 / 114
53.4%39 / 114
Legal Research BenchLegal
54.8% best5 / 90
34.1%50 / 90
Tax Agent BenchFinance
49.2% best4 / 82
32.1%23 / 82
LiveBench Data AnalysisReasoning
85.2% best1 / 80
71.4%52 / 80
LiveBench ReasoningReasoning
95.1% best1 / 80
82.9%48 / 80
Terminal-Bench 4.0Agentic
57.6% best8 / 61
25.3%28 / 61
DeepSWEAgentic
77.9% best3 / 59
73.7%13 / 59
Agent Arena steerabilityAgentic
13.2 best9 / 54
−2.636 / 54
Agent Arena task outcomeAgentic
13.2 best7 / 54
−0.734 / 54
LiveBench Coding 2.0Coding
89.7% best15 / 52
83.9%26 / 52
LiveBench DesignAgentic
73.7%32 / 52
74.0% best31 / 52
LiveBench ResearchAgentic
83.1% best12 / 52
72.7%29 / 52
LiveBench Long AgenticAgentic
69.9% best5 / 51
34.7%29 / 51
LiveBench Browser UseAgentic
92.0%4 / 49
92.0%4 / 49