Inference
EN

Gemini 4 Argon vs Muse Wonder

Change models
Gemini 4 ArgonGoogle
Muse WonderMeta
IndexAll categories, out of 100.
78.5 ±4.3 best
73.1 ±4.0
GapIndex points below the top.
Top
−5.4 · no clear gap
CoverageIndex weight that has results.
80%
85% best
SpeedOutput tokens per second.
28/s
80/s best
EloLMArena rating and rank.
1530 best
1503
ReleasedMonth of release.
2026-09
2026-10
Input / 1MUS dollars per 1M input tokens.
$2.00 best
$4.00
Output / 1MUS dollars per 1M output tokens.
$10.00 best
$20.00
Batch output / 1MBatch price per 1M output tokens.
$5.00
—
1K chats2K tokens in, 500 out, each.
$9.00 best
$18.00
1K documents20K tokens in, 1K out, each.
$50.00 best
$100.00
1K agent tasks200K tokens in, 20K out, each.
$600.00 best
$1,200.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
77.3 best
73.0
CodingCode writing and repair.
76.7 best
72.3
ReasoningLogic problems and puzzles.
79.8 best
73.1
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
76.5 best
68.6
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
74.4
MathMath problems.
75.9 best
73.5

Benchmarks

48 shared
Only Gemini 4 Argon: 38Only Muse Wonder: 14
Gemini 4 Argon
Muse Wonder
Artificial Analysis Humanity's Last ExamKnowledge
57.1% best4 / 222
50.1%12 / 222
Artificial Analysis Long Context ReasoningReasoning
79.7%45 / 217
80.7% best37 / 217
Critical Physics TasksReasoning
27.1%17 / 214
28.3% best15 / 214
OTIS Mock AIME 2024-2025Math
100.0% best1 / 200
99.4%17 / 200
Artificial Analysis Omniscience AccuracyKnowledge
48.3% best26 / 164
38.0%59 / 164
GDPval-AA normalizedAgentic
56.2%14 / 133
63.5% best5 / 133
Vibe Code Bench v1.1Coding
91.9% best3 / 123
83.1%22 / 123
Artificial Analysis SciCodeCoding
61.8% best5 / 114
60.3%10 / 114
FrontierMath-Tiers-1-3-v2-PrivateMath
86.0% best13 / 90
82.1%18 / 90
Legal Research BenchLegal
54.8% best5 / 90
50.5%7 / 90
Tax Agent BenchFinance
49.2% best4 / 82
36.3%15 / 82
LiveBench Data AnalysisReasoning
85.2% best1 / 80
81.6%5 / 80
LiveBench ReasoningReasoning
95.1% best1 / 80
90.6%11 / 80
Mystery Game PuzzlesReasoning
64.0% best8 / 80
51.0%15 / 80
Finance Agent (v2)Finance
65.4% best1 / 79
56.6%18 / 79
Code MigrationCoding
68.2% best2 / 77
62.6%6 / 77
EMBFinance
75.2% best4 / 75
67.1%18 / 75
FrontierMath-Tier-4-v2-PrivateMath
78.0% best12 / 72
70.7%17 / 72
Terminal-Bench 4.0Agentic
57.6% best8 / 61
49.5%11 / 61
DeepSWEAgentic
77.9%3 / 59
78.8% best2 / 59