Inference
EN

Gemini 3.7 Flash vs Muse Wonder

Change models
Gemini 3.7 FlashGoogle
Muse WonderMeta
IndexAll categories, out of 100.
68.5 ±2.2
73.1 ±4.0 best
GapIndex points below the top.
−4.6
Top
CoverageIndex weight that has results.
100% best
85%
SpeedOutput tokens per second.
85/s best
80/s
EloLMArena rating and rank.
1489
1503 best
ReleasedMonth of release.
2026-08
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.75 best
$4.00
Output / 1MUS dollars per 1M output tokens.
$3.75 best
$20.00
Batch output / 1MBatch price per 1M output tokens.
$1.88
—
1K chats2K tokens in, 500 out, each.
$3.38 best
$18.00
1K documents20K tokens in, 1K out, each.
$18.75 best
$100.00
1K agent tasks200K tokens in, 20K out, each.
$225.00 best
$1,200.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.1
73.0 best
CodingCode writing and repair.
66.9
72.3 best
ReasoningLogic problems and puzzles.
68.7
73.1 best
MultimodalTasks with images and text.
67.7
—
KnowledgeFacts and expert knowledge.
71.2 best
68.6
MultilingualTasks in many languages.
72.3
—
InstructionTasks with strict prompt rules.
88.3 best
74.4
MathMath problems.
66.8
73.5 best

Benchmarks

39 shared
Only Gemini 3.7 Flash: 54Only Muse Wonder: 23
Gemini 3.7 Flash
Muse Wonder
Artificial Analysis Humanity's Last ExamKnowledge
47.9%18 / 222
50.1% best12 / 222
Artificial Analysis Long Context ReasoningReasoning
81.7% best33 / 217
80.7%37 / 217
Critical Physics TasksReasoning
14.3%52 / 214
28.3% best15 / 214
OTIS Mock AIME 2024-2025Math
97.2%34 / 200
99.4% best17 / 200
Artificial Analysis Omniscience AccuracyKnowledge
55.3% best12 / 164
38.0%59 / 164
GDPval-AA normalizedAgentic
44.6%40 / 133
63.5% best5 / 133
Vibe Code Bench v1.1Coding
70.4%48 / 123
83.1% best22 / 123
Artificial Analysis SciCodeCoding
57.2%21 / 114
60.3% best10 / 114
FrontierMath-Tiers-1-3-v2-PrivateMath
71.6%28 / 90
82.1% best18 / 90
Legal Research BenchLegal
34.6%49 / 90
50.5% best7 / 90
Tax Agent BenchFinance
22.8%48 / 82
36.3% best15 / 82
LiveBench Data AnalysisReasoning
68.0%59 / 80
81.6% best5 / 80
LiveBench ReasoningReasoning
87.8%26 / 80
90.6% best11 / 80
Mystery Game PuzzlesReasoning
37.0%20 / 80
51.0% best15 / 80
Finance Agent (v2)Finance
59.0% best7 / 79
56.6%18 / 79
Code MigrationCoding
34.8%37 / 77
62.6% best6 / 77
EMBFinance
71.3% best13 / 75
67.1%18 / 75
FrontierMath-Tier-4-v2-PrivateMath
36.6%29 / 72
70.7% best17 / 72
LiveBench Agentic CodingAgentic
58.3%19 / 66
62.7% best9 / 66
LiveBench CodingCoding
78.9%27 / 66
80.7% best16 / 66