Inference
EN

Gemini 3.7 Flash vs Muse Wonder Full

Change models
Gemini 3.7 FlashGoogle
Muse Wonder FullMeta
IndexAll categories, out of 100.
68.5 ±2.2
77.3 ±5.3 best
GapIndex points below the top.
−8.8
Top
CoverageIndex weight that has results.
100% best
80%
SpeedOutput tokens per second.
85/s
—
EloLMArena rating and rank.
1489
—
ReleasedMonth of release.
2026-08
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.75
—
Output / 1MUS dollars per 1M output tokens.
$3.75
—
Batch output / 1MBatch price per 1M output tokens.
$1.88
—
1K chats2K tokens in, 500 out, each.
$3.38
—
1K documents20K tokens in, 1K out, each.
$18.75
—
1K agent tasks200K tokens in, 20K out, each.
$225.00
—
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
65.1
78.2 best
CodingCode writing and repair.
66.9
77.3 best
ReasoningLogic problems and puzzles.
68.7
75.6 best
MultimodalTasks with images and text.
67.7
—
KnowledgeFacts and expert knowledge.
71.2
71.7 best
MultilingualTasks in many languages.
72.3
—
InstructionTasks with strict prompt rules.
88.3
—
MathMath problems.
66.8
79.6 best

Benchmarks

26 shared
Only Gemini 3.7 Flash: 67Only Muse Wonder Full: 16
Gemini 3.7 Flash
Muse Wonder Full
Artificial Analysis Humanity's Last ExamKnowledge
47.9%18 / 222
53.6% best9 / 222
Artificial Analysis Long Context ReasoningReasoning
81.7%33 / 217
83.7% best10 / 217
Critical Physics TasksReasoning
14.3%52 / 214
32.9% best2 / 214
Artificial Analysis Omniscience AccuracyKnowledge
55.3% best12 / 164
41.0%46 / 164
LegalBenchLegal
87.3%6 / 149
87.4% best4 / 149
GDPval-AA normalizedAgentic
44.6%40 / 133
67.9% best2 / 133
Vibe Code Bench v1.1Coding
70.4%48 / 123
86.0% best14 / 123
Artificial Analysis SciCodeCoding
57.2%21 / 114
62.6% best4 / 114
MedScribeHealthcare
83.9%40 / 109
89.3% best8 / 109
MedCodeHealthcare
53.4% best9 / 106
49.9%18 / 106
Legal Research BenchLegal
34.6%49 / 90
53.4% best6 / 90
Tax Agent BenchFinance
22.8%48 / 82
43.0% best8 / 82
Finance Agent (v2)Finance
59.0%7 / 79
59.1% best6 / 79
Code MigrationCoding
34.8%37 / 77
61.0% best7 / 77
EMBFinance
71.3%13 / 75
71.9% best10 / 75
ProgramBenchCoding
0.0%34 / 65
0.5% best19 / 65
Terminal-Bench 4.0Agentic
12.1%42 / 61
58.1% best6 / 61
DeepSWEAgentic
65.3%34 / 59
79.0% best1 / 59
Agent Arena steerabilityAgentic
−7.342 / 54
9.6 best12 / 54
Agent Arena task outcomeAgentic
−3.538 / 54
11.1 best9 / 54