Inference
EN

GPT-6.1 Sol vs Muse Wonder Full

Change models
GPT-6.1 SolOpenAI
Muse Wonder FullMeta
IndexAll categories, out of 100.
78.0 ±2.2 best
77.3 ±5.3
GapIndex points below the top.
Top
−0.7 · no clear gap
CoverageIndex weight that has results.
100% best
80%
SpeedOutput tokens per second.
34/s
—
EloLMArena rating and rank.
1446
—
ReleasedMonth of release.
2026-09
2026-10
Input / 1MUS dollars per 1M input tokens.
$2.00
—
Output / 1MUS dollars per 1M output tokens.
$10.00
—
Batch output / 1MBatch price per 1M output tokens.
$5.00
—
1K chats2K tokens in, 500 out, each.
$9.00
—
1K documents20K tokens in, 1K out, each.
$50.00
—
1K agent tasks200K tokens in, 20K out, each.
$600.00
—
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
76.0
78.2 best
CodingCode writing and repair.
75.8
77.3 best
ReasoningLogic problems and puzzles.
81.8 best
75.6
MultimodalTasks with images and text.
72.2
—
KnowledgeFacts and expert knowledge.
78.0 best
71.7
MultilingualTasks in many languages.
73.2
—
InstructionTasks with strict prompt rules.
76.6
—
MathMath problems.
78.2
79.6 best

Benchmarks

36 shared
Only GPT-6.1 Sol: 62Only Muse Wonder Full: 6
GPT-6.1 Sol
Muse Wonder Full
Artificial Analysis Humanity's Last ExamKnowledge
52.9%10 / 222
53.6% best9 / 222
Artificial Analysis Long Context ReasoningReasoning
83.0%18 / 217
83.7% best10 / 217
Critical Physics TasksReasoning
31.7%4 / 214
32.9% best2 / 214
Artificial Analysis Omniscience AccuracyKnowledge
61.8% best5 / 164
41.0%46 / 164
GDPval-AA normalizedAgentic
54.8%22 / 133
67.9% best2 / 133
Vibe Code Bench v1.1Coding
88.9% best10 / 123
86.0%14 / 123
Artificial Analysis SciCodeCoding
54.2%35 / 114
62.6% best4 / 114
MedScribeHealthcare
86.5%22 / 109
89.3% best8 / 109
MedCodeHealthcare
48.8%28 / 106
49.9% best18 / 106
Legal Research BenchLegal
38.5%39 / 90
53.4% best6 / 90
Tax Agent BenchFinance
21.8%49 / 82
43.0% best8 / 82
Finance Agent (v2)Finance
52.0%37 / 79
59.1% best6 / 79
Code MigrationCoding
65.1% best5 / 77
61.0%7 / 77
EMBFinance
70.8%14 / 75
71.9% best10 / 75
ProgramBenchCoding
3.0% best6 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
55.1%9 / 61
58.1% best6 / 61
DeepSWEAgentic
71.9%18 / 59
79.0% best1 / 59
Agent Arena steerabilityAgentic
13.4 best8 / 54
9.612 / 54
Agent Arena task outcomeAgentic
11.7 best8 / 54
11.19 / 54
ProofBench v1.1Math
99.0% best6 / 54
94.0%11 / 54