Inference
EN

GPT-6 Sol vs Muse Wonder Full

Change models
GPT-6 SolOpenAI
Muse Wonder FullMeta
IndexAll categories, out of 100.
72.8 ±2.2
77.3 ±5.3 best
GapIndex points below the top.
−4.5 · no clear gap
Top
CoverageIndex weight that has results.
100% best
80%
SpeedOutput tokens per second.
61/s
—
EloLMArena rating and rank.
1397
—
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.
68.6
78.2 best
CodingCode writing and repair.
73.9
77.3 best
ReasoningLogic problems and puzzles.
76.1 best
75.6
MultimodalTasks with images and text.
70.1
—
KnowledgeFacts and expert knowledge.
71.9 best
71.7
MultilingualTasks in many languages.
65.5
—
InstructionTasks with strict prompt rules.
65.3
—
MathMath problems.
75.8
79.6 best

Benchmarks

31 shared
Only GPT-6 Sol: 63Only Muse Wonder Full: 11
GPT-6 Sol
Muse Wonder Full
Artificial Analysis Humanity's Last ExamKnowledge
47.9%18 / 222
53.6% best9 / 222
Artificial Analysis Long Context ReasoningReasoning
83.7%10 / 217
83.7%10 / 217
Critical Physics TasksReasoning
30.9%8 / 214
32.9% best2 / 214
Artificial Analysis Omniscience AccuracyKnowledge
54.5% best13 / 164
41.0%46 / 164
GDPval-AA normalizedAgentic
50.4%27 / 133
67.9% best2 / 133
Vibe Code Bench v1.1Coding
87.8% best12 / 123
86.0%14 / 123
Artificial Analysis SciCodeCoding
57.6%18 / 114
62.6% best4 / 114
MedScribeHealthcare
82.0%52 / 109
89.3% best8 / 109
MedCodeHealthcare
47.1%36 / 106
49.9% best18 / 106
Legal Research BenchLegal
28.8%57 / 90
53.4% best6 / 90
Tax Agent BenchFinance
15.0%62 / 82
43.0% best8 / 82
Finance Agent (v2)Finance
49.0%48 / 79
59.1% best6 / 79
Code MigrationCoding
57.2%9 / 77
61.0% best7 / 77
EMBFinance
71.5%12 / 75
71.9% best10 / 75
ProgramBenchCoding
2.0% best11 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
44.4%13 / 61
58.1% best6 / 61
DeepSWEAgentic
68.8%24 / 59
79.0% best1 / 59
Agent Arena steerabilityAgentic
10.1 best11 / 54
9.612 / 54
Agent Arena task outcomeAgentic
4.517 / 54
11.1 best9 / 54
ProofBench v1.1Math
83.0%16 / 54
94.0% best11 / 54