Inference
EN

GPT-6.1 Terra vs Muse Wonder Full

Change models
GPT-6.1 TerraOpenAI
Muse Wonder FullMeta
IndexAll categories, out of 100.
77.1 ±3.8
77.3 ±5.3 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
90% best
80%
SpeedOutput tokens per second.
46/s
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-10
2026-10
Input / 1MUS dollars per 1M input tokens.
$1.00
—
Output / 1MUS dollars per 1M output tokens.
$5.00
—
Batch output / 1MBatch price per 1M output tokens.
$2.50
—
1K chats2K tokens in, 500 out, each.
$4.50
—
1K documents20K tokens in, 1K out, each.
$25.00
—
1K agent tasks200K tokens in, 20K out, each.
$300.00
—
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
78.6 best
78.2
CodingCode writing and repair.
74.4
77.3 best
ReasoningLogic problems and puzzles.
81.3 best
75.6
MultimodalTasks with images and text.
73.2
—
KnowledgeFacts and expert knowledge.
70.5
71.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
76.9
79.6 best

Benchmarks

18 shared
Only GPT-6.1 Terra: 32Only Muse Wonder Full: 24
GPT-6.1 Terra
Muse Wonder Full
Artificial Analysis Humanity's Last ExamKnowledge
46.2%24 / 222
53.6% best9 / 222
Artificial Analysis Long Context ReasoningReasoning
82.7%23 / 217
83.7% best10 / 217
Critical Physics TasksReasoning
28.0%16 / 214
32.9% best2 / 214
Artificial Analysis Omniscience AccuracyKnowledge
47.6% best28 / 164
41.0%46 / 164
Vibe Code Bench v1.1Coding
84.0%19 / 123
86.0% best14 / 123
Artificial Analysis SciCodeCoding
55.1%28 / 114
62.6% best4 / 114
Legal Research BenchLegal
26.0%62 / 90
53.4% best6 / 90
Tax Agent BenchFinance
17.1%58 / 82
43.0% best8 / 82
Terminal-Bench 4.0Agentic
49.5%11 / 61
58.1% best6 / 61
Agent Arena steerabilityAgentic
16.6 best4 / 54
9.612 / 54
Agent Arena task outcomeAgentic
9.711 / 54
11.1 best9 / 54
MazeBench: visual spatial reasoning in a 3D open worldAgentic
16.0%4 / 48
17.0% best2 / 48
HLAB-Vals-1.1Legal
1.7%35 / 35
23.3% best5 / 35
Artificial Analysis AutomationBenchAgentic
60.2% best12 / 23
45.4%21 / 23
Artificial Analysis GDP.pdfAgentic
28.6%6 / 22
32.6% best1 / 22
Artificial Analysis Terminal-Bench v4.0Agentic
55.6%9 / 22
57.1% best7 / 22
Medical Long Context Reasoning (MLCR-AA)Reasoning
30.6% best8 / 22
22.2%12 / 22
HealthBench ProfessionalKnowledge
62.7% best6 / 18
62.3%7 / 18