Inference
EN

GPT-6.1 Terra vs Muse Spark 1.3

Change models
GPT-6.1 TerraOpenAI
Muse Spark 1.3Meta
IndexAll categories, out of 100.
77.1 ±3.8 best
70.1 ±4.0
GapIndex points below the top.
Top
−7.0
CoverageIndex weight that has results.
90% best
85%
SpeedOutput tokens per second.
46/s
76/s best
EloLMArena rating and rank.
—
1491
ReleasedMonth of release.
2026-10
2026-09
Input / 1MUS dollars per 1M input tokens.
$1.00 best
$1.25
Output / 1MUS dollars per 1M output tokens.
$5.00
$4.25 best
Batch output / 1MBatch price per 1M output tokens.
$2.50
—
1K chats2K tokens in, 500 out, each.
$4.50 best
$4.63
1K documents20K tokens in, 1K out, each.
$25.00 best
$29.25
1K agent tasks200K tokens in, 20K out, each.
$300.00 best
$335.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
78.6 best
70.4
CodingCode writing and repair.
74.4 best
68.8
ReasoningLogic problems and puzzles.
81.3 best
68.1
MultimodalTasks with images and text.
73.2
—
KnowledgeFacts and expert knowledge.
70.5 best
67.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
84.4
MathMath problems.
76.9 best
68.6

Benchmarks

24 shared
Only GPT-6.1 Terra: 26Only Muse Spark 1.3: 35
GPT-6.1 Terra
Muse Spark 1.3
Artificial Analysis Humanity's Last ExamKnowledge
46.2%24 / 222
48.7% best15 / 222
Artificial Analysis Long Context ReasoningReasoning
82.7%23 / 217
83.0% best18 / 217
Critical Physics TasksReasoning
28.0% best16 / 214
24.9%21 / 214
OTIS Mock AIME 2024-2025Math
100.0% best1 / 200
99.2%19 / 200
Artificial Analysis Omniscience AccuracyKnowledge
47.6% best28 / 164
43.6%41 / 164
Vibe Code Bench v1.1Coding
84.0% best19 / 123
82.9%23 / 123
Artificial Analysis SciCodeCoding
55.1%28 / 114
58.8% best14 / 114
FrontierMath-Tiers-1-3-v2-PrivateMath
90.9% best5 / 90
74.0%25 / 90
Legal Research BenchLegal
26.0%62 / 90
40.9% best33 / 90
Tax Agent BenchFinance
17.1%58 / 82
37.9% best14 / 82
LiveBench Data AnalysisReasoning
82.3% best4 / 80
79.6%13 / 80
LiveBench ReasoningReasoning
88.7%20 / 80
89.7% best15 / 80
Mystery Game PuzzlesReasoning
74.0% best4 / 80
25.0%37 / 80
FrontierMath-Tier-4-v2-PrivateMath
92.7% best6 / 72
46.3%24 / 72
Terminal-Bench 4.0Agentic
49.5% best11 / 61
10.6%45 / 61
Agent Arena steerabilityAgentic
16.6 best4 / 54
2.622 / 54
Agent Arena task outcomeAgentic
9.7 best11 / 54
3.720 / 54
LiveBench Coding 2.0Coding
90.8% best11 / 52
90.2%13 / 52
LiveBench DesignAgentic
82.3% best8 / 52
74.8%30 / 52
LiveBench ResearchAgentic
73.9% best25 / 52
68.6%36 / 52