Inference
EN

GPT-5.6 Sol vs Muse Spark 1.3

Change models
GPT-5.6 SolOpenAI
Muse Spark 1.3Meta
IndexAll categories, out of 100.
73.0 ±1.9 best
70.1 ±4.0
GapIndex points below the top.
Top
−2.9 · no clear gap
CoverageIndex weight that has results.
100% best
85%
SpeedOutput tokens per second.
64/s
76/s best
EloLMArena rating and rank.
1457
1491 best
ReleasedMonth of release.
2026-07
2026-09
Input / 1MUS dollars per 1M input tokens.
$4.40
$1.25 best
Output / 1MUS dollars per 1M output tokens.
$22.00
$4.25 best
Batch output / 1MBatch price per 1M output tokens.
$10.00
—
1K chats2K tokens in, 500 out, each.
$19.80
$4.63 best
1K documents20K tokens in, 1K out, each.
$110.00
$29.25 best
1K agent tasks200K tokens in, 20K out, each.
$1,320.00
$335.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
71.9 best
70.4
CodingCode writing and repair.
70.4 best
68.8
ReasoningLogic problems and puzzles.
76.3 best
68.1
MultimodalTasks with images and text.
72.6
—
KnowledgeFacts and expert knowledge.
72.7 best
67.5
MultilingualTasks in many languages.
66.4
—
InstructionTasks with strict prompt rules.
64.5
84.4 best
MathMath problems.
75.1 best
68.6

Benchmarks

52 shared
Only GPT-5.6 Sol: 73Only Muse Spark 1.3: 7
GPT-5.6 Sol
Muse Spark 1.3
Artificial Analysis Humanity's Last ExamKnowledge
49.5% best13 / 222
48.7%15 / 222
Artificial Analysis Long Context ReasoningReasoning
84.0% best8 / 217
83.0%18 / 217
Critical Physics TasksReasoning
32.3% best3 / 214
24.9%21 / 214
OTIS Mock AIME 2024-2025Math
100.0% best1 / 200
99.2%19 / 200
Artificial Analysis GPQA DiamondKnowledge
94.1% best5 / 199
93.5%8 / 199
Artificial Analysis Omniscience AccuracyKnowledge
59.4% best8 / 164
43.6%41 / 164
GDPval-AA normalizedAgentic
55.4%19 / 133
59.0% best10 / 133
Vibe Code Bench v1.1Coding
80.5%31 / 123
82.9% best23 / 123
Artificial Analysis SciCodeCoding
57.1%22 / 114
58.8% best14 / 114
Chess PuzzlesReasoning
59.0% best10 / 90
37.0%39 / 90
FrontierMath-Tiers-1-3-v2-PrivateMath
89.1% best9 / 90
74.0%25 / 90
Legal Research BenchLegal
48.1% best12 / 90
40.9%33 / 90
Terminal-Bench 2.1 · BenchLMAgentic
91.9% best2 / 86
88.8%7 / 86
Tax Agent BenchFinance
31.1%29 / 82
37.9% best14 / 82
LiveBench Data AnalysisReasoning
79.8% best12 / 80
79.6%13 / 80
LiveBench ReasoningReasoning
91.7% best5 / 80
89.7%15 / 80
Mystery Game PuzzlesReasoning
58.0% best10 / 80
25.0%37 / 80
Finance Agent (v2)Finance
53.8%31 / 79
58.9% best8 / 79
Code MigrationCoding
52.9% best12 / 77
27.6%44 / 77
EMBFinance
72.3% best7 / 75
62.7%31 / 75