Inference
EN

GPT-5.4 vs Muse Spark 1.1

Change models
GPT-5.4OpenAI
Muse Spark 1.1Meta
IndexAll categories, out of 100.
64.8 ±2.5 best
64.6 ±3.1
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
38/s
152/s best
EloLMArena rating and rank.
1452
1479 best
ReleasedMonth of release.
2026-03
2026-07
Input / 1MUS dollars per 1M input tokens.
$2.50
$1.25 best
Output / 1MUS dollars per 1M output tokens.
$15.00
$4.25 best
Batch output / 1MBatch price per 1M output tokens.
$7.50
—
1K chats2K tokens in, 500 out, each.
$12.50
$4.63 best
1K documents20K tokens in, 1K out, each.
$65.00
$29.25 best
1K agent tasks200K tokens in, 20K out, each.
$800.00
$335.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
62.1 best
61.9
CodingCode writing and repair.
61.8
64.8 best
ReasoningLogic problems and puzzles.
69.0 best
63.0
MultimodalTasks with images and text.
62.1
66.5 best
KnowledgeFacts and expert knowledge.
66.4
67.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
63.4
67.5 best
MathMath problems.
68.0 best
61.2

Benchmarks

43 shared
Only GPT-5.4: 56Only Muse Spark 1.1: 16
GPT-5.4
Muse Spark 1.1
Artificial Analysis Humanity's Last ExamKnowledge
43.7%31 / 222
46.2% best24 / 222
Artificial Analysis Long Context ReasoningReasoning
82.0% best29 / 217
77.7%74 / 217
Critical Physics TasksReasoning
23.4% best23 / 214
15.1%50 / 214
Artificial Analysis GPQA DiamondKnowledge
92.0% best22 / 199
89.8%38 / 199
Artificial Analysis Omniscience AccuracyKnowledge
50.8%18 / 164
52.1% best14 / 164
LegalBenchLegal
86.0% best17 / 149
85.0%27 / 149
TaxEval v2Finance
74.0%42 / 143
79.7% best2 / 143
LiveCodeBenchCoding
84.1%40 / 142
85.9% best25 / 142
GPQA Diamond · Vals AIKnowledge
91.7% best18 / 135
91.2%23 / 135
MMLU ProKnowledge
87.5%26 / 135
88.7% best17 / 135
GDPval-AA normalizedAgentic
37.3% best47 / 133
35.6%50 / 133
CorpFin v2Finance
65.3%28 / 131
71.3% best4 / 131
Vibe Code Bench v1.1Coding
48.5%69 / 123
72.2% best46 / 123
MedScribeHealthcare
77.5%69 / 109
88.9% best9 / 109
MortgageTaxFinance
68.3% best17 / 97
66.1%37 / 97
MMMU ProMultimodal
87.5% best14 / 92
86.6%18 / 92
SimpleQA VerifiedKnowledge
45.1%43 / 91
57.8% best20 / 91
Chess PuzzlesReasoning
48.0% best19 / 90
34.0%47 / 90
SWE-benchCoding
78.2%30 / 87
82.0% best21 / 87
SWE-bench ProCoding
57.7%41 / 83
61.5% best28 / 83