Inference
EN

GPT-5.4 vs Muse Spark 1.2

Change models
GPT-5.4OpenAI
Muse Spark 1.2Meta
IndexAll categories, out of 100.
64.8 ±2.5
64.9 ±3.3 best
GapIndex points below the top.
−0.1 · no clear gap
Top
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
38/s
123/s best
EloLMArena rating and rank.
1452
1484 best
ReleasedMonth of release.
2026-03
2026-08
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
62.7 best
CodingCode writing and repair.
61.8
64.3 best
ReasoningLogic problems and puzzles.
69.0 best
64.1
MultimodalTasks with images and text.
62.1
67.2 best
KnowledgeFacts and expert knowledge.
66.4 best
65.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
63.4
77.0 best
MathMath problems.
68.0 best
64.4

Benchmarks

31 shared
Only GPT-5.4: 68Only Muse Spark 1.2: 26
GPT-5.4
Muse Spark 1.2
Artificial Analysis Humanity's Last ExamKnowledge
43.7%31 / 222
45.5% best27 / 222
Artificial Analysis Long Context ReasoningReasoning
82.0% best29 / 217
79.0%58 / 217
Critical Physics TasksReasoning
23.4% best23 / 214
17.7%37 / 214
Artificial Analysis GPQA DiamondKnowledge
92.0% best22 / 199
90.4%33 / 199
Artificial Analysis Omniscience AccuracyKnowledge
50.8% best18 / 164
45.4%36 / 164
LegalBenchLegal
86.0% best17 / 149
85.3%22 / 149
TaxEval v2Finance
74.0%42 / 143
80.4% best1 / 143
MMLU ProKnowledge
87.5%26 / 135
88.3% best20 / 135
GDPval-AA normalizedAgentic
37.3%47 / 133
48.6% best28 / 133
CorpFin v2Finance
65.3%28 / 131
70.9% best5 / 131
Vibe Code Bench v1.1Coding
48.5%69 / 123
79.1% best32 / 123
MedScribeHealthcare
77.5%69 / 109
90.1% best5 / 109
MedCodeHealthcare
41.3%55 / 106
49.3% best24 / 106
MortgageTaxFinance
68.3% best17 / 97
65.4%43 / 97
MMMU ProMultimodal
87.5% best14 / 92
86.1%22 / 92
SimpleQA VerifiedKnowledge
45.1%43 / 91
60.3% best18 / 91
Chess PuzzlesReasoning
48.0% best19 / 90
27.0%52 / 90
SWE-benchCoding
78.2%30 / 87
86.6% best13 / 87
LiveBench Data AnalysisReasoning
79.3% best15 / 80
76.5%33 / 80
LiveBench ReasoningReasoning
88.1%25 / 80
90.0% best14 / 80