GPT-5.4 vs Muse Spark Open

Change models
GPT-5.4OpenAI
IndexAll categories, out of 100.
64.3 ±2.5
64.7 ±3.9 best
GapIndex points below the top.
−0.4 · no clear gap
Top
CoverageIndex weight that has results.
95% best
90%
SpeedOutput tokens per second.
38/s
65/s best
EloLMArena rating and rank.
1453
—
ReleasedMonth of release.
2026-03
2026-10
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.
61.8
64.5 best
CodingCode writing and repair.
60.5
62.8 best
ReasoningLogic problems and puzzles.
68.7 best
62.0
MultimodalTasks with images and text.
61.8
69.4 best
KnowledgeFacts and expert knowledge.
66.9 best
65.1
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
63.1
—
MathMath problems.
67.6 best
64.5

Benchmarks

26 shared
Only GPT-5.4: 75Only Muse Spark Open: 19
GPT-5.4
Muse Spark Open
43.7%31 / 222
43.9% best30 / 222
82.0% best29 / 217
78.3%63 / 217
93.3% best19 / 217
88.6%53 / 217
23.4% best23 / 214
14.9%51 / 214
95.3%46 / 200
98.1% best31 / 200
92.0% best22 / 199
89.0%48 / 199
50.8% best18 / 167
42.0%46 / 167
37.3%47 / 133
45.1% best39 / 133
74.0% best24 / 131
57.5%46 / 131
93.7% best26 / 126
89.0%39 / 126
48.5%71 / 125
76.2% best43 / 125
84.2% best20 / 122
57.2%44 / 122
96.4% best25 / 116
94.0%38 / 116
78.4%37 / 113
80.9% best16 / 113
45.1%43 / 91
56.6% best22 / 91
78.6% best22 / 90
69.8%30 / 90
79.3% best15 / 80
60.2%72 / 80
88.1% best25 / 80
73.7%71 / 80
35.0% best36 / 77
21.2%51 / 77
49.0% best23 / 72
31.7%32 / 72