GPT-5.6 Luna vs Muse Spark Open

Change models
IndexAll categories, out of 100.
65.5 ±2.1 best
65.1 ±3.9
GapIndex points below the top.
Top
−0.4 · no clear gap
CoverageIndex weight that has results.
100% best
90%
SpeedOutput tokens per second.
51/s
86/s best
EloLMArena rating and rank.
1431
—
ReleasedMonth of release.
2026-07
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.20 best
$1.25
Output / 1MUS dollars per 1M output tokens.
$1.20 best
$4.25
Batch output / 1MBatch price per 1M output tokens.
$0.60
—
1K chats2K tokens in, 500 out, each.
$1.00 best
$4.63
1K documents20K tokens in, 1K out, each.
$5.20 best
$29.25
1K agent tasks200K tokens in, 20K out, each.
$64.00 best
$335.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
64.7
64.8 best
CodingCode writing and repair.
67.4 best
63.3
ReasoningLogic problems and puzzles.
66.3 best
62.3
MultimodalTasks with images and text.
65.8
69.8 best
KnowledgeFacts and expert knowledge.
62.1
65.4 best
MultilingualTasks in many languages.
53.1
—
InstructionTasks with strict prompt rules.
48.2
—
MathMath problems.
68.4 best
64.9

Benchmarks

34 shared
Only GPT-5.6 Luna: 68Only Muse Spark Open: 11
GPT-5.6 Luna
Muse Spark Open
39.5%49 / 222
43.9% best30 / 222
83.7% best10 / 217
78.3%63 / 217
91.6% best31 / 217
88.6%52 / 217
20.6% best29 / 214
14.9%51 / 214
98.3% best28 / 200
98.1%31 / 200
91.1% best27 / 199
89.0%48 / 199
42.7% best42 / 164
42.0%44 / 164
48.0% best30 / 133
45.1%39 / 133
59.5% best43 / 131
57.5%46 / 131
88.0%42 / 126
89.0% best39 / 126
77.1% best39 / 123
76.2%41 / 123
60.2% best38 / 122
57.2%44 / 122
90.8%43 / 116
94.0% best38 / 116
53.6%38 / 114
58.4% best17 / 114
78.6%33 / 113
80.9% best16 / 113
41.0%51 / 91
56.6% best22 / 91
82.1% best18 / 90
69.8%30 / 90
36.5%46 / 90
38.5% best39 / 90
24.8%46 / 82
26.3% best42 / 82
78.0% best28 / 80
60.2%72 / 80