GPT-6 Luna vs Muse Ember

Change models
IndexAll categories, out of 100.
64.9 ±2.1 best
64.8 ±6.7
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
100% best
80%
SpeedOutput tokens per second.
61/s
174/s best
EloLMArena rating and rank.
1388
—
ReleasedMonth of release.
2026-09
2026-11
Input / 1MUS dollars per 1M input tokens.
$0.10
$0.10
Output / 1MUS dollars per 1M output tokens.
$0.50
$0.50
Batch output / 1MBatch price per 1M output tokens.
$0.25
—
1K chats2K tokens in, 500 out, each.
$0.45
$0.45
1K documents20K tokens in, 1K out, each.
$2.50
$2.50
1K agent tasks200K tokens in, 20K out, each.
$30.00
$30.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
66.5
69.3 best
CodingCode writing and repair.
66.0
72.2 best
ReasoningLogic problems and puzzles.
64.1 best
63.4
MultimodalTasks with images and text.
64.8
66.5 best
KnowledgeFacts and expert knowledge.
61.6 best
37.5
MultilingualTasks in many languages.
53.2
—
InstructionTasks with strict prompt rules.
39.9
—
MathMath problems.
68.2
—

Benchmarks

19 shared
Only GPT-6 Luna: 84Only Muse Ember: 1
GPT-6 Luna
Muse Ember
39.6% best56 / 167
21.1%128 / 167
81.6%28 / 125
83.7% best23 / 125
30.3%56 / 92
49.0% best11 / 92
19.9%57 / 84
38.2% best15 / 84
13.6%42 / 63
39.4% best17 / 63
2.321 / 56
9.8 best11 / 56
−0.4 best32 / 54
−7.642 / 54
0.0%26 / 52
0.0%26 / 52
15.2%32 / 44
30.6% best21 / 44
4.2%32 / 37
25.0% best2 / 37
53.2%18 / 24
68.1% best10 / 24
22.8%15 / 23
22.8%15 / 23
12.6%21 / 23
40.9% best15 / 23
26.1% best9 / 22
18.3%17 / 22
73.5%12 / 19
74.5% best9 / 19
57.1%
61.6%
20.2%
37.8%
25.2%
27.2%
62.8%
80.6%