GPT-5.6 Luna vs Muse Spark 1.2

Change models
IndexAll categories, out of 100.
65.5 ±2.1 best
64.9 ±3.3
GapIndex points below the top.
Top
−0.6 · no clear gap
CoverageIndex weight that has results.
100% best
95%
SpeedOutput tokens per second.
51/s
123/s best
EloLMArena rating and rank.
1431
1484 best
ReleasedMonth of release.
2026-07
2026-08
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 best
62.7
CodingCode writing and repair.
67.4 best
64.3
ReasoningLogic problems and puzzles.
66.3 best
64.1
MultimodalTasks with images and text.
65.8
67.2 best
KnowledgeFacts and expert knowledge.
62.1
65.2 best
MultilingualTasks in many languages.
53.1
—
InstructionTasks with strict prompt rules.
48.2
77.0 best
MathMath problems.
68.4 best
64.4

Benchmarks

54 shared
Only GPT-5.6 Luna: 48Only Muse Spark 1.2: 3
GPT-5.6 Luna
Muse Spark 1.2
39.5%49 / 222
45.5% best27 / 222
83.7% best10 / 217
79.0%58 / 217
20.6% best29 / 214
17.7%37 / 214
91.1% best27 / 199
90.4%33 / 199
42.7%42 / 164
45.4% best36 / 164
84.0%43 / 149
85.3% best22 / 149
TaxEval v2Finance
76.2%6 / 143
80.4% best1 / 143
MMLU ProKnowledge
86.0%50 / 135
88.3% best20 / 135
48.0%30 / 133
48.6% best28 / 133
CorpFin v2Finance
64.2%38 / 131
70.9% best5 / 131
77.1%39 / 123
79.1% best32 / 123
53.6%38 / 114
57.4% best19 / 114
MedScribeHealthcare
84.4%36 / 109
90.1% best5 / 109
MedCodeHealthcare
42.4%51 / 106
49.3% best24 / 106
67.3% best26 / 97
65.4%43 / 97
MMMU ProMultimodal
85.0%25 / 92
86.1% best22 / 92
41.0%51 / 91
60.3% best18 / 91
Chess PuzzlesReasoning
43.0% best31 / 90
27.0%52 / 90
36.5%46 / 90
43.8% best25 / 90
SWE-benchCoding
93.0% best9 / 87
86.6%13 / 87