GPT-6 Astra vs Muse Spark 1.3

Change models
IndexAll categories, out of 100.
78.0 ±1.9 best
70.1 ±4.0
GapIndex points below the top.
Top
−7.9
CoverageIndex weight that has results.
100% best
85%
SpeedOutput tokens per second.
34/s
76/s best
EloLMArena rating and rank.
1440
1491 best
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$10.00
$1.25 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$4.25 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
—
1K chats2K tokens in, 500 out, each.
$45.00
$4.63 best
1K documents20K tokens in, 1K out, each.
$250.00
$29.25 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$335.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
74.6 best
70.4
CodingCode writing and repair.
76.9 best
68.8
ReasoningLogic problems and puzzles.
83.8 best
68.1
MultimodalTasks with images and text.
71.2
—
KnowledgeFacts and expert knowledge.
78.5 best
67.5
MultilingualTasks in many languages.
73.6
—
InstructionTasks with strict prompt rules.
79.5
84.4 best
MathMath problems.
78.0 best
68.6

Benchmarks

53 shared
Only GPT-6 Astra: 85Only Muse Spark 1.3: 6
GPT-6 Astra
Muse Spark 1.3
54.7% best8 / 222
48.7%15 / 222
80.7%37 / 217
83.0% best18 / 217
31.7% best4 / 214
24.9%21 / 214
100.0% best1 / 200
99.2%19 / 200
96.1% best1 / 199
93.5%8 / 199
61.6% best6 / 164
43.6%41 / 164
53.7%25 / 133
59.0% best10 / 133
89.6% best8 / 123
82.9%23 / 123
56.5%24 / 114
58.8% best14 / 114
Chess PuzzlesReasoning
74.0% best3 / 90
37.0%39 / 90
93.7% best2 / 90
74.0%25 / 90
39.4%37 / 90
40.9% best33 / 90
20.7%52 / 82
37.9% best14 / 82
83.0% best2 / 80
79.6%13 / 80
92.7% best2 / 80
89.7%15 / 80
84.0% best2 / 80
25.0%37 / 80
53.5%33 / 79
58.9% best8 / 79
67.7% best3 / 77
27.6%44 / 77
EMBFinance
71.7% best11 / 75
62.7%31 / 75
87.3% best2 / 75
72.3%24 / 75