GPT-5.6 Terra vs Muse Spark 1.3

Change models
IndexAll categories, out of 100.
68.9 ±2.0
70.1 ±4.0 best
GapIndex points below the top.
−1.2 · no clear gap
Top
CoverageIndex weight that has results.
100% best
85%
SpeedOutput tokens per second.
66/s
76/s best
EloLMArena rating and rank.
1449
1491 best
ReleasedMonth of release.
2026-07
2026-09
Input / 1MUS dollars per 1M input tokens.
$2.00
$1.25 best
Output / 1MUS dollars per 1M output tokens.
$12.00
$4.25 best
Batch output / 1MBatch price per 1M output tokens.
$6.00
—
1K chats2K tokens in, 500 out, each.
$10.00
$4.63 best
1K documents20K tokens in, 1K out, each.
$52.00
$29.25 best
1K agent tasks200K tokens in, 20K out, each.
$640.00
$335.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
68.2
70.4 best
CodingCode writing and repair.
68.4
68.8 best
ReasoningLogic problems and puzzles.
72.5 best
68.1
MultimodalTasks with images and text.
67.3
—
KnowledgeFacts and expert knowledge.
65.5
67.5 best
MultilingualTasks in many languages.
60.7
—
InstructionTasks with strict prompt rules.
56.4
84.4 best
MathMath problems.
72.8 best
68.6

Benchmarks

50 shared
Only GPT-5.6 Terra: 59Only Muse Spark 1.3: 9
GPT-5.6 Terra
Muse Spark 1.3
42.9%34 / 222
48.7% best15 / 222
83.0%18 / 217
83.0%18 / 217
30.0% best10 / 214
24.9%21 / 214
99.7% best14 / 200
99.2%19 / 200
92.5%18 / 199
93.5% best8 / 199
46.8% best31 / 164
43.6%41 / 164
47.6%33 / 133
59.0% best10 / 133
74.6%44 / 123
82.9% best23 / 123
55.0%29 / 114
58.8% best14 / 114
Chess PuzzlesReasoning
47.0% best24 / 90
37.0%39 / 90
86.0% best13 / 90
74.0%25 / 90
41.3% best30 / 90
40.9%33 / 90
87.4%14 / 86
88.8% best7 / 86
30.0%34 / 82
37.9% best14 / 82
79.3%15 / 80
79.6% best13 / 80
90.6% best11 / 80
89.7%15 / 80
35.0% best23 / 80
25.0%37 / 80
54.4%27 / 79
58.9% best8 / 79
47.8% best13 / 77
27.6%44 / 77
EMBFinance
66.2% best23 / 75
62.7%31 / 75