Hy4 vs Muse Spark 1.3

Change models
Hy4Tencent
IndexAll categories, out of 100.
72.0 ±7.8 best
70.1 ±4.0
GapIndex points below the top.
Top
−1.9 · no clear gap
CoverageIndex weight that has results.
65%
85% best
SpeedOutput tokens per second.
52/s
76/s best
EloLMArena rating and rank.
—
1491
ReleasedMonth of release.
2026-11
2026-09
Input / 1MUS dollars per 1M input tokens.
$0.417 best
$1.25
Output / 1MUS dollars per 1M output tokens.
$1.25 best
$4.25
1K chats2K tokens in, 500 out, each.
$1.46 best
$4.63
1K documents20K tokens in, 1K out, each.
$9.59 best
$29.25
1K agent tasks200K tokens in, 20K out, each.
$108.41 best
$335.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
74.5 best
70.4
CodingCode writing and repair.
68.4
68.8 best
ReasoningLogic problems and puzzles.
—
68.1
MultimodalTasks with images and text.
57.4
—
KnowledgeFacts and expert knowledge.
83.7 best
67.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
84.4
MathMath problems.
—
68.6

Benchmarks

8 shared
Only Hy4: 13Only Muse Spark 1.3: 51
Hy4
Muse Spark 1.3
81.0%30 / 123
82.9% best23 / 123
41.3% best30 / 90
40.9%33 / 90
34.4%17 / 82
37.9% best14 / 82
39.4% best15 / 61
10.6%45 / 61
DeepSWEAgentic
74.9%8 / 59
75.4% best6 / 59
8.8 best14 / 54
2.622 / 54
6.7 best12 / 54
3.720 / 54
56.2% best4 / 32
49.4%14 / 32