Kimi K2.5 (Reasoning) vs Muse Glimmer 30B
Change modelsKimi K2.5 (Reasoning)Moonshot AI
Muse Glimmer 30BMeta
IndexAll categories, out of 100.
53.0 ±4.0
53.0 ±4.3
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
—
90/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-01
2026-08
Input / 1MUS dollars per 1M input tokens.
$0.60
$0.30 best
Output / 1MUS dollars per 1M output tokens.
$3.00
$1.20 best
Batch output / 1MBatch price per 1M output tokens.
—
$0.96
1K chats2K tokens in, 500 out, each.
$2.70
$1.20 best
1K documents20K tokens in, 1K out, each.
$15.00
$7.20 best
1K agent tasks200K tokens in, 20K out, each.
$180.00
$84.00 best
ContextMaximum tokens in one request.
128K
131K best
AgenticMulti-step tasks with tools.
50.6
53.3 best
CodingCode writing and repair.
56.0 best
54.4
ReasoningLogic problems and puzzles.
52.1
53.2 best
MultimodalTasks with images and text.
53.9
54.0 best
KnowledgeFacts and expert knowledge.
55.5 best
48.7
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
54.6
61.0 best
MathMath problems.
52.2
53.5 best
Benchmarks
11 sharedOnly Kimi K2.5 (Reasoning): 12Only Muse Glimmer 30B: 10
Kimi K2.5 (Reasoning)
Muse Glimmer 30B