MAI-Thinking-1 vs Muse Glimmer 30B

Change models
IndexAll categories, out of 100.
52.8 ±8.1 best
52.5 ±4.3
GapIndex points below the top.
Top
−0.3 · no clear gap
CoverageIndex weight that has results.
70%
95% best
SpeedOutput tokens per second.
—
116/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-06
2026-08
Input / 1MUS dollars per 1M input tokens.
—
$0.35
Output / 1MUS dollars per 1M output tokens.
—
$1.50
Batch output / 1MBatch price per 1M output tokens.
—
$0.96
1K chats2K tokens in, 500 out, each.
—
$1.45
1K documents20K tokens in, 1K out, each.
—
$8.50
1K agent tasks200K tokens in, 20K out, each.
—
$100.00
ContextMaximum tokens in one request.
256K best
131K
AgenticMulti-step tasks with tools.
45.3
52.5 best
CodingCode writing and repair.
54.5 best
53.8
ReasoningLogic problems and puzzles.
—
52.4
MultimodalTasks with images and text.
—
53.6
KnowledgeFacts and expert knowledge.
52.7 best
48.8
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
67.1 best
60.0
MathMath problems.
52.0
52.8 best

Benchmarks

4 shared
Only MAI-Thinking-1: 8Only Muse Glimmer 30B: 17
MAI-Thinking-1
Muse Glimmer 30B
73.5%52 / 114
76.0% best43 / 114
52.8% best62 / 83
51.2%68 / 83
85.0% best2 / 57
77.0%22 / 57
94.5%19 / 34
94.7% best18 / 34