readable AI benchmarks

Meta

Muse Glimmer (high)

reasoning · open weights · Aug 10, 2026

Quality Score34.2
Value Score34.0
Reliability33.6
Cache Discount88%

Model specification

Reasoning
reasoning
Input modalities
text, image
Output modalities
text
Context window
131,072 tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.325
Output
$1.35
Cached Input
$0.040
Cached Output
not available
Cost per task
$0.073

Capability

Intelligence
35.1
Coding
49.0
Agentic
22.9
Omniscience
-32.9
Correct
27.0%
Blended price
$0.228

Answer outcomes

Correct 27.0%Incorrect 59.8%Abstained 13.2%

Artificial Analysis benchmarks

GDPval-AA v2
23%
τ³-Banking
24%
Terminal-Bench v2.1
52%
SciCode
44%
Humanity’s Last Exam
22%
GPQA Diamond
84%
CritPt
3%
AA-Omniscience
34%
AA-LCR
80%

Similar models