readable AI benchmarks

Meta

Muse Spark 1.2 (xhigh)

reasoning · closed weights · Aug 5, 2026

Quality Score68.6
Value Score50.0
Reliability63.6
Cache Discount88%

Model specification

Reasoning
reasoning
Input modalities
text, image, video, speech
Output modalities
text
Context window
1,048,576 tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$1.25
Output
$4.25
Cached Input
$0.150
Cached Output
not available
Cost per task
$0.399

Capability

Intelligence
56.8
Coding
72.2
Agentic
49.3
Omniscience
27.2
Correct
45.4%
Blended price
$0.780

Answer outcomes

Correct 45.4%Incorrect 18.2%Abstained 36.4%

Artificial Analysis benchmarks

GDPval-AA v2
56%
τ³-Banking
35%
Terminal-Bench v2.1
80%
SciCode
56%
Humanity’s Last Exam
45%
GPQA Diamond
90%
CritPt
18%
AA-Omniscience
64%
AA-LCR
83%

Similar models