Meta
muse-spark
proprietaryMultimodal
Benchmark Average (0–100)
76.4%
Average of non-null benchmark scores across all evaluated tasks.
BENCHMARK SCORES
GPQA89.5%
Graduate-Level Google-Proof Q&A. PhD-level multiple-choice questions in chemistry, biology, and physics. Scored by accuracy.
SWE-bench Verified77.4%
SWE-bench Verified evaluates models on real-world software engineering tasks from GitHub issues.
HLE58.4%
Humanity's Last Exam (HLE) is a multi-modal benchmark testing frontier knowledge across mathematics, humanities, and natural sciences with 2,500 expert-level questions.
MMMU-Pro80.4%
MMMU-Pro is a more challenging version of MMMU with harder multimodal understanding tasks.
OTHER BENCHMARKS
ARC-AGI v2
42.5%
CharXIV-R
86.4%
ScreenSpot Pro
84.1%
MODEL INFO
Organization
Meta
Context Window
—
Release Date
2026-04-08
Knowledge Cutoff
—
Parameters
—
License
proprietary
METADATA
Announcement Date
2026-04-08
Organization Country
US
Canonical ID
—