benchgap
Meta · model

Muse Spark 1.2 benchmark scores

As of 2026-11-22, Muse Spark 1.2 (Meta) has measured scores on 24 benchmarks and estimated scores on 118 more.

BenchmarkScoreSource
AA-GPQA Diamond90.4%measured
AA-HLE45.5%measured
AA-SciCode57.4%measured
Artificial Analysis Intelligence Index39.6%measured
CritPt17.7%measured
GDPval-AA48.6%measured
GPQA Diamond92.0%estimated ± 1.9 pp, high confidence
HLE52.4%estimated ± 8.5 pp, medium confidence
AA-LCR79.0%measured
LiveCodeBench v688.4%estimated ± 4.7 pp, high confidence
AA-Omniscience Accuracy45.4%measured
SciCode57.0%estimated ± 3.1 pp, high confidence
Terminal-Bench 2.182.9%measured
BrowseComp77.2%estimated ± 8.8 pp, medium confidence
HLE w/ tools57.3%estimated ± 5.3 pp, medium confidence
LongBench v264.8%estimated ± 5.5 pp, medium confidence
AA Coding Index72.2%measured
APEX-Agents41.3%estimated ± 9.4 pp, low confidence
APEX-Agents-AA25.4%estimated ± 9.3 pp, medium confidence
BioMysteryBench (human-difficult)47.5%estimated ± 6.8 pp, low confidence
DeepSearchQA92.5%estimated ± 4.5 pp, high confidence
SWE-bench Verified85.3%estimated ± 4.4 pp, high confidence
BFCL v476.5%estimated ± 2.7 pp, medium confidence
CyberGym79.3%estimated ± 5.3 pp, medium confidence
JobBench51.6%estimated ± 8.7 pp, medium confidence
SWE-bench Pro59.8%estimated ± 4.8 pp, high confidence
WideResearch78.8%estimated ± 3.3 pp, high confidence
AA Agentic Index44.0%measured
MMLU-Pro86.7%estimated ± 4.8 pp, high confidence
FailureSensorIQ67.2%estimated ± 1.7 pp, high confidence
GPQA92.4%estimated ± 5.1 pp, medium confidence
MMLU90.5%estimated ± 0.9 pp, medium confidence
Vals GPQA Diamond89.5%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench87.4%estimated ± 5.7 pp, low confidence
Vals MMLU-Pro88.3%measured
MMMLU90.6%estimated ± 0.7 pp, low confidence
Chess Puzzles27.0%measured
AA MMLU-Pro88.0%estimated ± 0.8 pp, high confidence
Gert Labs45.2%measured
AA-AnalystAgent44.8%estimated ± 5.9 pp, low confidence
AA EnterpriseOps-Gym47.3%measured
AA Harvey LAB v1.092.9%estimated ± 1.2 pp, medium confidence
AA Tau3 Banking41.2%estimated ± 3.7 pp, high confidence
AA Terminal-Bench 2.180.1%measured
ApprenticeBench5.5%estimated ± 10.4 pp, low confidence
ARC-AGI-188.0%estimated ± 7.8 pp, low confidence
ARC-AGI-264.6%estimated ± 14.4 pp, low confidence
BabaIsBench76.3%estimated ± 14.1 pp, low confidence
CursorBench 3.162.2%estimated ± 3.4 pp, medium confidence
CursorBench 3.267.1%estimated ± 3.3 pp, medium confidence
EBR-bench14.1%estimated ± 12.7 pp, low confidence
Terminal-Bench 3.013.1%estimated ± 6.9 pp, medium confidence
FrontierCode 1.1 Main43.9%estimated ± 3.5 pp, low confidence
FrontierSWE v212.0%measured
Furniture Assembly23.4%estimated ± 12.1 pp, low confidence
MaxxBench38.8%measured
MazeBench0.0%measured
Mystery Game Puzzles18.9%estimated ± 10.3 pp, low confidence
NYT Connections79.2%measured
OSWorld-Verified81.1%estimated ± 8.4 pp, low confidence
Terminal-Bench 4.119.9%estimated ± 10.9 pp, low confidence
Terminal-Bench Hard53.3%estimated ± 3.9 pp, high confidence
Vals SWE-bench86.6%measured
Terminal-Bench 2.1 (Vals AI)69.7%measured
VulcanBench v387.0%measured
CWE-Bench-AA49.7%estimated ± 8.1 pp, medium confidence
AA Cyber Index26.4%estimated ± 9.2 pp, low confidence
DeepsecBench-AA15.2%estimated ± 8.2 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)57.9%estimated ± 4.3 pp, medium confidence
HealthBench Professional (raw, Artificial Analysis)63.9%estimated ± 0.8 pp, low confidence
AA ITBench43.9%estimated ± 3.2 pp, high confidence
Bug Hunt Bench25.3%estimated ± 7.7 pp, low confidence
CursorBench 4.037.5%estimated ± 2.0 pp, high confidence
CWE-bench v157.4%estimated ± 5.1 pp, medium confidence
DeepSWE59.3%measured
DRACO86.9%estimated ± 0.7 pp, low confidence
FrontierCode 2.024.3%estimated ± 4.8 pp, medium confidence
FrontierPhysics0.0%estimated ± 6.1 pp, low confidence
HLE w/o tools43.9%estimated ± 4.9 pp, high confidence
OSWorld 2.153.2%estimated ± 3.6 pp, medium confidence
OSWorld 2.1 Offline55.5%estimated ± 1.9 pp, medium confidence
PostTrainBench v1.129.3%estimated ± 3.7 pp, high confidence
SpireClimb5.8%estimated ± 7.2 pp, medium confidence
StealthMark30.3%estimated ± 7.7 pp, low confidence
Toolathlon-Verified70.7%estimated ± 2.3 pp, medium confidence
VulcanBench Frontier v483.9%estimated ± 4.0 pp, low confidence
AA AutomationBench51.6%estimated ± 9.9 pp, low confidence
GDP.pdf18.5%estimated ± 4.2 pp, high confidence
AA Terminal-Bench 4.04.4%estimated ± 11.0 pp, low confidence
ARC-AGI-32.8%estimated ± 8.6 pp, low confidence
ARC-AGI-3 Provider Adapter6.3%estimated ± 7.3 pp, medium confidence
cursorBench4144.8%estimated ± 3.7 pp, high confidence
CWE-bench43.9%estimated ± 6.2 pp, medium confidence
MKA34.5%estimated ± 4.6 pp, high confidence
SkillsBench official leaderboard (BenchFlow)53.0%estimated ± 6.1 pp, medium confidence
BinaryAudit35.8%estimated ± 12.1 pp, low confidence
OTelBench22.5%estimated ± 6.6 pp, medium confidence
Vibe Code Bench60.4%estimated ± 10.0 pp, low confidence
FACTS Multimodal44.7%estimated ± 4.0 pp, high confidence
Hermes Bench69.6%estimated ± 2.9 pp, high confidence
Hermes Index37.2%estimated ± 3.1 pp, high confidence
ExploitBench28.6%estimated ± 13.4 pp, low confidence
ExploitGym12.3%estimated ± 2.7 pp, high confidence
C-Eval97.4%estimated ± 1.0 pp, low confidence
MCP Atlas78.7%estimated ± 7.8 pp, low confidence
MMLU-Redux96.6%estimated ± 0.8 pp, low confidence
NL2Repo50.6%estimated ± 4.7 pp, high confidence
PostTrainBench v132.5%estimated ± 3.6 pp, high confidence
QwenClawBench93.2%estimated ± 6.0 pp, low confidence
SuperGPQA91.2%estimated ± 9.3 pp, medium confidence
Terminal-Bench 2.072.8%estimated ± 5.8 pp, medium confidence
Toolathlon55.9%estimated ± 6.3 pp, medium confidence
AA LiveCodeBench95.6%estimated ± 2.6 pp, medium confidence
HealthBench Hard32.0%estimated ± 8.6 pp, low confidence
React Native Evals82.3%estimated ± 3.2 pp, high confidence
ResearchClawBench20.6%estimated ± 1.9 pp, medium confidence
PostTrainBench33.1%estimated ± 2.4 pp, medium confidence
DAYJOB0.0%estimated ± 6.3 pp, low confidence
DAYJOB Healthcare0.2%estimated ± 6.1 pp, low confidence
Finance Agent v255.5%estimated ± 2.4 pp, medium confidence
BioMysteryBench (human-solvable)88.7%estimated ± 0.6 pp, medium confidence
FrontierCode 1.1 Extended60.3%estimated ± 3.4 pp, low confidence
HealthBench (raw)53.6%estimated ± 6.0 pp, medium confidence
HealthBench (length-adjusted)55.7%estimated ± 3.4 pp, medium confidence
HealthBench Professional57.8%estimated ± 4.2 pp, medium confidence
HealthBench Professional (raw)64.0%estimated ± 4.5 pp, high confidence
HLE-Verified20.8%estimated ± 2.0 pp, low confidence
LABBench282.2%estimated ± 1.8 pp, low confidence
ScarfBench62.9%estimated ± 3.8 pp, medium confidence
BlenderWorld (text-only)70.6%estimated ± 4.0 pp, medium confidence
Cookie-Bench79.1%estimated ± 2.5 pp, medium confidence
STEMBench2.5%estimated ± 0.2 pp, medium confidence
SimpleQA53.0%estimated ± 4.3 pp, low confidence
Agents' Last Exam30.6%estimated ± 9.7 pp, medium confidence
OpenHarmony Bench v1.058.9%estimated ± 2.4 pp, high confidence
SEC-Bench Pro39.1%estimated ± 12.3 pp, low confidence
MRCRv285.6%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.4%estimated ± 2.6 pp, low confidence
BioBasicsBench35.1%estimated ± 2.8 pp, medium confidence
LifeVal75.2%estimated ± 3.8 pp, medium confidence
ExploitBench Internal Port0.1%estimated ± 1.4 pp, low confidence
SWE-Atlas Codebase QnA55.8%estimated ± 4.8 pp, high confidence