benchgap
Meta · model

Muse Spark 1.1 benchmark scores

As of 2026-11-22, Muse Spark 1.1 (Meta) has measured scores on 35 benchmarks and estimated scores on 135 more.

BenchmarkScoreSource
AA-GPQA Diamond89.8%measured
AA-HLE46.2%measured
AA-SciCode58.8%measured
Artificial Analysis Intelligence Index33.7%measured
CritPt15.1%measured
GDPval-AA35.6%measured
GPQA Diamond93.6%estimated ± 1.2 pp, medium confidence
HLE62.1%measured
AA-LCR77.7%measured
LiveCodeBench v689.1%estimated ± 2.2 pp, medium confidence
AA-Omniscience Accuracy52.1%measured
SciCode48.5%estimated ± 2.9 pp, medium confidence
Terminal-Bench 2.180.0%measured
BrowseComp82.9%estimated ± 1.9 pp, high confidence
HLE w/ tools50.0%estimated ± 4.9 pp, medium confidence
LongBench v263.8%estimated ± 5.5 pp, medium confidence
VITA-Bench51.3%estimated ± 9.9 pp, low confidence
AA Coding Index71.3%measured
AA-MMMU-Pro80.0%estimated ± 4.9 pp, medium confidence
APEX-Agents27.6%estimated ± 9.4 pp, low confidence
APEX-Agents-AA35.2%estimated ± 2.9 pp, medium confidence
BioMysteryBench (human-difficult)46.6%estimated ± 6.8 pp, low confidence
DeepSearchQA84.9%measured
SWE-bench Verified82.0%estimated ± 3.6 pp, high confidence
AutomationBench11.0%estimated ± 10.4 pp, low confidence
BFCL v475.2%estimated ± 2.7 pp, medium confidence
CyberGym59.0%measured
JobBench54.7%measured
SkillsBench62.1%estimated ± 9.1 pp, low confidence
SWE-bench Pro61.5%measured
WideResearch82.3%estimated ± 1.2 pp, medium confidence
AA Agentic Index27.5%measured
MMLU-Pro85.9%estimated ± 2.5 pp, low confidence
FailureSensorIQ67.7%estimated ± 1.7 pp, high confidence
GPQA93.6%estimated ± 1.2 pp, medium confidence
MMLU90.5%estimated ± 0.9 pp, medium confidence
Vals GPQA Diamond91.2%measured
Vals LiveCodeBench85.9%measured
Vals MMLU-Pro88.7%measured
MMMLU90.3%estimated ± 0.7 pp, low confidence
MMMU89.4%estimated ± 3.7 pp, low confidence
Chess Puzzles34.0%measured
AA MMLU-Pro89.1%estimated ± 0.7 pp, high confidence
Gert Labs56.1%measured
AA-AnalystAgent55.7%estimated ± 3.7 pp, low confidence
AA EnterpriseOps-Gym46.4%estimated ± 1.2 pp, medium confidence
AA Harvey LAB v1.085.8%estimated ± 1.2 pp, medium confidence
AA Tau3 Banking31.8%estimated ± 3.7 pp, high confidence
AA Terminal-Bench 2.182.5%estimated ± 2.5 pp, high confidence
ApprenticeBench4.1%estimated ± 4.0 pp, medium confidence
ARC-AGI-196.3%estimated ± 3.9 pp, high confidence
ARC-AGI-282.0%estimated ± 13.0 pp, low confidence
CursorBench 3.165.7%estimated ± 3.4 pp, medium confidence
CursorBench 3.260.0%estimated ± 3.6 pp, high confidence
EBR-bench19.5%estimated ± 12.7 pp, low confidence
Terminal-Bench 3.012.7%estimated ± 6.9 pp, medium confidence
FrontierCode 1.1 Main40.3%estimated ± 3.5 pp, low confidence
FrontierSWE v218.2%estimated ± 8.3 pp, medium confidence
Furniture Assembly32.3%estimated ± 14.1 pp, low confidence
MaxxBench49.1%estimated ± 10.3 pp, low confidence
MazeBench1.4%estimated ± 2.7 pp, high confidence
Mystery Game Puzzles25.0%estimated ± 10.3 pp, low confidence
NYT Connections84.9%measured
OSWorld-Verified80.8%measured
ParseBench-166.4%estimated ± 8.6 pp, low confidence
Terminal-Bench 4.117.1%estimated ± 10.9 pp, low confidence
Terminal-Bench Hard53.0%estimated ± 3.9 pp, high confidence
Vals SWE-bench82.0%measured
Terminal-Bench 2.1 (Vals AI)69.3%measured
VulcanBench v384.2%estimated ± 5.6 pp, low confidence
CWE-Bench-AA45.0%estimated ± 4.5 pp, medium confidence
AA Cyber Index17.9%estimated ± 9.2 pp, low confidence
DeepsecBench-AA20.3%estimated ± 8.2 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)56.1%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)61.7%estimated ± 0.8 pp, low confidence
AA ITBench41.7%estimated ± 4.0 pp, high confidence
Bug Hunt Bench21.1%estimated ± 9.0 pp, low confidence
CursorBench 4.037.1%estimated ± 2.0 pp, medium confidence
CWE-bench v146.2%estimated ± 4.5 pp, low confidence
DeepSWE53.3%measured
DRACO79.0%estimated ± 2.0 pp, medium confidence
FrontierCode 2.021.7%estimated ± 6.7 pp, medium confidence
FrontierPhysics0.3%estimated ± 6.1 pp, medium confidence
HLE w/o tools52.2%measured
OSWorld 2.014.2%measured
OSWorld 2.170.3%estimated ± 3.6 pp, high confidence
OSWorld 2.1 Offline17.0%estimated ± 1.9 pp, low confidence
PostTrainBench v1.125.8%estimated ± 3.7 pp, high confidence
SpireClimb5.8%estimated ± 7.2 pp, medium confidence
StealthMark44.9%estimated ± 9.7 pp, low confidence
Toolathlon-Verified69.8%estimated ± 1.0 pp, low confidence
VulcanBench Frontier v483.3%estimated ± 4.0 pp, low confidence
AA AutomationBench8.9%estimated ± 4.8 pp, low confidence
GDP.pdf16.9%estimated ± 4.1 pp, medium confidence
AA Terminal-Bench 4.04.3%estimated ± 11.0 pp, low confidence
ARC-AGI-314.3%estimated ± 7.2 pp, medium confidence
ARC-AGI-3 Provider Adapter9.5%estimated ± 7.3 pp, medium confidence
cursorBench4145.1%estimated ± 3.7 pp, high confidence
CWE-bench50.7%estimated ± 6.2 pp, medium confidence
MKA4.9%estimated ± 3.1 pp, medium confidence
SkillsBench official leaderboard (BenchFlow)54.7%estimated ± 6.1 pp, medium confidence
BinaryAudit35.8%estimated ± 12.1 pp, low confidence
OTelBench22.5%estimated ± 6.6 pp, medium confidence
Vibe Code Bench57.6%estimated ± 10.0 pp, low confidence
FACTS Multimodal47.7%estimated ± 4.0 pp, high confidence
Hermes Bench33.8%estimated ± 1.5 pp, low confidence
Hermes Index3.7%estimated ± 5.5 pp, low confidence
CharXiv88.4%measured
CharXiv w/o tools86.8%estimated ± 2.0 pp, medium confidence
ExploitBench37.7%estimated ± 13.4 pp, low confidence
ExploitGym0.8%measured
AI2D_TEST93.5%estimated ± 0.9 pp, low confidence
C-Eval95.7%estimated ± 1.0 pp, low confidence
Claw-Eval73.5%estimated ± 4.5 pp, medium confidence
CountBench98.1%estimated ± 3.7 pp, low confidence
DeepPlanning53.8%estimated ± 13.1 pp, low confidence
DynaMath87.7%estimated ± 0.8 pp, low confidence
ERQA70.3%estimated ± 5.6 pp, medium confidence
MathVision93.3%estimated ± 0.9 pp, high confidence
MCP Atlas88.1%measured
MLVU (M-Avg)88.4%estimated ± 1.5 pp, high confidence
MMLU-Redux97.5%estimated ± 0.8 pp, low confidence
MMMU-Pro81.9%estimated ± 2.5 pp, medium confidence
NL2Repo46.9%estimated ± 4.7 pp, high confidence
PostTrainBench v126.8%estimated ± 3.6 pp, high confidence
QwenClawBench73.0%estimated ± 2.6 pp, medium confidence
RealWorldQA86.7%estimated ± 1.5 pp, high confidence
ScreenSpot Pro83.4%estimated ± 6.8 pp, medium confidence
SuperGPQA100.0%estimated ± 7.2 pp, low confidence
Terminal-Bench 2.072.6%estimated ± 5.8 pp, medium confidence
Toolathlon75.6%measured
Video-MME (with subtitle)90.1%estimated ± 2.9 pp, high confidence
VideoMMMU86.9%estimated ± 1.5 pp, medium confidence
We-Math84.6%estimated ± 7.9 pp, low confidence
AA LiveCodeBench92.8%estimated ± 2.6 pp, medium confidence
HealthBench Hard31.3%estimated ± 8.6 pp, low confidence
LiveCodeBench Pro84.9%estimated ± 6.0 pp, low confidence
MedXpertQA (MM)78.4%estimated ± 6.4 pp, low confidence
MedXpertQA (Text)68.9%estimated ± 8.9 pp, low confidence
React Native Evals82.1%estimated ± 3.2 pp, high confidence
ResearchClawBench20.1%estimated ± 1.8 pp, medium confidence
PostTrainBench23.5%estimated ± 3.7 pp, high confidence
DAYJOB0.8%estimated ± 6.3 pp, medium confidence
DAYJOB Healthcare0.4%estimated ± 6.1 pp, low confidence
Finance Agent v257.2%measured
BioMysteryBench (human-solvable)87.6%estimated ± 0.6 pp, medium confidence
FrontierCode 1.1 Extended56.5%estimated ± 3.0 pp, low confidence
HealthBench (raw)54.2%estimated ± 6.0 pp, medium confidence
HealthBench (length-adjusted)52.4%estimated ± 2.2 pp, medium confidence
HealthBench Professional59.3%measured
HealthBench Professional (raw)64.5%estimated ± 4.5 pp, high confidence
HLE-Verified17.2%estimated ± 2.0 pp, low confidence
LABBench282.4%estimated ± 1.8 pp, low confidence
ScarfBench61.8%estimated ± 3.8 pp, low confidence
BlenderWorld (text-only)70.6%estimated ± 4.0 pp, medium confidence
Cookie-Bench81.2%estimated ± 2.5 pp, medium confidence
STEMBench2.6%estimated ± 0.2 pp, medium confidence
SimpleQA33.5%estimated ± 7.8 pp, low confidence
Agents' Last Exam20.6%estimated ± 3.3 pp, low confidence
OpenHarmony Bench v1.058.9%estimated ± 2.4 pp, high confidence
SEC-Bench Pro46.8%estimated ± 12.3 pp, low confidence
BabyVision76.3%measured
MMVU79.9%estimated ± 3.6 pp, medium confidence
MRCRv285.4%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.3%estimated ± 2.6 pp, low confidence
BioBasicsBench35.7%estimated ± 2.8 pp, medium confidence
LifeVal67.4%estimated ± 5.0 pp, medium confidence
ExploitBench Internal Port0.2%estimated ± 1.4 pp, low confidence
MathVision w/ Python94.9%estimated ± 1.0 pp, low confidence
SWE-Atlas Codebase QnA50.2%estimated ± 4.8 pp, high confidence