benchgap
Meta · model

Muse Spark 1.3 benchmark scores

As of 2026-11-22, Muse Spark 1.3 (Meta) has measured scores on 36 benchmarks and estimated scores on 119 more.

BenchmarkScoreSource
AA-GPQA Diamond93.5%measured
AA-HLE48.7%measured
AA-SciCode58.8%measured
AIME2699.2%estimated ± 1.2 pp, low confidence
Artificial Analysis Intelligence Index48.1%measured
CritPt24.9%measured
GDPval-AA59.0%measured
GPQA Diamond93.9%estimated ± 2.4 pp, high confidence
HLE56.6%estimated ± 8.5 pp, medium confidence
AA-LCR83.0%measured
LiveCodeBench v688.8%estimated ± 4.7 pp, medium confidence
AA-Omniscience Accuracy43.6%measured
SciCode58.4%estimated ± 3.1 pp, high confidence
Terminal-Bench 2.188.8%measured
BrowseComp91.7%estimated ± 1.9 pp, high confidence
HLE w/ tools62.3%estimated ± 5.3 pp, medium confidence
LongBench v268.4%estimated ± 5.5 pp, medium confidence
τ²-bench results92.8%estimated ± 6.5 pp, low confidence
AA Coding Index75.8%measured
APEX-Agents38.0%estimated ± 7.4 pp, low confidence
APEX-Agents-AA38.8%estimated ± 2.9 pp, low confidence
BioMysteryBench (human-difficult)49.0%estimated ± 6.8 pp, low confidence
DeepSearchQA89.4%measured
SWE-bench Verified90.7%estimated ± 5.1 pp, low confidence
AutomationBench49.4%measured
BFCL v477.2%estimated ± 2.7 pp, medium confidence
CyberGym85.4%estimated ± 3.1 pp, low confidence
JobBench64.9%measured
SWE-bench Pro67.2%estimated ± 4.2 pp, high confidence
WideResearch84.5%estimated ± 1.2 pp, low confidence
AA Agentic Index55.7%measured
MMLU-Pro85.5%estimated ± 5.0 pp, medium confidence
FailureSensorIQ67.7%estimated ± 1.7 pp, high confidence
GPQA93.6%estimated ± 6.1 pp, medium confidence
MMLU90.5%estimated ± 0.9 pp, medium confidence
Vals GPQA Diamond92.6%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench84.7%estimated ± 3.0 pp, high confidence
Vals MMLU-Pro87.8%estimated ± 2.9 pp, high confidence
MMMLU91.3%estimated ± 0.7 pp, low confidence
Chess Puzzles37.0%measured
AA MMLU-Pro87.7%estimated ± 0.8 pp, high confidence
Gert Labs57.0%measured
AA-AnalystAgent44.8%estimated ± 5.9 pp, low confidence
AA EnterpriseOps-Gym46.8%estimated ± 1.2 pp, medium confidence
AA Harvey LAB v1.093.7%estimated ± 1.2 pp, medium confidence
AA Tau3 Banking50.5%measured
AA Terminal-Bench 2.183.4%estimated ± 2.5 pp, high confidence
ApprenticeBench19.0%measured
ARC-AGI-193.4%estimated ± 7.8 pp, low confidence
ARC-AGI-278.4%estimated ± 14.4 pp, low confidence
BabaIsBench46.0%measured
CursorBench 3.165.7%estimated ± 3.4 pp, medium confidence
CursorBench 3.267.2%estimated ± 2.0 pp, high confidence
EBR-bench14.5%estimated ± 10.4 pp, low confidence
Terminal-Bench 3.016.9%estimated ± 3.2 pp, high confidence
FrontierCode 1.1 Main52.6%estimated ± 3.5 pp, low confidence
FrontierMath v2 (Tier 4)46.3%measured
FrontierMath v2 (Tiers 1-3)74.0%measured
FrontierSWE v225.8%measured
Furniture Assembly33.2%estimated ± 9.3 pp, medium confidence
MaxxBench49.7%estimated ± 5.7 pp, medium confidence
MazeBench0.0%measured
MirrorCode54.4%measured
Mystery Game Puzzles25.0%measured
NYT Connections85.1%measured
OSWorld-Verified79.5%estimated ± 2.3 pp, medium confidence
Terminal-Bench 4.114.9%measured
Terminal-Bench Hard56.6%estimated ± 2.8 pp, medium confidence
Vals SWE-bench94.7%estimated ± 3.7 pp, high confidence
Terminal-Bench 2.1 (Vals AI)72.3%measured
VulcanBench v387.6%estimated ± 3.9 pp, medium confidence
CWE-Bench-AA60.1%estimated ± 4.5 pp, medium confidence
AA Cyber Index31.7%estimated ± 9.2 pp, low confidence
DeepsecBench-AA20.8%estimated ± 8.2 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)60.5%estimated ± 4.3 pp, medium confidence
HealthBench Professional (raw, Artificial Analysis)68.0%estimated ± 0.8 pp, medium confidence
AA ITBench45.3%estimated ± 3.2 pp, high confidence
Bug Hunt Bench32.2%measured
CursorBench 4.041.6%measured
CWE-bench v155.0%measured
DeepSWE75.4%measured
DRACO86.9%estimated ± 0.7 pp, low confidence
FrontierCode 2.027.1%estimated ± 4.7 pp, medium confidence
FrontierPhysics1.8%estimated ± 4.7 pp, high confidence
HLE w/o tools54.4%estimated ± 4.9 pp, high confidence
OSWorld 2.066.9%measured
OSWorld 2.171.0%estimated ± 3.6 pp, high confidence
OSWorld 2.1 Offline77.7%estimated ± 1.9 pp, medium confidence
PostTrainBench v1.135.6%estimated ± 1.7 pp, low confidence
SpireClimb5.8%estimated ± 7.2 pp, medium confidence
StealthMark39.5%measured
Terminal-Bench 4.022.1%estimated ± 4.5 pp, high confidence
Terminal-Bench-Science 0.10.0%estimated ± 10.7 pp, low confidence
Toolathlon-Verified79.7%estimated ± 1.0 pp, medium confidence
VulcanBench Frontier v488.6%estimated ± 1.8 pp, high confidence
AA AutomationBench58.0%estimated ± 9.9 pp, low confidence
GDP.pdf21.4%estimated ± 4.1 pp, medium confidence
AA Terminal-Bench 4.014.5%estimated ± 6.2 pp, medium confidence
ARC-AGI-33.4%estimated ± 9.8 pp, medium confidence
ARC-AGI-3 Provider Adapter46.6%estimated ± 7.3 pp, medium confidence
cursorBench4141.9%measured
CWE-bench54.3%estimated ± 5.8 pp, low confidence
MKA38.5%estimated ± 4.6 pp, high confidence
SkillsBench official leaderboard (BenchFlow)55.1%estimated ± 6.1 pp, medium confidence
BinaryAudit35.8%estimated ± 12.1 pp, low confidence
CompileBench95.5%estimated ± 10.0 pp, low confidence
OTelBench27.5%estimated ± 4.1 pp, low confidence
Vibe Code Bench73.9%estimated ± 10.0 pp, low confidence
FACTS Multimodal47.8%estimated ± 4.0 pp, high confidence
Hermes Bench72.7%estimated ± 2.4 pp, low confidence
Hermes Index37.2%estimated ± 3.1 pp, high confidence
ExploitBench43.9%estimated ± 7.2 pp, medium confidence
ExploitGym14.5%estimated ± 2.7 pp, high confidence
C-Eval94.7%estimated ± 1.2 pp, low confidence
Claw-Eval78.6%estimated ± 4.5 pp, medium confidence
HMMT Feb 2026100.0%estimated ± 1.5 pp, low confidence
HMMT Nov 202595.6%estimated ± 1.5 pp, low confidence
MCP Atlas78.9%estimated ± 5.8 pp, low confidence
MMAnswerBench92.7%estimated ± 2.4 pp, low confidence
MMLU-Redux96.4%estimated ± 0.8 pp, low confidence
NL2Repo56.3%estimated ± 4.7 pp, medium confidence
SuperGPQA87.8%estimated ± 9.3 pp, medium confidence
Terminal-Bench 2.074.5%estimated ± 5.8 pp, medium confidence
Toolathlon55.6%estimated ± 1.7 pp, medium confidence
HealthBench Hard33.4%estimated ± 8.6 pp, low confidence
React Native Evals83.2%estimated ± 3.2 pp, medium confidence
ResearchClawBench21.6%estimated ± 1.9 pp, medium confidence
PostTrainBench33.1%estimated ± 2.4 pp, high confidence
DAYJOB0.4%estimated ± 3.2 pp, high confidence
DAYJOB Healthcare0.7%estimated ± 4.2 pp, high confidence
Finance Agent v256.6%estimated ± 2.4 pp, medium confidence
BioMysteryBench (human-solvable)89.4%estimated ± 0.6 pp, medium confidence
FrontierCode 1.1 Extended59.5%estimated ± 3.0 pp, medium confidence
HealthBench (raw)56.3%estimated ± 6.0 pp, medium confidence
HealthBench (length-adjusted)56.9%estimated ± 3.4 pp, medium confidence
HealthBench Professional60.0%estimated ± 4.2 pp, medium confidence
HealthBench Professional (raw)66.5%estimated ± 4.5 pp, high confidence
HLE-Verified54.1%estimated ± 2.0 pp, medium confidence
LABBench282.7%estimated ± 1.8 pp, low confidence
ScarfBench69.5%estimated ± 3.8 pp, medium confidence
BlenderWorld (text-only)70.3%estimated ± 2.8 pp, medium confidence
Cookie-Bench77.7%estimated ± 1.3 pp, medium confidence
STEMBench2.5%estimated ± 0.2 pp, medium confidence
SimpleQA50.5%estimated ± 4.3 pp, low confidence
Agents' Last Exam33.6%estimated ± 9.7 pp, medium confidence
OpenHarmony Bench v1.058.9%estimated ± 2.4 pp, high confidence
OpenHarmony Bench v1.263.8%estimated ± 11.0 pp, low confidence
SEC-Bench Pro46.0%estimated ± 9.3 pp, medium confidence
MRCRv285.9%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.5%estimated ± 2.6 pp, low confidence
SWE-Marathon50.9%estimated ± 2.1 pp, medium confidence
BioBasicsBench41.8%estimated ± 2.8 pp, medium confidence
LifeVal75.2%estimated ± 3.8 pp, medium confidence
ExploitBench Internal Port0.3%estimated ± 1.4 pp, medium confidence
SWE-Atlas Codebase QnA59.4%measured