benchgap
Meta · model

Muse Glimmer 30B benchmark scores

As of 2026-11-22, Muse Glimmer 30B (Meta) has measured scores on 26 benchmarks and estimated scores on 140 more.

BenchmarkScoreSource
AA-GPQA Diamond83.5%measured
AA-HLE22.0%measured
AA-SciCode44.9%measured
AIME2694.7%measured
Artificial Analysis Intelligence Index6.3%measured
CritPt2.6%measured
GDPval-AA14.2%measured
GPQA Diamond82.7%estimated ± 2.4 pp, high confidence
HLE24.7%estimated ± 8.5 pp, medium confidence
IFBench77.0%measured
AA-LCR83.3%measured
LiveCodeBench v686.2%estimated ± 2.7 pp, high confidence
AA-Omniscience Accuracy28.0%measured
SciCode43.6%measured
Terminal-Bench 2.151.7%measured
BrowseComp71.2%estimated ± 1.9 pp, low confidence
HLE w/ tools40.6%estimated ± 5.3 pp, low confidence
IFEval94.2%estimated ± 3.6 pp, high confidence
LongBench v268.6%estimated ± 5.5 pp, medium confidence
VITA-Bench46.4%estimated ± 9.9 pp, low confidence
AA Coding Index49.0%measured
AA-MMMU-Pro74.3%measured
APEX-Agents9.6%estimated ± 9.4 pp, low confidence
APEX-Agents-AA34.2%estimated ± 5.5 pp, medium confidence
BioMysteryBench (human-difficult)29.1%estimated ± 6.8 pp, low confidence
DeepSearchQA74.6%measured
SWE-bench Verified76.0%measured
BFCL v469.9%estimated ± 2.7 pp, high confidence
CyberGym53.6%estimated ± 5.3 pp, low confidence
JobBench47.7%estimated ± 7.9 pp, medium confidence
SkillsBench44.3%measured
SWE-bench Pro51.2%measured
WideResearch73.0%estimated ± 1.3 pp, low confidence
AA Agentic Index10.5%measured
MMLU-Pro85.3%estimated ± 5.0 pp, medium confidence
AA-IFBench79.1%estimated ± 7.4 pp, medium confidence
GPQA84.6%estimated ± 6.1 pp, medium confidence
MMLU90.5%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond82.6%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench84.8%estimated ± 0.8 pp, medium confidence
Vals MMLU-Pro84.1%estimated ± 2.9 pp, high confidence
MATH-50097.6%estimated ± 3.1 pp, medium confidence
MMMLU87.5%estimated ± 0.7 pp, medium confidence
MMMU82.5%estimated ± 0.8 pp, high confidence
AIME 202596.0%estimated ± 1.8 pp, medium confidence
AA MMLU-Pro85.3%estimated ± 0.8 pp, high confidence
Gert Labs32.7%measured
AA-AnalystAgent46.5%estimated ± 3.7 pp, medium confidence
AA EnterpriseOps-Gym43.1%estimated ± 2.3 pp, medium confidence
AA Harvey LAB v1.079.4%estimated ± 1.2 pp, low confidence
AA Tau3 Banking22.0%estimated ± 3.7 pp, medium confidence
ApprenticeBench0.0%estimated ± 6.3 pp, low confidence
ARC-AGI-176.7%estimated ± 7.8 pp, low confidence
ARC-AGI-235.6%estimated ± 14.4 pp, low confidence
CursorBench 3.131.4%estimated ± 3.4 pp, low confidence
CursorBench 3.242.8%estimated ± 3.6 pp, medium confidence
Terminal-Bench 3.03.8%estimated ± 9.1 pp, low confidence
FrontierCode 1.1 Main20.4%estimated ± 4.2 pp, low confidence
FrontierMath v2 (Tiers 1-3)35.2%estimated ± 8.8 pp, medium confidence
FrontierSWE v20.4%estimated ± 8.3 pp, low confidence
MazeBench0.1%estimated ± 2.7 pp, high confidence
OfficeQA Pro50.3%estimated ± 6.8 pp, low confidence
OSWorld-Verified65.9%measured
ParseBench-157.5%estimated ± 5.2 pp, low confidence
Terminal-Bench 4.10.0%estimated ± 10.9 pp, low confidence
Vals SWE-bench69.3%estimated ± 5.3 pp, low confidence
Terminal-Bench 2.1 (Vals AI)46.2%estimated ± 7.3 pp, low confidence
CWE-Bench-AA42.0%estimated ± 8.1 pp, medium confidence
AA Cyber Index7.4%estimated ± 9.2 pp, low confidence
DeepsecBench-AA10.2%estimated ± 8.2 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)48.6%estimated ± 7.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)29.0%estimated ± 0.8 pp, low confidence
AA ITBench36.2%estimated ± 4.0 pp, high confidence
Bug Hunt Bench18.0%estimated ± 10.5 pp, low confidence
Chartography (tools)79.8%estimated ± 4.1 pp, low confidence
CursorBench 4.028.9%estimated ± 3.3 pp, medium confidence
CWE-bench v140.9%estimated ± 5.7 pp, medium confidence
DeepSWE45.7%estimated ± 7.5 pp, low confidence
DRACO60.0%estimated ± 2.0 pp, low confidence
FrontierCode 2.019.2%estimated ± 6.7 pp, low confidence
HLE w/o tools20.9%estimated ± 4.9 pp, high confidence
OSWorld 2.00.0%estimated ± 3.6 pp, medium confidence
OSWorld 2.117.6%estimated ± 3.6 pp, medium confidence
OSWorld 2.1 Offline42.8%estimated ± 10.1 pp, low confidence
PostTrainBench v1.120.6%estimated ± 4.4 pp, medium confidence
Toolathlon-Verified31.4%estimated ± 2.3 pp, low confidence
VulcanBench Frontier v475.1%estimated ± 6.8 pp, low confidence
AA AutomationBench44.7%estimated ± 9.9 pp, low confidence
GDP.pdf14.4%estimated ± 4.2 pp, medium confidence
ARC-AGI-31.3%estimated ± 9.8 pp, medium confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
cursorBench4144.8%estimated ± 3.7 pp, medium confidence
CWE-bench35.3%estimated ± 6.2 pp, low confidence
MKA33.0%estimated ± 4.6 pp, medium confidence
Vibe Code Bench5.4%estimated ± 8.4 pp, medium confidence
Hermes Bench42.5%estimated ± 2.9 pp, medium confidence
Hermes Index22.1%estimated ± 5.7 pp, low confidence
ParseBench-263.5%estimated ± 5.0 pp, medium confidence
CharXiv78.8%measured
CharXiv w/o tools78.5%estimated ± 1.2 pp, high confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
AI2D_TEST93.2%estimated ± 0.9 pp, medium confidence
C-Eval87.5%estimated ± 1.0 pp, low confidence
Claw-Eval60.6%estimated ± 6.2 pp, low confidence
CountBench94.5%estimated ± 2.9 pp, medium confidence
DeepPlanning47.9%estimated ± 13.1 pp, low confidence
DynaMath85.3%estimated ± 0.8 pp, medium confidence
ERQA60.6%estimated ± 3.1 pp, high confidence
HMMT Feb 202594.7%estimated ± 1.9 pp, medium confidence
HMMT Feb 202686.1%estimated ± 4.0 pp, high confidence
HMMT Nov 202592.0%estimated ± 3.2 pp, high confidence
MathVision82.9%estimated ± 3.0 pp, high confidence
MCP Atlas75.5%measured
MLVU (M-Avg)85.3%estimated ± 1.5 pp, high confidence
MMAnswerBench82.3%estimated ± 1.3 pp, high confidence
MMLU-Redux94.5%estimated ± 0.8 pp, medium confidence
MMMU-Pro74.0%measured
NL2Repo34.8%estimated ± 4.7 pp, high confidence
OmniDocBench 1.575.8%measured
PostTrainBench v116.1%estimated ± 4.6 pp, medium confidence
QwenClawBench62.7%estimated ± 2.6 pp, high confidence
RealWorldQA85.1%estimated ± 1.4 pp, medium confidence
ScreenSpot Pro75.4%measured
SimpleVQA61.6%estimated ± 7.5 pp, medium confidence
SuperGPQA67.1%estimated ± 9.3 pp, medium confidence
Toolathlon27.0%estimated ± 6.3 pp, low confidence
V*95.1%estimated ± 6.5 pp, low confidence
Video-MME (w/o subtitle)82.3%estimated ± 1.3 pp, high confidence
Video-MME (with subtitle)86.0%estimated ± 2.9 pp, high confidence
VideoMMMU85.1%estimated ± 1.5 pp, medium confidence
We-Math80.5%estimated ± 7.4 pp, low confidence
AA LiveCodeBench88.1%estimated ± 4.7 pp, low confidence
HealthBench Hard17.7%estimated ± 8.6 pp, low confidence
LiveCodeBench Pro76.4%estimated ± 6.0 pp, low confidence
MedXpertQA (MM)60.8%estimated ± 2.4 pp, high confidence
MMLU-Pro (Arcee)86.9%estimated ± 4.0 pp, medium confidence
React Native Evals77.8%estimated ± 2.7 pp, medium confidence
ResearchClawBench18.9%estimated ± 1.8 pp, high confidence
SWE-Rebench57.8%estimated ± 3.6 pp, medium confidence
PostTrainBench19.0%estimated ± 3.7 pp, medium confidence
Finance Agent v255.1%estimated ± 2.4 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
FrontierCode 1.1 Extended52.8%estimated ± 3.0 pp, low confidence
HealthBench (raw)30.1%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)46.7%estimated ± 3.4 pp, low confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)41.9%estimated ± 4.5 pp, medium confidence
HLE-Verified22.6%estimated ± 7.1 pp, low confidence
ScarfBench24.5%estimated ± 9.1 pp, low confidence
STEMBench2.4%estimated ± 0.2 pp, medium confidence
SimpleQA29.1%estimated ± 4.3 pp, medium confidence
LiveCodeBench76.8%estimated ± 14.6 pp, low confidence
Agents' Last Exam29.7%estimated ± 9.7 pp, low confidence
BabyVision w/ Python88.8%estimated ± 3.8 pp, low confidence
OpenHarmony Bench v1.051.0%estimated ± 2.4 pp, high confidence
IMOAnswerBench74.0%estimated ± 10.7 pp, low confidence
BabyVision51.3%estimated ± 9.1 pp, low confidence
MMVU74.7%estimated ± 2.7 pp, medium confidence
PerceptionBench57.5%estimated ± 4.9 pp, low confidence
ZeroBench18.1%estimated ± 6.7 pp, low confidence
MRCRv285.9%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.5%estimated ± 2.6 pp, low confidence
OCRBench V270.0%estimated ± 3.3 pp, high confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
LifeVal11.0%estimated ± 5.0 pp, low confidence
MMMU-Pro w/ Python77.6%estimated ± 2.0 pp, high confidence