benchgap
Other · model

Gemma 4 E4B benchmark scores

As of 2026-11-22, Gemma 4 E4B (Other) has measured scores on 19 benchmarks and estimated scores on 85 more.

BenchmarkScoreSource
AA-GPQA Diamond57.6%measured
AA-HLE3.8%measured
AA-SciCode24.4%measured
Artificial Analysis Intelligence Index4.8%measured
CritPt0.6%measured
GDPval-AA0.0%measured
GPQA Diamond58.9%estimated ± 1.2 pp, high confidence
HLE4.4%estimated ± 6.5 pp, low confidence
IFBench54.7%estimated ± 6.6 pp, medium confidence
AA-LCR32.0%measured
LiveCodeBench v652.0%measured
AA-Omniscience Accuracy9.7%measured
SciCode25.0%estimated ± 3.1 pp, medium confidence
BrowseComp0.0%estimated ± 9.2 pp, low confidence
HLE w/ tools33.8%estimated ± 5.3 pp, low confidence
IFEval90.0%estimated ± 2.8 pp, high confidence
LongBench v251.2%estimated ± 5.5 pp, medium confidence
τ²-bench results20.8%measured
AA Coding Index9.4%measured
AA-MMMU-Pro51.4%measured
APEX-Agents0.0%estimated ± 9.4 pp, low confidence
APEX-Agents-AA6.0%estimated ± 9.5 pp, medium confidence
BioMysteryBench (human-difficult)11.6%estimated ± 6.8 pp, low confidence
DeepSearchQA34.7%estimated ± 9.6 pp, medium confidence
SWE-bench Verified43.4%estimated ± 6.3 pp, low confidence
BFCL v453.9%estimated ± 2.7 pp, high confidence
CyberGym0.0%estimated ± 6.0 pp, low confidence
JobBench0.0%estimated ± 8.7 pp, low confidence
SWE-bench Pro0.0%estimated ± 6.0 pp, low confidence
WideResearch0.0%estimated ± 7.8 pp, low confidence
AA Agentic Index0.0%estimated ± 3.1 pp, high confidence
MMLU-Pro69.4%measured
AA-IFBench44.2%measured
BBH89.2%estimated ± 2.8 pp, medium confidence
GPQA58.6%measured
MMLU80.3%estimated ± 0.9 pp, medium confidence
Vals GPQA Diamond56.7%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench60.9%estimated ± 5.7 pp, low confidence
Vals MMLU-Pro73.3%estimated ± 2.3 pp, high confidence
MMMLU85.9%estimated ± 0.7 pp, medium confidence
MMMU65.9%estimated ± 0.8 pp, medium confidence
AA MMLU-Pro82.5%estimated ± 0.8 pp, medium confidence
Gert Labs26.9%estimated ± 10.0 pp, low confidence
AA Tau3 Banking0.0%estimated ± 4.1 pp, medium confidence
ARC-AGI-175.2%estimated ± 7.8 pp, low confidence
ARC-AGI-231.7%estimated ± 14.4 pp, low confidence
MazeBench0.4%estimated ± 5.5 pp, low confidence
OSWorld-Verified55.4%estimated ± 8.4 pp, low confidence
ParseBench-141.1%measured
Vals SWE-bench31.7%estimated ± 5.5 pp, low confidence
CWE-Bench-AA0.0%estimated ± 10.1 pp, low confidence
DeepsecBench-AA0.0%estimated ± 8.9 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)0.4%estimated ± 2.5 pp, low confidence
AA ITBench35.7%estimated ± 5.1 pp, low confidence
CWE-bench v10.0%estimated ± 6.4 pp, low confidence
DRACO0.0%estimated ± 2.0 pp, low confidence
HLE w/o tools19.7%estimated ± 4.9 pp, high confidence
Toolathlon-Verified0.0%estimated ± 3.1 pp, medium confidence
GDP.pdf17.0%estimated ± 4.6 pp, medium confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
Vibe Code Bench2.2%estimated ± 10.0 pp, low confidence
Hermes Bench0.0%estimated ± 2.9 pp, medium confidence
Hermes Index0.0%estimated ± 8.7 pp, low confidence
ParseBench-242.8%measured
CharXiv76.8%estimated ± 5.6 pp, low confidence
CharXiv w/o tools70.7%estimated ± 1.2 pp, high confidence
AI2D_TEST88.0%estimated ± 2.0 pp, low confidence
C-Eval87.0%estimated ± 1.0 pp, low confidence
CountBench92.6%estimated ± 3.0 pp, high confidence
DynaMath79.8%estimated ± 5.3 pp, low confidence
ERQA47.4%estimated ± 6.4 pp, medium confidence
MathVision59.1%estimated ± 3.0 pp, high confidence
MCP Atlas56.5%estimated ± 10.7 pp, low confidence
MLVU (M-Avg)74.5%estimated ± 2.2 pp, high confidence
MMLU-Redux83.8%estimated ± 0.6 pp, high confidence
MMMU-Pro52.6%measured
NL2Repo3.1%estimated ± 4.7 pp, medium confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
RealWorldQA78.3%estimated ± 2.8 pp, high confidence
ScreenSpot Pro57.9%estimated ± 9.6 pp, low confidence
SimpleVQA41.5%estimated ± 7.5 pp, medium confidence
SuperGPQA40.8%estimated ± 8.5 pp, low confidence
Toolathlon27.0%estimated ± 6.3 pp, low confidence
Video-MME (w/o subtitle)68.5%estimated ± 1.3 pp, high confidence
Video-MME (with subtitle)72.8%estimated ± 3.0 pp, high confidence
VideoMMMU58.9%estimated ± 2.4 pp, high confidence
We-Math70.2%estimated ± 7.4 pp, low confidence
HealthBench Hard6.5%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)79.4%estimated ± 4.0 pp, medium confidence
React Native Evals66.4%estimated ± 3.2 pp, medium confidence
ResearchClawBench11.1%estimated ± 2.2 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (length-adjusted)54.1%estimated ± 3.7 pp, medium confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
ScarfBench24.4%estimated ± 9.1 pp, low confidence
STEMBench2.2%estimated ± 0.2 pp, low confidence
SimpleQA4.0%estimated ± 4.3 pp, low confidence
MMVU59.5%estimated ± 2.7 pp, medium confidence
MRCRv225.4%measured
MMLongBench-Doc56.7%estimated ± 2.6 pp, low confidence
OCRBench V262.4%estimated ± 3.3 pp, high confidence
BioBasicsBench6.2%estimated ± 10.2 pp, low confidence
MMMU-Pro w/ Python57.0%estimated ± 2.0 pp, medium confidence