benchgap
Other · model

Gemma 3 27B benchmark scores

As of 2026-11-22, Gemma 3 27B (Other) has measured scores on 13 benchmarks and estimated scores on 79 more.

BenchmarkScoreSource
AA-GPQA Diamond42.8%measured
AA-HLE4.4%measured
AA-SciCode23.3%measured
Artificial Analysis Intelligence Index4.9%measured
CritPt0.0%measured
GDPval-AA0.0%measured
GPQA Diamond68.9%estimated ± 2.4 pp, medium confidence
HLE16.7%estimated ± 8.5 pp, low confidence
IFBench53.7%estimated ± 6.6 pp, low confidence
AA-LCR7.3%measured
LiveCodeBench v656.4%estimated ± 4.7 pp, high confidence
AA-Omniscience Accuracy13.0%measured
SciCode23.9%estimated ± 3.1 pp, medium confidence
BrowseComp1.5%estimated ± 9.0 pp, low confidence
HLE w/ tools33.8%estimated ± 5.3 pp, low confidence
IFEval85.0%estimated ± 2.8 pp, high confidence
LongBench v251.2%estimated ± 5.5 pp, low confidence
τ²-bench results10.5%measured
AA Coding Index10.1%measured
AA-MMMU-Pro48.0%measured
APEX-Agents0.0%estimated ± 9.4 pp, low confidence
APEX-Agents-AA6.0%estimated ± 9.5 pp, medium confidence
BioMysteryBench (human-difficult)0.0%estimated ± 6.8 pp, low confidence
DeepSearchQA3.5%estimated ± 4.5 pp, medium confidence
SWE-bench Verified41.8%estimated ± 6.3 pp, low confidence
BFCL v453.9%estimated ± 2.7 pp, high confidence
CyberGym45.7%estimated ± 5.3 pp, low confidence
JobBench0.0%estimated ± 8.7 pp, low confidence
SWE-bench Pro15.0%estimated ± 6.0 pp, low confidence
WideResearch0.0%estimated ± 7.8 pp, low confidence
AA Agentic Index0.1%measured
MMLU-Pro74.8%estimated ± 5.0 pp, medium confidence
AA-IFBench31.8%measured
GPQA47.8%estimated ± 6.1 pp, medium confidence
MMLU80.3%estimated ± 0.9 pp, medium confidence
Vals GPQA Diamond42.0%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench59.4%estimated ± 5.7 pp, low confidence
Vals MMLU-Pro65.7%estimated ± 2.9 pp, medium confidence
MMMLU83.3%estimated ± 0.7 pp, medium confidence
MMMU63.2%estimated ± 2.7 pp, medium confidence
AA MMLU-Pro83.0%estimated ± 0.8 pp, medium confidence
Gert Labs26.9%estimated ± 10.0 pp, low confidence
AA Harvey LAB v1.079.4%estimated ± 1.2 pp, low confidence
AA Tau3 Banking16.1%estimated ± 3.7 pp, medium confidence
ARC-AGI-174.7%estimated ± 7.8 pp, low confidence
ARC-AGI-230.5%estimated ± 14.4 pp, low confidence
MazeBench0.4%estimated ± 5.5 pp, low confidence
OSWorld-Verified55.4%estimated ± 8.4 pp, low confidence
ParseBench-141.9%estimated ± 6.2 pp, low confidence
Vals SWE-bench32.5%estimated ± 5.5 pp, low confidence
CWE-Bench-AA0.0%estimated ± 10.1 pp, low confidence
AA Cyber Index0.1%estimated ± 9.2 pp, low confidence
DeepsecBench-AA0.0%estimated ± 8.9 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)2.1%estimated ± 2.5 pp, low confidence
AA ITBench32.9%estimated ± 4.0 pp, medium 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-Verified0.6%estimated ± 2.3 pp, low 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 Bench2.4%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-234.0%estimated ± 6.2 pp, low confidence
CharXiv60.6%estimated ± 6.3 pp, low confidence
AI2D_TEST88.0%estimated ± 2.0 pp, low confidence
C-Eval87.0%estimated ± 1.0 pp, low confidence
MCP Atlas64.6%estimated ± 7.8 pp, low confidence
MMLU-Redux92.6%estimated ± 0.8 pp, low confidence
MMMU-Pro48.1%estimated ± 1.5 pp, high confidence
NL2Repo3.6%estimated ± 4.7 pp, medium confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
ScreenSpot Pro55.0%estimated ± 10.8 pp, low confidence
SuperGPQA64.4%estimated ± 9.3 pp, low confidence
Toolathlon27.0%estimated ± 6.3 pp, low confidence
Video-MME (w/o subtitle)71.1%estimated ± 1.7 pp, low confidence
HealthBench Hard0.0%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)77.1%estimated ± 4.0 pp, low confidence
React Native Evals66.6%estimated ± 3.2 pp, medium confidence
ResearchClawBench0.3%estimated ± 1.9 pp, medium 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
STEMBench2.3%estimated ± 0.2 pp, low confidence
SimpleQA8.5%estimated ± 4.3 pp, low confidence
MRCRv222.8%estimated ± 11.3 pp, low confidence
MMLongBench-Doc39.5%estimated ± 2.6 pp, low confidence
BioBasicsBench6.3%estimated ± 10.2 pp, low confidence
MMMU-Pro w/ Python53.9%estimated ± 2.0 pp, medium confidence