benchgap
Google · model

Gemini 3.5 Flash-Lite benchmark scores

As of 2026-11-22, Gemini 3.5 Flash-Lite (Google) has measured scores on 32 benchmarks and estimated scores on 140 more.

BenchmarkScoreSource
AA-GPQA Diamond83.8%measured
AA-HLE18.8%measured
AA-SciCode41.3%measured
AIME2695.9%estimated ± 1.2 pp, low confidence
Artificial Analysis Intelligence Index11.7%measured
CritPt0.0%measured
GDPval-AA24.2%measured
GPQA Diamond87.3%estimated ± 1.8 pp, high confidence
HLE22.5%estimated ± 8.5 pp, medium confidence
AA-LCR76.0%measured
LiveCodeBench v686.0%estimated ± 2.2 pp, medium confidence
AA-Omniscience Accuracy26.5%measured
SciCode41.4%estimated ± 3.1 pp, high confidence
Terminal-Bench 2.154.0%measured
BrowseComp83.8%estimated ± 4.7 pp, high confidence
HLE w/ tools45.5%estimated ± 5.3 pp, low confidence
LongBench v262.5%estimated ± 5.5 pp, medium confidence
AA Coding Index49.3%measured
AA-MMMU-Pro79.0%measured
APEX-Agents17.4%estimated ± 9.4 pp, low confidence
APEX-Agents-AA29.8%estimated ± 7.8 pp, medium confidence
BioMysteryBench (human-difficult)0.0%estimated ± 6.8 pp, low confidence
DeepSearchQA80.9%estimated ± 4.5 pp, high confidence
SWE-bench Verified76.1%estimated ± 3.6 pp, high confidence
BFCL v473.2%estimated ± 2.7 pp, high confidence
CyberGym57.8%estimated ± 5.3 pp, low confidence
JobBench21.2%estimated ± 8.7 pp, medium confidence
SWE-bench Pro54.2%measured
WideResearch81.4%estimated ± 2.1 pp, medium confidence
AA Agentic Index15.9%measured
MMLU-Pro85.3%estimated ± 4.8 pp, high confidence
FailureSensorIQ65.9%estimated ± 1.7 pp, high confidence
GPQA85.7%estimated ± 4.5 pp, high confidence
MMLU90.5%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond83.8%measured
Vals LiveCodeBench79.0%measured
Vals MMLU-Pro85.8%measured
MMMLU83.3%estimated ± 0.7 pp, medium confidence
MMMU85.9%estimated ± 2.7 pp, high confidence
Chess Puzzles16.0%measured
AA MMLU-Pro85.3%estimated ± 0.7 pp, high confidence
Gert Labs23.8%measured
AA EnterpriseOps-Gym42.3%measured
AA Harvey LAB v1.079.8%estimated ± 1.2 pp, low confidence
AA Tau3 Banking25.2%estimated ± 3.7 pp, medium confidence
AA Terminal-Bench 2.179.7%estimated ± 2.5 pp, medium confidence
ApprenticeBench6.1%estimated ± 6.3 pp, low confidence
ARC-AGI-175.7%estimated ± 6.5 pp, medium confidence
ARC-AGI-232.1%estimated ± 13.8 pp, low confidence
CursorBench 3.147.9%estimated ± 4.8 pp, low confidence
CursorBench 3.248.9%estimated ± 3.6 pp, medium confidence
EBR-bench7.8%estimated ± 10.4 pp, low confidence
Terminal-Bench 3.02.0%estimated ± 6.9 pp, low confidence
FrontierCode 1.1 Main19.5%estimated ± 4.6 pp, medium confidence
FrontierMath v2 (Tier 4)0.0%measured
FrontierMath v2 (Tiers 1-3)26.0%measured
FrontierSWE v25.6%estimated ± 8.3 pp, low confidence
Furniture Assembly32.1%estimated ± 7.1 pp, medium confidence
MaxxBench0.0%estimated ± 5.6 pp, low confidence
MazeBench0.0%estimated ± 2.7 pp, high confidence
Mystery Game Puzzles19.0%measured
NYT Connections60.4%measured
OfficeQA Pro51.4%estimated ± 6.8 pp, medium confidence
OSWorld-Verified74.0%measured
ParseBench-159.5%measured
Terminal-Bench 4.10.0%estimated ± 10.9 pp, low confidence
Terminal-Bench Hard44.9%estimated ± 3.9 pp, medium confidence
Vals SWE-bench75.0%measured
Terminal-Bench 2.1 (Vals AI)50.2%measured
VulcanBench v380.5%estimated ± 5.6 pp, low confidence
CWE-Bench-AA34.8%estimated ± 8.1 pp, low confidence
AA Cyber Index11.0%estimated ± 9.2 pp, low confidence
DeepsecBench-AA7.0%estimated ± 8.2 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)49.3%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)44.8%estimated ± 1.1 pp, low confidence
AA ITBench37.9%estimated ± 4.0 pp, high confidence
Bug Hunt Bench15.4%estimated ± 10.5 pp, low confidence
Chartography (tools)82.8%estimated ± 4.1 pp, low confidence
CursorBench 4.031.2%estimated ± 3.3 pp, medium confidence
CWE-bench v135.4%estimated ± 5.7 pp, low confidence
DeepSWE56.3%estimated ± 7.2 pp, low confidence
DRACO71.9%estimated ± 2.0 pp, medium confidence
FrontierCode 2.019.7%estimated ± 6.7 pp, low confidence
FrontierPhysics0.0%estimated ± 4.6 pp, medium confidence
HLE w/o tools32.9%estimated ± 4.9 pp, high confidence
OSWorld 2.08.3%estimated ± 3.6 pp, high confidence
OSWorld 2.13.2%estimated ± 3.6 pp, medium confidence
PostTrainBench v1.119.8%estimated ± 3.7 pp, medium confidence
SpireClimb5.8%estimated ± 7.2 pp, low confidence
StealthMark30.5%estimated ± 3.5 pp, medium confidence
SWE-bench Multimodal15.0%estimated ± 5.6 pp, low confidence
Toolathlon-Verified41.9%estimated ± 2.3 pp, low confidence
VulcanBench Frontier v471.2%estimated ± 6.8 pp, low confidence
AA AutomationBench39.8%estimated ± 9.9 pp, low confidence
GDP.pdf11.1%estimated ± 4.2 pp, medium confidence
AA Terminal-Bench 4.00.0%estimated ± 13.7 pp, low confidence
ARC-AGI-30.0%estimated ± 8.6 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
CWE-bench28.6%estimated ± 6.2 pp, low confidence
MKA32.8%estimated ± 4.6 pp, medium confidence
SkillsBench official leaderboard (BenchFlow)47.8%estimated ± 6.1 pp, medium confidence
BinaryAudit35.8%estimated ± 12.1 pp, low confidence
CompileBench82.2%estimated ± 10.0 pp, low confidence
OTelBench21.6%estimated ± 4.1 pp, medium confidence
Vibe Code Bench21.5%estimated ± 10.0 pp, low confidence
FACTS Multimodal36.1%measured
Hermes Bench55.0%estimated ± 2.9 pp, high confidence
Hermes Index16.6%estimated ± 5.7 pp, low confidence
ParseBench-262.2%measured
CharXiv83.5%estimated ± 5.6 pp, low confidence
CharXiv w/o tools77.7%estimated ± 1.8 pp, low confidence
ExploitBench31.5%estimated ± 1.9 pp, low confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
AI2D_TEST94.1%estimated ± 2.0 pp, medium confidence
C-Eval89.1%estimated ± 1.0 pp, medium confidence
Claw-Eval65.6%estimated ± 6.2 pp, low confidence
CountBench97.5%estimated ± 2.9 pp, medium confidence
DynaMath85.5%estimated ± 3.0 pp, medium confidence
ERQA68.5%estimated ± 3.1 pp, high confidence
HMMT Feb 202683.5%estimated ± 1.5 pp, low confidence
HMMT Nov 202591.1%estimated ± 1.5 pp, medium confidence
MathVision89.6%estimated ± 3.1 pp, high confidence
MCP Atlas64.6%estimated ± 7.8 pp, low confidence
MMAnswerBench80.4%estimated ± 2.4 pp, medium confidence
MMLU-Redux94.3%estimated ± 0.8 pp, medium confidence
MMMU-Pro79.7%estimated ± 1.5 pp, high confidence
NL2Repo42.5%estimated ± 4.7 pp, high confidence
PostTrainBench v118.2%estimated ± 3.6 pp, high confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
RealWorldQA85.5%estimated ± 2.9 pp, medium confidence
ScreenSpot Pro81.4%estimated ± 10.1 pp, low confidence
SuperGPQA66.3%estimated ± 9.3 pp, medium confidence
Terminal-Bench 2.058.8%estimated ± 5.8 pp, medium confidence
Toolathlon40.1%estimated ± 6.3 pp, medium confidence
V*100.0%estimated ± 7.5 pp, medium confidence
Video-MME (w/o subtitle)85.9%estimated ± 1.7 pp, medium confidence
Video-MME (with subtitle)87.6%estimated ± 3.7 pp, medium confidence
AA LiveCodeBench88.9%estimated ± 2.6 pp, high confidence
HealthBench Hard0.0%estimated ± 8.6 pp, low confidence
LiveCodeBench Pro79.0%estimated ± 6.0 pp, low confidence
MedXpertQA (MM)76.5%estimated ± 6.5 pp, low confidence
MMLU-Pro (Arcee)77.1%estimated ± 4.0 pp, low confidence
React Native Evals76.5%estimated ± 3.2 pp, high confidence
ResearchClawBench15.0%estimated ± 1.9 pp, high confidence
SWE-Rebench58.1%estimated ± 8.9 pp, low confidence
PostTrainBench17.2%estimated ± 3.7 pp, medium confidence
DAYJOB0.0%measured
DAYJOB Healthcare0.0%measured
Finance Agent v255.1%estimated ± 2.4 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
FrontierCode 1.1 Extended54.0%estimated ± 3.0 pp, low confidence
HealthBench (raw)26.3%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)45.5%estimated ± 3.4 pp, low confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)38.4%estimated ± 4.5 pp, medium confidence
HLE-Verified0.1%estimated ± 4.6 pp, low confidence
LABBench280.8%estimated ± 1.8 pp, low confidence
ScarfBench24.6%estimated ± 9.1 pp, low confidence
BlenderWorld (text-only)70.1%estimated ± 2.8 pp, medium confidence
Cookie-Bench77.0%estimated ± 1.3 pp, medium confidence
STEMBench2.4%estimated ± 0.2 pp, medium confidence
SimpleQA27.0%estimated ± 4.3 pp, medium confidence
Agents' Last Exam29.6%estimated ± 9.7 pp, low confidence
BabyVision w/ Python90.2%estimated ± 4.0 pp, low confidence
OpenHarmony Bench v1.051.0%estimated ± 2.4 pp, medium confidence
SEC-Bench Pro20.7%estimated ± 5.6 pp, low confidence
MRCRv272.2%measured
MMLongBench-Doc61.2%estimated ± 2.6 pp, low confidence
BioBasicsBench34.1%estimated ± 3.8 pp, low confidence
LifeVal1.8%estimated ± 5.0 pp, low confidence
MMMU-Pro w/ Python81.8%estimated ± 2.0 pp, high confidence
ExploitBench Internal Port0.0%estimated ± 1.4 pp, low confidence