benchgap
Google · model

Gemini 3.1 Flash-Lite benchmark scores

As of 2026-11-22, Gemini 3.1 Flash-Lite (Google) has measured scores on 14 benchmarks and estimated scores on 105 more.

BenchmarkScoreSource
AA-GPQA Diamond82.1%estimated ± 3.6 pp, high confidence
AA-HLE19.4%estimated ± 6.2 pp, medium confidence
AA-SciCode45.2%estimated ± 3.8 pp, medium confidence
AIME2694.3%estimated ± 1.4 pp, high confidence
Artificial Analysis Intelligence Index19.1%estimated ± 5.8 pp, medium confidence
CritPt1.8%estimated ± 5.3 pp, medium confidence
GDPval-AA18.8%estimated ± 10.5 pp, low confidence
GPQA Diamond85.7%estimated ± 1.8 pp, medium confidence
HLE40.4%estimated ± 9.2 pp, low confidence
LiveCodeBench v686.5%estimated ± 2.2 pp, medium confidence
AA-Omniscience Accuracy37.0%estimated ± 6.5 pp, medium confidence
SciCode44.0%estimated ± 4.5 pp, low confidence
Terminal-Bench 2.116.8%estimated ± 6.7 pp, low confidence
BrowseComp67.1%estimated ± 8.8 pp, medium confidence
HLE w/ tools45.6%estimated ± 5.7 pp, medium confidence
AA Coding Index41.7%estimated ± 5.6 pp, medium confidence
AA-MMMU-Pro71.9%estimated ± 4.9 pp, medium confidence
APEX-Agents-AA12.1%estimated ± 9.3 pp, medium confidence
SWE-bench Verified73.0%estimated ± 4.4 pp, high confidence
CyberGym48.7%estimated ± 11.0 pp, low confidence
JobBench18.7%estimated ± 14.2 pp, low confidence
SWE-bench Pro53.0%estimated ± 2.9 pp, low confidence
WideResearch67.6%estimated ± 3.3 pp, high confidence
JevBench 1.414.3%measured
AA Agentic Index15.3%estimated ± 9.4 pp, medium confidence
MMLU-Pro85.6%estimated ± 4.8 pp, high confidence
FailureSensorIQ62.0%estimated ± 1.7 pp, medium confidence
GPQA83.3%estimated ± 4.5 pp, high confidence
MMLU93.5%estimated ± 1.2 pp, medium confidence
Vals GPQA Diamond81.1%measured
Vals LiveCodeBench80.1%measured
Vals MMLU-Pro86.2%measured
MMMU80.0%estimated ± 3.7 pp, medium confidence
Chess Puzzles19.3%estimated ± 12.3 pp, low confidence
AA MMLU-Pro87.3%estimated ± 1.1 pp, high confidence
Gert Labs25.7%measured
AA Terminal-Bench 2.179.2%estimated ± 2.5 pp, medium confidence
ApprenticeBench3.2%estimated ± 10.4 pp, low confidence
ARC-AGI-170.1%estimated ± 6.5 pp, medium confidence
ARC-AGI-220.2%estimated ± 13.8 pp, low confidence
CursorBench 3.136.5%estimated ± 5.8 pp, low confidence
CursorBench 3.248.6%estimated ± 5.4 pp, low confidence
EBR-bench0.0%estimated ± 9.1 pp, low confidence
FrontierCode 1.1 Main14.8%estimated ± 5.2 pp, low confidence
FrontierMath v2 (Tier 4)2.3%estimated ± 4.0 pp, high confidence
FrontierMath v2 (Tiers 1-3)27.7%measured
FrontierSWE v24.7%estimated ± 9.5 pp, low confidence
MazeBench0.0%estimated ± 2.7 pp, high confidence
Mystery Game Puzzles11.8%estimated ± 9.8 pp, low confidence
NYT Connections8.2%measured
OfficeQA Pro52.3%estimated ± 7.0 pp, low confidence
OSWorld-Verified63.5%estimated ± 8.6 pp, low confidence
ParseBench-156.7%measured
Terminal-Bench 4.14.0%estimated ± 14.9 pp, low confidence
Terminal-Bench Hard43.5%estimated ± 3.9 pp, medium confidence
Vals SWE-bench62.8%measured
Terminal-Bench 2.1 (Vals AI)34.1%measured
VulcanBench v380.9%estimated ± 5.6 pp, low confidence
CWE-Bench-AA36.5%estimated ± 8.1 pp, low confidence
AA Cyber Index11.4%estimated ± 12.4 pp, low confidence
DeepsecBench-AA7.7%estimated ± 8.2 pp, low confidence
AA ITBench36.1%estimated ± 4.6 pp, low confidence
CursorBench 4.030.7%estimated ± 3.4 pp, medium confidence
CWE-bench v136.6%estimated ± 5.7 pp, low confidence
DeepSWE56.3%estimated ± 7.2 pp, low confidence
HLE w/o tools34.4%estimated ± 4.9 pp, high confidence
OSWorld 2.15.0%estimated ± 3.6 pp, medium confidence
PostTrainBench v1.19.6%estimated ± 3.7 pp, medium confidence
StealthMark41.3%estimated ± 10.7 pp, low confidence
SWE-bench Multimodal3.3%estimated ± 5.6 pp, low confidence
Toolathlon-Verified60.1%estimated ± 3.0 pp, high confidence
AA AutomationBench40.9%estimated ± 9.9 pp, low confidence
GDP.pdf11.8%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
CWE-bench30.1%estimated ± 6.2 pp, low confidence
MKA32.8%estimated ± 4.6 pp, medium confidence
SkillsBench official leaderboard (BenchFlow)20.1%measured
BinaryAudit7.4%estimated ± 12.0 pp, low confidence
OTelBench6.8%estimated ± 6.6 pp, medium confidence
Vibe Code Bench0.0%measured
Hermes Index17.8%estimated ± 5.7 pp, low confidence
ParseBench-263.6%measured
CharXiv73.2%measured
CharXiv w/o tools75.5%estimated ± 1.8 pp, low confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
AI2D_TEST87.8%estimated ± 0.9 pp, medium confidence
CountBench93.2%estimated ± 3.7 pp, low confidence
DynaMath82.7%estimated ± 0.8 pp, medium confidence
ERQA61.9%estimated ± 5.6 pp, medium confidence
HMMT Feb 202684.6%estimated ± 3.1 pp, high confidence
HMMT Nov 202591.5%estimated ± 1.5 pp, medium confidence
MathVision81.1%estimated ± 3.3 pp, high confidence
MLVU (M-Avg)83.4%estimated ± 1.5 pp, high confidence
MMAnswerBench80.9%estimated ± 2.4 pp, medium confidence
MMMU-Pro75.2%estimated ± 3.1 pp, high confidence
NL2Repo37.8%estimated ± 4.7 pp, medium confidence
PostTrainBench v119.0%estimated ± 3.1 pp, low confidence
RealWorldQA80.4%estimated ± 1.5 pp, high confidence
ScreenSpot Pro58.6%estimated ± 6.8 pp, medium confidence
Terminal-Bench 2.044.4%estimated ± 5.8 pp, medium confidence
Toolathlon37.8%estimated ± 8.0 pp, medium confidence
Video-MME (with subtitle)83.3%estimated ± 2.9 pp, high confidence
VideoMMMU84.4%estimated ± 1.5 pp, medium confidence
We-Math84.5%estimated ± 7.9 pp, low confidence
AA LiveCodeBench84.2%estimated ± 2.6 pp, high confidence
MedXpertQA (MM)72.3%estimated ± 6.4 pp, low confidence
React Native Evals0.0%estimated ± 3.0 pp, low confidence
SWE-Rebench0.0%estimated ± 6.5 pp, low confidence
PostTrainBench7.7%estimated ± 3.7 pp, medium confidence
Finance Agent v255.1%estimated ± 2.4 pp, low confidence
LABBench281.0%estimated ± 1.8 pp, low confidence
ScarfBench35.0%estimated ± 12.3 pp, low confidence
Agents' Last Exam29.6%estimated ± 9.7 pp, low confidence
OpenHarmony Bench v1.048.9%estimated ± 3.2 pp, medium confidence
BabyVision26.4%estimated ± 11.5 pp, low confidence
MMVU73.1%estimated ± 3.6 pp, low confidence
LifeVal2.9%estimated ± 5.0 pp, low confidence
MMMU-Pro w/ Python77.9%estimated ± 2.7 pp, medium confidence