benchgap
Google · model

Gemini 3.7 Flash benchmark scores

As of 2026-11-22, Gemini 3.7 Flash (Google) has measured scores on 50 benchmarks and estimated scores on 137 more.

BenchmarkScoreSource
AA-GPQA Diamond94.5%measured
AA-HLE47.9%measured
AA-SciCode57.2%measured
AIME2699.2%estimated ± 1.2 pp, low confidence
Artificial Analysis Intelligence Index39.1%measured
CritPt14.3%measured
GDPval-AA44.6%measured
GPQA Diamond93.8%estimated ± 1.4 pp, high confidence
HLE57.5%estimated ± 6.1 pp, medium confidence
AA-LCR81.7%measured
LiveCodeBench v690.3%estimated ± 2.2 pp, low confidence
AA-Omniscience Accuracy55.3%measured
SciCode54.2%estimated ± 2.9 pp, low confidence
Terminal-Bench 2.185.8%measured
BrowseComp84.5%estimated ± 1.9 pp, high confidence
HLE w/ tools55.4%estimated ± 5.3 pp, medium confidence
LongBench v267.2%estimated ± 5.5 pp, medium confidence
τ²-bench results92.4%estimated ± 6.5 pp, low confidence
AA Coding Index76.1%measured
AA-MMMU-Pro85.5%measured
APEX-Agents37.5%estimated ± 7.4 pp, low confidence
APEX-Agents-AA38.4%estimated ± 2.9 pp, medium confidence
BioMysteryBench (human-difficult)43.5%measured
DeepSearchQA90.9%estimated ± 4.5 pp, high confidence
SWE-bench Verified89.0%estimated ± 2.2 pp, medium confidence
AutomationBench30.4%measured
BFCL v476.2%estimated ± 2.7 pp, medium confidence
CyberGym79.5%estimated ± 4.5 pp, high confidence
JobBench62.9%estimated ± 4.9 pp, medium confidence
SWE-bench Pro73.9%estimated ± 4.7 pp, high confidence
WideResearch83.7%estimated ± 3.3 pp, medium confidence
AA Agentic Index36.4%measured
MMLU-Pro87.7%estimated ± 4.8 pp, medium confidence
FailureSensorIQ68.3%estimated ± 1.7 pp, high confidence
GPQA94.4%estimated ± 1.6 pp, high confidence
MMLU90.5%estimated ± 0.9 pp, medium confidence
Vals GPQA Diamond93.9%measured
Vals LiveCodeBench88.7%measured
Vals MMLU-Pro90.1%measured
MMMLU90.2%estimated ± 0.7 pp, low confidence
MMMU89.7%estimated ± 2.7 pp, medium confidence
Chess Puzzles66.0%measured
AA MMLU-Pro89.6%estimated ± 0.7 pp, medium confidence
Gert Labs61.4%measured
AA-AnalystAgent60.0%measured
AA Harvey LAB v1.090.7%measured
AA Tau3 Banking43.4%estimated ± 3.3 pp, medium confidence
AA Terminal-Bench 2.185.8%measured
ApprenticeBench16.0%measured
ARC-AGI-195.5%measured
ARC-AGI-284.6%measured
BabaIsBench100.0%measured
CursorBench 3.161.8%estimated ± 3.4 pp, medium confidence
CursorBench 3.260.7%estimated ± 1.6 pp, medium confidence
EBR-bench13.1%estimated ± 9.3 pp, medium confidence
Terminal-Bench 3.014.9%measured
FrontierCode 1.1 Main43.6%measured
FrontierMath v2 (Tier 4)36.6%measured
FrontierMath v2 (Tiers 1-3)71.6%measured
FrontierSWE v220.3%measured
Furniture Assembly26.7%measured
MaxxBench50.7%estimated ± 6.6 pp, low confidence
MazeBench1.0%measured
MirrorCode41.1%measured
Mystery Game Puzzles37.0%measured
NYT Connections94.0%measured
OfficeQA Pro67.6%estimated ± 6.8 pp, medium confidence
OSWorld-Verified78.4%estimated ± 2.3 pp, medium confidence
ParseBench-170.4%measured
Terminal-Bench 4.112.4%measured
Terminal-Bench Hard55.9%estimated ± 2.8 pp, medium confidence
Vals SWE-bench80.8%measured
Terminal-Bench 2.1 (Vals AI)77.5%measured
VulcanBench v386.3%estimated ± 5.6 pp, low confidence
CWE-Bench-AA54.7%estimated ± 4.5 pp, medium confidence
AA Cyber Index22.6%estimated ± 9.2 pp, low confidence
DeepsecBench-AA23.0%estimated ± 8.2 pp, medium confidence
Harvey LAB-AA v1.17.5%estimated ± 4.0 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)57.7%estimated ± 4.3 pp, medium confidence
HealthBench Professional (raw, Artificial Analysis)60.9%estimated ± 0.8 pp, low confidence
AA ITBench48.3%estimated ± 3.2 pp, high confidence
Bug Hunt Bench25.3%estimated ± 7.7 pp, medium confidence
Chartography (tools)86.6%estimated ± 4.1 pp, low confidence
CursorBench 4.042.1%estimated ± 2.0 pp, high confidence
CWE-bench v157.4%estimated ± 5.1 pp, medium confidence
DeepSWE65.3%measured
DRACO86.9%estimated ± 0.7 pp, low confidence
FrontierCode 2.024.3%estimated ± 4.8 pp, medium confidence
FrontierPhysics0.0%estimated ± 4.4 pp, high confidence
HLE w/o tools51.1%estimated ± 4.9 pp, high confidence
OSWorld 2.047.9%measured
OSWorld 2.174.0%estimated ± 3.6 pp, high confidence
OSWorld 2.1 Offline43.4%estimated ± 1.9 pp, low confidence
PostTrainBench v1.124.8%estimated ± 3.7 pp, high confidence
SpireClimb5.8%estimated ± 7.2 pp, medium confidence
StealthMark45.3%estimated ± 6.5 pp, medium confidence
SWE-bench Multimodal56.8%estimated ± 5.6 pp, low confidence
Terminal-Bench 4.019.9%estimated ± 4.5 pp, high confidence
Terminal-Bench-Science 0.10.0%estimated ± 10.7 pp, low confidence
Toolathlon-Verified78.5%estimated ± 1.0 pp, medium confidence
VulcanBench Frontier v486.5%estimated ± 4.0 pp, low confidence
AA AutomationBench60.4%estimated ± 9.9 pp, low confidence
GDP.pdf22.9%estimated ± 4.2 pp, high confidence
AA Terminal-Bench 4.012.0%estimated ± 6.2 pp, medium confidence
ARC-AGI-37.6%estimated ± 8.6 pp, low confidence
ARC-AGI-3 Provider Adapter29.8%estimated ± 7.3 pp, medium confidence
cursorBench4144.8%estimated ± 3.7 pp, high confidence
CWE-bench65.7%estimated ± 4.6 pp, high confidence
MKA40.6%estimated ± 4.6 pp, high confidence
SkillsBench official leaderboard (BenchFlow)59.0%estimated ± 6.1 pp, low confidence
BinaryAudit35.8%estimated ± 12.1 pp, low confidence
CompileBench100.0%estimated ± 10.0 pp, low confidence
OTelBench22.5%estimated ± 6.6 pp, medium confidence
Vibe Code Bench72.6%estimated ± 5.6 pp, low confidence
FACTS Multimodal52.5%estimated ± 4.0 pp, high confidence
Hermes Bench70.1%estimated ± 1.5 pp, medium confidence
Hermes Index37.2%estimated ± 3.1 pp, high confidence
ParseBench-276.7%measured
CharXiv88.7%measured
CharXiv w/o tools84.5%measured
ExploitBench32.4%estimated ± 6.5 pp, low confidence
ExploitGym13.5%estimated ± 2.7 pp, high confidence
AI2D_TEST93.5%estimated ± 0.9 pp, low confidence
C-Eval97.3%estimated ± 1.0 pp, low confidence
CountBench100.0%estimated ± 2.9 pp, low confidence
DynaMath87.8%estimated ± 0.8 pp, low confidence
ERQA70.6%estimated ± 2.9 pp, medium confidence
HMMT Feb 202697.3%estimated ± 1.5 pp, low confidence
HMMT Nov 202595.5%estimated ± 1.5 pp, low confidence
MathVision94.7%estimated ± 3.1 pp, medium confidence
MCP Atlas77.7%estimated ± 5.8 pp, low confidence
MLVU (M-Avg)88.5%estimated ± 1.5 pp, high confidence
MMAnswerBench92.1%estimated ± 2.4 pp, low confidence
MMLU-Redux97.9%estimated ± 0.8 pp, low confidence
MMMU-Pro85.0%estimated ± 1.5 pp, medium confidence
NL2Repo46.0%estimated ± 4.7 pp, high confidence
PostTrainBench v125.4%estimated ± 3.6 pp, high confidence
QwenClawBench93.2%estimated ± 6.0 pp, low confidence
RealWorldQA86.8%estimated ± 1.5 pp, high confidence
ScreenSpot Pro83.7%estimated ± 6.8 pp, medium confidence
SuperGPQA100.0%estimated ± 9.3 pp, low confidence
Terminal-Bench 2.077.6%estimated ± 5.8 pp, low confidence
Toolathlon54.9%estimated ± 1.7 pp, medium confidence
V*100.0%estimated ± 7.5 pp, low confidence
Video-MME (w/o subtitle)90.9%estimated ± 1.7 pp, low confidence
Video-MME (with subtitle)90.2%estimated ± 2.9 pp, high confidence
VideoMMMU86.9%estimated ± 1.5 pp, medium confidence
We-Math84.6%estimated ± 7.9 pp, low confidence
AA LiveCodeBench92.1%estimated ± 2.6 pp, medium confidence
HealthBench Hard31.0%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)78.5%estimated ± 6.4 pp, low confidence
React Native Evals83.3%estimated ± 3.2 pp, medium confidence
ResearchClawBench19.8%estimated ± 1.9 pp, high confidence
PostTrainBench33.1%estimated ± 2.4 pp, high confidence
DAYJOB1.4%estimated ± 2.7 pp, high confidence
DAYJOB Healthcare0.0%estimated ± 4.0 pp, high confidence
Finance Agent v257.5%estimated ± 2.4 pp, medium confidence
BioMysteryBench (human-solvable)87.1%measured
FrontierCode 1.1 Extended60.1%estimated ± 3.4 pp, low confidence
HealthBench (raw)55.6%estimated ± 6.0 pp, medium confidence
HealthBench (length-adjusted)57.3%estimated ± 2.5 pp, low confidence
HealthBench Professional57.8%estimated ± 4.2 pp, medium confidence
HealthBench Professional (raw)65.9%estimated ± 4.5 pp, high confidence
HLE-Verified53.6%measured
LABBench282.1%measured
ScarfBench64.7%estimated ± 3.8 pp, medium confidence
BlenderWorld (text-only)72.8%estimated ± 2.8 pp, medium confidence
Cookie-Bench82.6%estimated ± 1.3 pp, medium confidence
STEMBench2.6%estimated ± 0.2 pp, medium confidence
SimpleQA35.9%estimated ± 7.8 pp, low confidence
Agents' Last Exam26.3%measured
BabyVision w/ Python89.6%estimated ± 3.7 pp, low confidence
OpenHarmony Bench v1.058.9%estimated ± 2.4 pp, high confidence
SEC-Bench Pro53.9%estimated ± 9.3 pp, medium confidence
BabyVision63.4%estimated ± 7.4 pp, low confidence
MMVU80.1%estimated ± 3.6 pp, medium confidence
PerceptionBench58.0%estimated ± 3.8 pp, medium confidence
ZeroBench23.5%estimated ± 7.1 pp, low confidence
MRCRv285.9%estimated ± 11.3 pp, low confidence
LVBench85.4%measured
MMLongBench-Doc61.5%estimated ± 2.6 pp, low confidence
BioBasicsBench39.0%estimated ± 2.8 pp, medium confidence
LifeVal85.2%estimated ± 2.3 pp, medium confidence
MMMU-Pro w/ Python87.7%estimated ± 2.0 pp, medium confidence
ExploitBench Internal Port16.7%estimated ± 1.4 pp, medium confidence
MathVision w/ Python95.0%estimated ± 1.0 pp, low confidence
SWE-Atlas Codebase QnA59.1%estimated ± 4.8 pp, high confidence