Gemini 3.7 Flash

Gemini 3.7 Flash ranks first on 1H-VideoQA.

Google DeepMind Released 13 Aug 2026 Family Gemini 3.7 The lab's model card

147

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Google DeepMind Aug 2026

Gemini 3.7 Flash

Closed weights Mid-size

158.2 #21 of 271

Epoch Capabilities Index

DeepSWE 65.5% #12 /28
Terminal-Bench 4.0 11.2% #23 /23
Harvey LAB (Legal Agent Benchmark) 8.75% #25 /80

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

Benchmark	Score	Rank	Source
LMArena (Elo)	1,490	#14 of 333	Official leaderboard
FACTS Multimodal	49.8%	#2 of 39	Official leaderboard
MRCR v2	97%	#2 of 27	Model card
Extended NYT Connections	94%	#9 of 97	Official leaderboard
Judgemark v4	83.4	#4 of 40	Official leaderboard
SimpleQA Verified	73.2%	#6 of 56	Official leaderboard
FACTS Parametric	78.7%	#5 of 45	Official leaderboard
FACTS Benchmark Suite	65.4%	#5 of 40	Official leaderboard
Global MMLU Lite	94.9%	#6 of 43	Official leaderboard
Creative Writing v3	76.1	#29 of 120	Official leaderboard
Continual Learning Exam	33.7%	#3 of 10	Official leaderboard
BullshitBench V2	35%	#65 of 122	Official leaderboard
FACTS Search V2	80.9%	#12 of 21	Official leaderboard
BullshitBench	23.6%	#65 of 107	Official leaderboard
HLE-Verified	53.6%	#3 of 4	Model card

Math and science

Benchmark	Score	Rank	Source
GPQA Diamond	94.8%	#6 of 219	Epoch AI
DTBench	94.7%	#10 of 178	Official leaderboard
ARC-AGI-2	84.6%	#14 of 95	Official leaderboard
ARC-AGI	95.5%	#15 of 92	Official leaderboard
OTIS Mock AIME 2024-2025	97.2%	#35 of 202	Epoch AI
Human Behavior Bench	79.7	#3 of 11	Official leaderboard
ProofBench	58%	#24 of 83	Epoch AI
FrontierMath Tiers 1-3 v2	71.6%	#26 of 89	Epoch AI
CritPt	14.3%	#47 of 160	Epoch AI
BioMysteryBench	87.1%	#3 of 8	Model card
FrontierMath Tier 4 v2	36.6%	#28 of 71	Epoch AI
ProofBench v1.1	58%	#25 of 51	Official leaderboard
LatchBio Capabilities v1.0	40.8%	#17 of 27	Official leaderboard
xbench-ScienceQA	70.2%	#20 of 29	Official leaderboard
Verifying the Verifiers (Project APE CRED benchmark)	74%	#16 of 23	Official leaderboard
Terminal-Bench-Science	5.71%	#15 of 17	Official leaderboard
ForecastBench	65.7	#80 of 86	Official leaderboard
LABBench2	82.1%	#3 of 3	Model card

Coding

Benchmark	Score	Rank	Source
WebDev Arena	1,587	#22 of 105	Epoch AI
Code Arena	1,590	#30 of 124	Official leaderboard
Image-to-WebDev Arena	1,599	#15 of 55	Official leaderboard
IOI v2 (Vals)	67.8%	#15 of 45	Official leaderboard
Vibe Code Bench	70.4%	#45 of 115	Official leaderboard
FrontierCode	43.6%	#18 of 46	Epoch AI
DeepSWE	65.5%	#12 of 28	Official leaderboard
Code Migration	34.8%	#38 of 78	Official leaderboard
Vision2Web	76.5%	#5 of 10	Official leaderboard
ALE-Bench	904	#62 of 121	Epoch AI
MirrorCode	41.1%	#17 of 28	Epoch AI
FrontierSWE	20.3%	#15 of 21	Epoch AI
Vals RSI Index	0.18	#20 of 25	Official leaderboard
FrontierCode 1.1	43.6%	#10 of 12	Model card
Senior SWE-Bench	14.7%	#21 of 23	Official leaderboard
SWE-Marathon v1.1	22.5%	#16 of 17	Official leaderboard
ProgramBench	0%	#25 of 25	Official leaderboard
RSI-Exam	30.9%	#18 of 18	Official leaderboard
Android Bench 2.0	7.30%	#11 of 11	Official leaderboard
Google RE-Bench (GRB)	27%	#1 of 1	Model card

Agents and tools

Benchmark	Score	Rank	Source
Chess Puzzles	66%	#5 of 83	Epoch AI
Game Arena Chess	1,398	#3 of 39	Official leaderboard
Game Arena Coin Game	484	#3 of 35	Official leaderboard
Game Arena Reversi	816	#5 of 36	Official leaderboard
LLM Chess	1,107	#18 of 124	Official leaderboard
Game Arena Four in a Row	544	#9 of 38	Official leaderboard
Terminal-Bench 2.1	85.8%	#13 of 53	Model card
Mystery Game Puzzles	37%	#20 of 80	Epoch AI
Game Arena Word Association	324	#9 of 36	Official leaderboard
Kaggle Game Arena	368	#10 of 39	Official leaderboard
Game Arena Word Art	1,059	#9 of 35	Official leaderboard
Game Arena Poker	6.46	#8 of 31	Official leaderboard
Game Arena Checkers	1,073	#10 of 38	Official leaderboard
Game Arena Dark Hex	290	#11 of 38	Official leaderboard
Game Arena Bargaining	220	#11 of 36	Official leaderboard
Game Arena Clobber	390	#11 of 36	Official leaderboard
Game Arena Nine Men's Morris	705	#14 of 36	Official leaderboard
Game Arena Go	1,006	#16 of 36	Official leaderboard
Game Arena Dots and Boxes	908	#18 of 37	Official leaderboard
Game Arena Ultimate Tic-Tac-Toe	269	#19 of 36	Official leaderboard
Game Arena Lines of Action	471	#20 of 36	Official leaderboard
Agent Arena	-0.01	#32 of 53	Official leaderboard
ApprenticeBench	16%	#12 of 18	Official leaderboard
AutomationBench	30.4%	#28 of 41	Model card
OSWorld 2.0	47.9%	#15 of 19	Model card
RecreationBench	21.1%	#9 of 10	Official leaderboard
Terminal-Bench 4.0	11.2%	#23 of 23	Official leaderboard
Terminal-Bench 3.0	14.9%	#5 of 5	Model card

Professional work

Benchmark	Score	Rank	Source
LegalBench	87.3%	#6 of 138	Official leaderboard
Vals Finance Agent v2	59%	#7 of 80	Official leaderboard
MedCode	53.4%	#9 of 96	Official leaderboard
ProfBench	57.5%	#8 of 72	Official leaderboard
APEX-Agents	67.8%	#7 of 56	Epoch AI
Excel Modeling Benchmark	71.3%	#13 of 76	Official leaderboard
TaxEval v2	74.7%	#32 of 129	Official leaderboard
Harvey LAB (Legal Agent Benchmark)	8.75%	#25 of 80	Official leaderboard
MortgageTax	66.7%	#30 of 86	Official leaderboard
MedScribe	83.9%	#38 of 98	Official leaderboard
Legal Research Bench	34.6%	#46 of 88	Official leaderboard
Remote Labor Index	5.00%	#9 of 17	Official leaderboard
PolicyBench	82.7%	#27 of 50	Official leaderboard
Tax Agent Bench	22.8%	#45 of 79	Official leaderboard
GDPval-AA v2	1,525	#15 of 26	Model card
TaxCalcBench v2	26%	#17 of 26	Official leaderboard
$OneMillion-Bench	22.5%	#9 of 13	Official leaderboard
Agents' Last Exam	26.3%	#18 of 25	Model card

Vision, audio and robotics

Benchmark	Score	Rank	Source
Vision Arena	1,295	#5 of 136	Official leaderboard
1H-VideoQA	89.1%	#1 of 20	Official leaderboard
LVBench	85.4%	#3 of 25	Model card
CharXiv	88.7%	#12 of 67	Model card
ParseBench	70.7%	#9 of 42	Official leaderboard
ClockBench	53.3%	#9 of 37	Official leaderboard
Humanity's Sixth Sense	39.8%	#8 of 29	Official leaderboard
VoxelBench	1,845	#20 of 56	Official leaderboard
GDP.pdf	23.8%	#16 of 39	Epoch AI
Code2Video Benchmark	1,477	#12 of 19	Official leaderboard
Furniture Assembly Benchmark	26.7%	#29 of 35	Epoch AI
LADDER	42.8%	#4 of 4	Official leaderboard

Safety and security

Benchmark	Score	Rank	Source
BioSecBench-Refusal	54.8%	#3 of 22	Official leaderboard
TxBench-Antibody-Discovery	50.7%	#8 of 28	Official leaderboard
Human Pathogen Capabilities Test v2 (HPCT v2)	63.6%	#21 of 71	Official leaderboard
GDM Stealth	75%	#2 of 6	Model card
GDM Situational Awareness	54.5%	#3 of 8	Model card
TxBench-Oligo-Discovery	37.8%	#11 of 28	Official leaderboard
SpatialBench-Long	29.8%	#12 of 27	Official leaderboard
SRE-Bench	4.58%	#15 of 33	Official leaderboard
scBench-Long	18.8%	#13 of 27	Official leaderboard
TxBench-Preclinical-Pharmacology	55.3%	#14 of 28	Official leaderboard
CBRN Conversational Evals	1.80%	#1 of 2	Model card
CBRN Science Eval	3.50%	#1 of 2	Model card
PCT (Polarized Contrastive Pairs)	45.1%	#24 of 46	Official leaderboard
EpiBench	22%	#15 of 27	Official leaderboard
MetagenomicsBench	31.7%	#16 of 26	Official leaderboard
BioSecBench-Function	33.7%	#17 of 27	Official leaderboard
VariantBench	31.4%	#17 of 27	Official leaderboard
DistressBench	69%	#27 of 42	Official leaderboard
BioSecBench-Surveillance	41.5%	#18 of 27	Official leaderboard
OncologyBench	14.7%	#21 of 30	Official leaderboard
CyberBench v1.1 (Vals)	43.8%	#38 of 43	Official leaderboard
Chem / Bio Dynamic Jailbreak Eval	39%	#2 of 2	Model card
Cyber Adaptive Jailbreak Eval	24%	#2 of 2	Model card
Cyber Conversational Evals	11.4%	#2 of 2	Model card
Cyber Static Jailbreak Eval	50%	#2 of 2	Model card
Gray Swan Bio Eval	15%	#2 of 2	Model card
Gray Swan Cyber Eval	88%	#2 of 2	Model card
Harmful manipulation propensity evaluation	21.3%	#1 of 1	Model card

Other

Benchmark	Score	Rank	Source
CAIS Text Capabilities Index	49.3	#9 of 66	Official leaderboard
ACCoRD	77.0	#21 of 150	Official leaderboard
CAIS Vision Capabilities Index	68.7	#8 of 53	Official leaderboard
Conceptual Reasoning Index	64.6	#23 of 149	Official leaderboard
LMCA	50.4%	#25 of 139	Epoch AI
SAGE (Vals)	49.2%	#23 of 81	Official leaderboard
CAIS Risk Index	51.1	#32 of 65	Official leaderboard
Artificial Analysis Intelligence Index v4.1	56.0	#4 of 7	Model card

Google DeepMind's models over time

Google DeepMind's models in color, against every other model on the Epoch Capabilities Index, by release date.

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Gemini 3.7 Flash model card 13 Aug 2026

Artificial Analysis Intelligence Index 56
FrontierCode 1.1 Main (Score) 43.6
DeepSWE v1.1 65.3
Code Arena (Web development, Elo) 1588
Terminal-bench 2.1 85.8
Terminal-bench 3.0 14.9
AutomationBench (Private set) 30.4
GDPVal-AA v2 (Elo) 1525
Harvey LAB-AA 90.7
GDP.pdf 34
CharXiv Reasoning (With tools; No tools = 84.5%) 88.7
LVBench 85.4
GDM-MRCR v2 (8-needle), 128k (average) 97
OSWorld-2.0 47.9
Agent's Last Exam (Pass rate) 26.3
HLE-Verified 53.6
Best of BioMysteryBench, Human solvable / BioMysteryBench, Human difficult 87.1
LABBench2 82.1

Its system cards

Every result in the longer documents the lab published with it. 16 of them aren't in the launch post.

Frontier Safety Framework Report - Gemini 3.7 Flash 13 Aug 2026

Robustness