Gemini 3 Pro

Gemini 3 Pro ranks first on 18 of the 169 benchmarks it has scores on.

Google DeepMind Released 18 Nov 2025 Family Gemini 3 The lab's model card

177

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Google DeepMind Nov 2025

Gemini 3 Pro

Closed weights Flagship

153.2 #49 of 271

Epoch Capabilities Index

Humanity's Last Exam 37.5% #8 /47
SWE-bench Verified 72.9% #21 /32
SWE-Bench Pro 43.3% #8 /24

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
MMLU-Pro	90.1%	#2 of 212	Official leaderboard
SuperGPQA	73.8%	#1 of 58	Official leaderboard
MMMLU	91.8%	#3 of 62	Model card
LMArena (Elo)	1,485	#18 of 333	Official leaderboard
Judgemark v2.1	86.6	#3 of 42	Official leaderboard
Extended NYT Connections	94.4%	#7 of 97	Official leaderboard
EQ-Bench 3	1,553	#9 of 78	Official leaderboard
SimpleQA Verified	72.1%	#7 of 56	Official leaderboard
Global PIQA	93.4%	#1 of 8	Model card
MultiNRC	59%	#6 of 38	Official leaderboard
Humanity's Last Exam	37.5%	#8 of 47	Official leaderboard
Global MMLU Lite	94.5%	#8 of 43	Official leaderboard
Phare	73.3%	#12 of 62	Official leaderboard
IndicGenBench	59.9	#3 of 13	Official leaderboard
SkateBench v2	76.2%	#5 of 21	Official leaderboard
WritingBench	78.5	#12 of 45	Official leaderboard
Creative Writing v3	74.3	#34 of 120	Official leaderboard
MultiChallenge	65.7%	#11 of 35	Official leaderboard
FACTS Benchmark Suite	70.5%	#1 of 3	Model card
Longform Creative Writing (EQ-Bench)	68.8	#44 of 119	Official leaderboard
BullshitBench V2	48%	#47 of 122	Official leaderboard
MRCR v2	77%	#12 of 27	Model card
BullshitBench	30.9%	#48 of 107	Official leaderboard
Document Arena	1,451	#26 of 37	Official leaderboard
CL-bench	15.8%	#18 of 24	Official leaderboard
Vectara Hallucination Leaderboard (2025 dataset)	13.6%	#89 of 104	Official leaderboard

Math and science

Benchmark	Score	Rank	Source
SMT 2025	93.4%	#1 of 40	Official leaderboard
HiPhO	78.3%	#1 of 35	Official leaderboard
AIME 2025	100%	#5 of 143	Model card
PHYBench	50.4%	#1 of 28	Official leaderboard
General365	62.8%	#1 of 23	Official leaderboard
HMMT 2025	97.5%	#3 of 53	Official leaderboard
GPQA Diamond	92.6%	#25 of 219	Epoch AI
BRUMO 2025	98.3%	#5 of 42	Official leaderboard
SimpleBench	76.4%	#13 of 100	Official leaderboard
FrontierMath	37.6%	#12 of 70	Epoch AI
HMMT Nov 2025	93.3%	#4 of 22	Official leaderboard
FrontierMath Tier 4	18.8%	#11 of 55	Epoch AI
CMIMC 2025	90%	#8 of 33	Official leaderboard
OTIS Mock AIME 2024-2025	91.4%	#56 of 202	Epoch AI
CORE-Bench	40%	#5 of 17	Official leaderboard
MathArena (Apex, IMO, USAMO)	23.4%	#14 of 47	Official leaderboard
xbench-ScienceQA	71.6%	#12 of 29	Official leaderboard
CritPt	6.90%	#67 of 160	Epoch AI
ARC-AGI-2	54%	#41 of 95	Official leaderboard
ProofBench	20%	#30 of 59	Official leaderboard
ARC-AGI	75%	#49 of 92	Official leaderboard
IMO-ProofBench	30%	#6 of 10	Official leaderboard
LABBench2	56.4%	#3 of 5	Official leaderboard
HMMT 2026	86.4%	#20 of 31	Official leaderboard
Leipzig Benchmark	14%	#13 of 19	Official leaderboard
Putnam 2025	91.0	#3 of 4	Official leaderboard
AIME 2026	91.7%	#25 of 31	Official leaderboard
ForecastBench	65.1	#74 of 86	Official leaderboard

Coding

Benchmark	Score	Rank	Source
MLE-bench	64.4%	#1 of 12	Official leaderboard
OJBench	70%	#1 of 8	Official leaderboard
WeirdML	69.9%	#21 of 112	Official leaderboard
METR Time Horizon	3.7 h	#8 of 39	Epoch AI
AlgoTune	1.83×	#4 of 18	Official leaderboard
IOI (Vals)	38.8%	#14 of 55	Official leaderboard
METR Time Horizon 1.1	3.7 h	#8 of 26	Official leaderboard
SWE-Bench Pro	43.3%	#8 of 24	Official leaderboard
OTelBench	15.9%	#5 of 14	Official leaderboard
ALE-Bench	1,177	#44 of 121	Epoch AI
SWE-bench Multilingual	68.7%	#5 of 13	Official leaderboard
SWE-fficiency	10.2%	#7 of 17	Official leaderboard
GSO-Bench	18.6%	#14 of 30	Official leaderboard
PostTrainBench	18.1%	#11 of 23	Official leaderboard
LiveCodeBench Pro	2,439	#2 of 4	Model card
Vibe Code Bench v1	14.3%	#9 of 17	Official leaderboard
WebDev Arena	1,439	#56 of 105	Epoch AI
Code Arena	1,440	#67 of 124	Official leaderboard
FrontierCS	33.1	#8 of 14	Official leaderboard
OpenHands Index	49%	#19 of 33	Official leaderboard
SWE-bench Verified	72.9%	#21 of 32	Epoch AI
CooperBench	21.8%	#4 of 6	Official leaderboard
Vibe Code Bench	14.3%	#91 of 115	Official leaderboard
Image-to-WebDev Arena	1,441	#45 of 55	Official leaderboard

Agents and tools

Benchmark	Score	Rank	Source
SnakeBench	38	#2 of 183	Official leaderboard
MCP-Universe	44.6%	#1 of 30	Official leaderboard
BFCL V4	72.5%	#3 of 65	Official leaderboard
BalatroBench	19.3	#1 of 16	Official leaderboard
Step Race	5	#4 of 59	Official leaderboard
MCPMark	53.9%	#2 of 28	Official leaderboard
ITBench	58.3%	#1 of 13	Official leaderboard
VITA-Bench	31.5%	#2 of 18	Official leaderboard
BALROG	58.1%	#4 of 35	Official leaderboard
Terminal-Bench 2.0	69.4%	#6 of 43	Official leaderboard
GAIA	78.1%	#10 of 57	Official leaderboard
Game Arena Chess Openings	1,253	#2 of 11	Official leaderboard
LLM Chess	1,034	#24 of 124	Official leaderboard
LisanBench	4677.0	#26 of 133	Official leaderboard
Pencil Puzzle Bench	16.7%	#14 of 53	Official leaderboard
Elimination Game	5	#16 of 56	Official leaderboard
tau2-bench	85.4%	#24 of 69	Model card
Agent Poker Bench	1,079	#6 of 17	Official leaderboard
MobileWorld	55.6%	#7 of 18	Official leaderboard
ScreenSpot-Pro	72.7%	#11 of 25	Model card
LMArena Search Arena	1,201	#17 of 35	Official leaderboard
Toolathlon	36.4%	#27 of 50	Official leaderboard
RWSearch	74.5%	#4 of 7	Official leaderboard
DeepResearch Bench	46.3%	#14 of 24	Epoch AI
MCP Atlas	70.3%	#21 of 34	Official leaderboard
tau3-bench	82.5%	#5 of 7	Official leaderboard
Terminal-Bench 2.1	73.9%	#10 of 13	Official leaderboard
τ³-bench Banking	18%	#20 of 25	Official leaderboard

Professional work

Benchmark	Score	Rank	Source
LegalBench	87%	#7 of 138	Official leaderboard
MortgageTax	69.1%	#7 of 86	Official leaderboard
FailureSensorIQ	69.1%	#2 of 24	Official leaderboard
MedCode	52.2%	#14 of 96	Official leaderboard
Vending-Bench	$4,388	#2 of 9	Official leaderboard
Vals Finance Agent v1	44.1%	#11 of 47	Official leaderboard
Vals Finance Agent	55.1%	#14 of 49	Official leaderboard
LEXam	55.4%	#10 of 31	Official leaderboard
ProfBench	51.7%	#25 of 72	Official leaderboard
CorpFin v2	63.7%	#43 of 119	Official leaderboard
Vending-Bench 2	$5,478	#29 of 66	Official leaderboard
GDPval	40.3%	#5 of 11	Epoch AI
TaxEval v2	72.6%	#60 of 129	Official leaderboard
TaxCalcBench	36.3%	#8 of 17	Official leaderboard
prinzbench	35.0	#14 of 26	Official leaderboard
Vending-Bench Arena	$3,384	#21 of 32	Official leaderboard
PRBench	40.6%	#32 of 44	Official leaderboard
CaseLaw v2	53%	#42 of 53	Official leaderboard
MedScribe	72%	#83 of 98	Official leaderboard
Remote Labor Index	1.25%	#16 of 17	Official leaderboard

Vision, audio and robotics

Benchmark	Score	Rank	Source
VideoMME v2 (with subtitles)	49.4%	#1 of 31	Official leaderboard
VPCT	91%	#1 of 28	Epoch AI
MADQA	85.2%	#1 of 16	Official leaderboard
MATH-Vision (MathVision)	86.6%	#8 of 105	Official leaderboard
Vision Arena	1,289	#12 of 136	Official leaderboard
Video-MMMU	87.6%	#3 of 30	Model card
VisualPuzzles	52.7%	#3 of 29	Official leaderboard
OCRBench v2	63.4%	#7 of 65	Official leaderboard
MDPBench	86.4	#1 of 9	Official leaderboard
VISTA	51.5%	#7 of 54	Official leaderboard
MMMU-Pro	81%	#10 of 72	Model card
ZeroBench	20%	#11 of 66	Official leaderboard
GeoBench	84%	#8 of 48	Official leaderboard
VideoDR (with search)	76%	#1 of 6	Official leaderboard
EnigmaEval	18.2%	#8 of 41	Epoch AI
RoboRewardBench	0.85	#4 of 19	Official leaderboard
OmniDocBench v1.6	92.9	#2 of 7	Official leaderboard
Audio MC	54.6%	#5 of 16	Official leaderboard
CharXiv	81.4%	#25 of 67	Model card
Math Kangaroo 2025 (MathArena)	84.2%	#9 of 22	Official leaderboard
ClockBench	31.1%	#17 of 37	Official leaderboard
BabyVision	49.7%	#13 of 27	Official leaderboard
OmniDocBench v1.5	0.12	#11 of 13	Model card
VoxelBench	1,289	#50 of 56	Official leaderboard
OCR Arena	1,367	#10 of 11	Official leaderboard

Safety and security

Benchmark	Score	Rank	Source
LAB-Bench CloningScenarios	94.2%	#1 of 11	Model card
BinaryAudit	43.9%	#4 of 20	Official leaderboard
WMDP Chemistry	84.8%	#1 of 5	Model card
Cyber key skills benchmark v1	91.7%	#1 of 4	Model card
SecureBio VMQA, single choice	61.2%	#1 of 4	Model card
WMDP Biology	88.2%	#2 of 7	Model card
LAB-Bench ProtocolQA	87.4%	#5 of 15	Model card
Agentic BAIM-LLM Evaluation (ABLE)	74.7%	#6 of 16	Official leaderboard
AIR-Bench 2024	73.2%	#32 of 82	Official leaderboard
LAB-Bench SeqQA	87.6%	#5 of 12	Model card
HELM Safety	92.5	#35 of 75	Official leaderboard
Spiral-Bench v1.2	38.7	#10 of 21	Official leaderboard
KORA	29.5%	#27 of 42	Official leaderboard
FORTRESS	41.7%	#46 of 66	Official leaderboard
SimpleSafetyTests	97.5%	#54 of 75	Official leaderboard
GDM Situational Awareness	27.3%	#6 of 8	Model card
Anthropic Red Team	97%	#59 of 75	Official leaderboard
GDM Stealth	25%	#5 of 6	Model card
Chain-of-thought comprehensibility	100%	#1 of 1	Model card
Chain-of-thought informativeness	99.8%	#1 of 1	Model card
Cyber key skills benchmark v2	0%	#1 of 1	Model card

Other

Benchmark	Score	Rank	Source
HELM Capabilities	79.9	#5 of 60	Official leaderboard
CAIS Text Capabilities Index	39.7	#19 of 66	Official leaderboard
CAIS Vision Capabilities Index	57.1	#20 of 53	Official leaderboard
SAGE (Vals)	47.6%	#31 of 81	Official leaderboard
CAIS Risk Index	64.0	#55 of 65	Official leaderboard

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 Pro model card 18 Nov 2025

Its system card

Every result in the longer documents the lab published with it. 17 of them aren't in the launch post.

Gemini 3 Pro

Gemini 3 Pro

Where it ranks

Knowledge and language

Math and science

Coding

Agents and tools

Professional work

Vision, audio and robotics

Safety and security

Other

Google DeepMind's models over time

Its launch post

Its system card

Alignment

Monitorability

Bio and chem risk

Cyber risk

AI R&D risk

Persuasion