Gemini 3.1 Pro

Gemini 3.1 Pro ranks first on 7 of the 225 benchmarks it has scores on.

Google DeepMind Released 19 Feb 2026 Family Gemini 3.1 The lab's model card

230

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Google DeepMind Feb 2026

Gemini 3.1 Pro

Closed weights Flagship

155.2 #37 of 271

Epoch Capabilities Index

Humanity's Last Exam 46.4% #3 /47
SWE-bench Verified 75.6% #12 /32
SWE-Bench Pro 46.1% #5 /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	91.2%	#1 of 212	Official leaderboard
SEA-HELM	77.4	#1 of 62	Official leaderboard
SimpleQA Verified	77.5%	#1 of 56	Official leaderboard
MMMLU	92.6%	#2 of 62	Model card
FACTS Search	85.6%	#1 of 31	Official leaderboard
Extended NYT Connections	97.4%	#4 of 97	Official leaderboard
SkateBench v2	96.9%	#1 of 21	Official leaderboard
LMArena (Elo)	1,487	#17 of 333	Official leaderboard
Humanity's Last Exam	46.4%	#3 of 47	Official leaderboard
MultiNRC	64.7%	#3 of 38	Official leaderboard
FACTS Parametric	79%	#4 of 45	Official leaderboard
Judgemark v4	78.7	#8 of 40	Official leaderboard
EQ-Bench 3	1,527	#17 of 78	Official leaderboard
MultiChallenge	71.4%	#8 of 35	Official leaderboard
FACTS Benchmark Suite	60.6%	#10 of 40	Official leaderboard
CL-bench	20.8%	#6 of 24	Official leaderboard
MRCR v2	84.9%	#7 of 27	Model card
Phare	70.6%	#18 of 62	Official leaderboard
CL-bench Life	16.9%	#5 of 16	Official leaderboard
FACTS Multimodal	41.3%	#14 of 39	Official leaderboard
FACTS Search V2	83.7%	#8 of 21	Official leaderboard
Creative Writing v3	71.2	#47 of 120	Official leaderboard
Longform Creative Writing (EQ-Bench)	68.2	#47 of 119	Official leaderboard
BullshitBench V2	37%	#61 of 122	Official leaderboard
Vectara Hallucination Leaderboard (2025 dataset)	10.4%	#62 of 104	Official leaderboard
Document Arena	1,459	#23 of 37	Official leaderboard
BullshitBench	21.8%	#67 of 107	Official leaderboard
EQ-Bench 4	1,132	#25 of 32	Official leaderboard
FACTS Grounding v2	56.6%	#13 of 15	Official leaderboard

Math and science

Benchmark	Score	Rank	Source
GPQA Diamond	94.4%	#8 of 219	Epoch AI
ARC-AGI	98%	#7 of 92	Official leaderboard
SimpleBench	79.6%	#10 of 100	Official leaderboard
MathArena (Apex, IMO, USAMO)	60.9%	#5 of 47	Official leaderboard
DTBench	92.5%	#19 of 178	Official leaderboard
AIME 2026	98.3%	#5 of 31	Official leaderboard
FrontierMath	36.9%	#13 of 70	Epoch AI
OTIS Mock AIME 2024-2025	95.6%	#39 of 202	Epoch AI
ARC-AGI-2	77.1%	#19 of 95	Official leaderboard
IMProofBench	45.7%	#2 of 10	Official leaderboard
FrontierMath Tier 4	16.7%	#12 of 55	Epoch AI
CritPt	17.7%	#37 of 160	Epoch AI
Echo General AI Prediction Leaderboard	1,006	#4 of 17	Official leaderboard
Project Euler (MathArena)	89%	#1 of 4	Official leaderboard
HMMT 2026	94.7%	#8 of 31	Official leaderboard
USAMO 2026	74.4%	#3 of 9	Official leaderboard
IMO-ProofBench	49%	#4 of 10	Official leaderboard
ProofBench	26%	#25 of 59	Official leaderboard
FrontierMath Tiers 1-3 v2	59.6%	#41 of 89	Epoch AI
ForecastBench	62.7	#43 of 86	Official leaderboard
FrontierMath Tier 4 v2	26.8%	#39 of 71	Epoch AI
Leipzig Benchmark	15%	#12 of 19	Official leaderboard
Prophet Arena	85.0	#12 of 18	Official leaderboard
ProofBench v1.1	26%	#37 of 51	Official leaderboard
MysteryMechanism	20.7%	#24 of 29	Official leaderboard
BixBench3	24.8	#17 of 20	Official leaderboard
ResearchClawBench	13.3	#21 of 23	Official leaderboard

Coding

Benchmark	Score	Rank	Source
SciCode	59%	#2 of 47	Model card
METR Time Horizon	6.4 h	#3 of 39	Epoch AI
LiveSQLBench	36.5%	#3 of 36	Official leaderboard
AlgoTune	2.02×	#2 of 18	Official leaderboard
METR Time Horizon 1.1	6.4 h	#3 of 26	Official leaderboard
WeirdML	72.1%	#19 of 112	Official leaderboard
SWE-Bench Pro	46.1%	#5 of 24	Official leaderboard
LiveCodeBench Pro	2,887	#1 of 4	Model card
OpenHands Index	60.6%	#9 of 33	Official leaderboard
FrontierCS	68.9	#4 of 14	Official leaderboard
AndroidBench	74.3%	#11 of 32	Official leaderboard
PostTrainBench	21.6%	#8 of 23	Official leaderboard
SWE-bench Verified	75.6%	#12 of 32	Epoch AI
ALE-Bench	1,161	#46 of 121	Epoch AI
FrontierCode	16.7%	#5 of 12	Official leaderboard
GSO-Bench	22.6%	#13 of 30	Official leaderboard
WebDev Arena	1,447	#54 of 105	Epoch AI
Code Arena	1,447	#65 of 124	Official leaderboard
IOI v2 (Vals)	51.8%	#25 of 45	Official leaderboard
Vibe Code Bench	32%	#72 of 115	Official leaderboard
ProgramBench	0%	#16 of 25	Official leaderboard
SWE-Marathon	4.00%	#8 of 12	Official leaderboard
Code Migration	17.3%	#54 of 78	Official leaderboard
EvoCode-Bench	13.7%	#9 of 13	Official leaderboard
SWE Atlas Refactoring	33.8%	#12 of 17	Official leaderboard
Image-to-WebDev Arena	1,481	#39 of 55	Official leaderboard
SWE Atlas Test Writing	29.8%	#18 of 22	Official leaderboard
GBAEval	0.85%	#18 of 21	Official leaderboard
SWE Atlas	13.5%	#19 of 22	Official leaderboard
ScarfBench	37.6%	#9 of 10	Official leaderboard
PostTrainBench 1.1	22%	#10 of 11	Official leaderboard
PostTrainBench 1.2	18.1%	#16 of 17	Official leaderboard
MirrorCode	8.89%	#27 of 28	Epoch AI
DeepSWE	11.7%	#28 of 28	Official leaderboard
Vibe Code Bench 1-100	6.69%	#26 of 26	Official leaderboard
Senior SWE-Bench	2.11%	#23 of 23	Official leaderboard

Agents and tools

Benchmark	Score	Rank	Source
SnakeBench	37	#5 of 183	Official leaderboard
Terminal-Bench 2.0	80.2%	#2 of 43	Official leaderboard
Game Arena Five in a Row	1,131	#1 of 20	Official leaderboard
PinchBench	80.7%	#3 of 48	Official leaderboard
LLM Chess	1,511	#9 of 124	Official leaderboard
BALROG	57%	#5 of 35	Official leaderboard
SkillsBench	60.8%	#3 of 21	Official leaderboard
LisanBench	6445.0	#20 of 133	Official leaderboard
Game Arena Chess	1,324	#6 of 39	Official leaderboard
Game Arena Four in a Row	589	#6 of 38	Official leaderboard
Pencil Puzzle Bench	33.3%	#9 of 53	Official leaderboard
Toolathlon	48.8%	#9 of 50	Official leaderboard
Chess Puzzles	51%	#16 of 83	Epoch AI
Game Arena Word Art	1,100	#7 of 35	Official leaderboard
OSWorld-Verified	78.3%	#7 of 33	Official leaderboard
BrowseComp	85.9%	#17 of 77	Model card
Game Arena Clobber	475	#8 of 36	Official leaderboard
Game Arena Nine Men's Morris	788	#8 of 36	Official leaderboard
Kaggle Game Arena	381	#9 of 39	Official leaderboard
Game Arena Go	1,149	#9 of 36	Official leaderboard
Game Arena Werewolf	-0	#2 of 8	Official leaderboard
MobileGym	58.8%	#1 of 4	Official leaderboard
Game Arena Coin Game	420	#9 of 35	Official leaderboard
PinchBench 2.0	81%	#15 of 57	Official leaderboard
Game Arena Dark Hex	296	#10 of 38	Official leaderboard
PACT	1,557	#7 of 26	Official leaderboard
Game Arena Word Association	308	#10 of 36	Official leaderboard
MobileWorld	58.1%	#5 of 18	Official leaderboard
Game Arena Dots and Boxes	976	#11 of 37	Official leaderboard
Mystery Game Puzzles	34%	#24 of 80	Epoch AI
DeepSearchQA	60.2%	#3 of 10	Official leaderboard
Game Arena Reversi	710	#11 of 36	Official leaderboard
Harbor-Index	13.4%	#3 of 9	Official leaderboard
Game Arena Checkers	972	#13 of 38	Official leaderboard
Claw-Eval	77.3%	#8 of 23	Official leaderboard
Game Arena Lines of Action	570	#13 of 36	Official leaderboard
LMArena Search Arena	1,207	#14 of 35	Official leaderboard
MCP Atlas	78.2%	#14 of 34	Official leaderboard
Game Arena Bargaining	196	#15 of 36	Official leaderboard
DeepResearch Bench	47.8%	#10 of 24	Epoch AI
Toolathlon-Verified	61.1%	#11 of 25	Official leaderboard
Game Arena Ultimate Tic-Tac-Toe	359	#16 of 36	Official leaderboard
UniClawBench	32.5%	#5 of 10	Official leaderboard
Claw-Eval Pass^3	57.8%	#12 of 23	Official leaderboard
GAIA	55.5%	#30 of 57	Official leaderboard
Claw-Eval-Live	53.3%	#7 of 12	Official leaderboard
τ³-bench Banking	26%	#16 of 25	Official leaderboard
Agent Arena	-0.04	#37 of 53	Official leaderboard
EBR-bench	14.3%	#20 of 28	Epoch AI
ARC-AGI-3	0.42%	#18 of 24	Official leaderboard
Game Arena Poker	-16.06	#24 of 31	Official leaderboard
Long-Horizon-Terminal-Bench (LHTB)	27.9%	#20 of 25	Official leaderboard
DeepTerminalBench	16%	#8 of 9	Official leaderboard
Terminal-Bench 2.1	65.8%	#12 of 13	Official leaderboard
Long-Horizon-Terminal-Bench 2.0	41.3%	#15 of 15	Official leaderboard

Professional work

Benchmark	Score	Rank	Source
MedCode	59.1%	#2 of 96	Official leaderboard
LegalBench	87.4%	#5 of 138	Official leaderboard
MortgageTax	69.4%	#6 of 86	Official leaderboard
Vals Finance Agent	59.7%	#7 of 49	Official leaderboard
CaseLaw v2	64.8%	#12 of 53	Official leaderboard
TaxCalcBench	49%	#4 of 17	Official leaderboard
ProfBench	55.2%	#17 of 72	Official leaderboard
CorpFin v2	64.5%	#37 of 119	Official leaderboard
RadLE 2.0	660.0	#4 of 12	Official leaderboard
prinzbench	50.0	#9 of 26	Official leaderboard
SpreadsheetBench 2	23.7%	#3 of 8	Official leaderboard
TaxEval v2	72.9%	#56 of 129	Official leaderboard
FORTE	70.3%	#11 of 21	Official leaderboard
CADGenBench	31.1%	#6 of 11	Official leaderboard
PRBench	44%	#25 of 44	Official leaderboard
PolicyBench	81.2%	#30 of 50	Official leaderboard
Physical-Engineering's Last Exam	0.15	#11 of 18	Official leaderboard
Vending-Bench 2	$3,774	#43 of 66	Official leaderboard
EEBench	46.3%	#18 of 26	Official leaderboard
Excel Modeling Benchmark	52.6%	#54 of 76	Official leaderboard
MedScribe	76.1%	#70 of 98	Official leaderboard
Legal Research Bench	20.7%	#64 of 88	Official leaderboard
Vals Finance Agent v2	43%	#59 of 80	Official leaderboard
Tax Agent Bench	9.29%	#65 of 79	Official leaderboard
Harvey LAB (Legal Agent Benchmark)	0%	#67 of 80	Official leaderboard
APEX-Agents	35.1%	#47 of 56	Epoch AI
E-Commerce Bench	1.30	#16 of 19	Official leaderboard
Public Benefits Bench	53.8%	#43 of 50	Official leaderboard
PhysicianBench	6.00%	#12 of 13	Official leaderboard
TaxCalcBench v2	0%	#25 of 26	Official leaderboard
FrontierFinance	30.7%	#16 of 16	Official leaderboard
GDPval-AA	1,317	#16 of 16	Model card
JobBench	15.9%	#16 of 16	Official leaderboard

Vision, audio and robotics

Benchmark	Score	Rank	Source
MATH-Vision (MathVision)	95.7%	#2 of 105	Official leaderboard
MMMU-Pro	80.5%	#11 of 72	Model card
Vision Arena	1,280	#23 of 136	Official leaderboard
GeoBench	84%	#9 of 48	Official leaderboard
ZeroBench	19%	#13 of 66	Official leaderboard
Math Kangaroo 2025 (MathArena)	89.4%	#5 of 22	Official leaderboard
ParseBench	69.1%	#16 of 42	Official leaderboard
1H-VideoQA	78.2%	#8 of 20	Official leaderboard
Drone-Bench	68.9%	#8 of 19	Official leaderboard
ClockBench	32.2%	#16 of 37	Official leaderboard
BabyVision	51.6%	#12 of 27	Official leaderboard
ArtifactArena	1,089	#11 of 21	Official leaderboard
VoxelBench	1,642	#30 of 56	Official leaderboard
EnigmaEval	36.8%	#3 of 5	Official leaderboard
Blueprint-Bench 2	26.5%	#24 of 35	Official leaderboard
GDP.pdf	17%	#27 of 39	Epoch AI
Furniture Assembly Benchmark	26.7%	#28 of 35	Epoch AI
Code2Video Benchmark	1,454	#16 of 19	Official leaderboard
Dual-Arm Sim	8.50	#9 of 10	Official leaderboard
Claw-Eval-MM	45.7%	#10 of 11	Official leaderboard
LongExtractionBench	48.6%	#3 of 3	Official leaderboard

Safety and security

Benchmark	Score	Rank	Source
Agentic BAIM-LLM Evaluation (ABLE)	84.6%	#1 of 16	Official leaderboard
BinaryAudit	49.1%	#2 of 20	Official leaderboard
BrowseSafe++	89.9%	#2 of 15	Official leaderboard
Human Pathogen Capabilities Test v2 (HPCT v2)	65.4%	#11 of 71	Official leaderboard
SMDD-Bench	39%	#2 of 7	Official leaderboard
PCT (Polarized Contrastive Pairs)	42.2%	#20 of 46	Official leaderboard
ExploitBench	26%	#5 of 9	Official leaderboard
DrugDiscoveryBench	41.9%	#11 of 19	Official leaderboard
FORTRESS	29.8%	#39 of 66	Official leaderboard
KORA	31.6%	#25 of 42	Official leaderboard
Dictatorship Eval	53.4%	#12 of 20	Official leaderboard
CyberGym	38.8%	#21 of 33	Official leaderboard
DistressBench	68.8%	#28 of 42	Official leaderboard
CyberGym-E2E	43.8%	#4 of 5	Official leaderboard
ExploitGym	1.38%	#15 of 18	Official leaderboard
SRE-Bench	0%	#30 of 33	Official leaderboard
CyberBench (Vals)	36.4%	#26 of 26	Official leaderboard
BiomniBench	44.3	#8 of 8	Official leaderboard
Harmful manipulation efficacy study	3.60	#1 of 1	Model card

Other

Benchmark	Score	Rank	Source
LMCA	53.8%	#19 of 139	Epoch AI
Conceptual Reasoning Index	63.8	#24 of 149	Official leaderboard
CAIS Text Capabilities Index	45.8	#14 of 66	Official leaderboard
CAIS Vision Capabilities Index	62.1	#14 of 53	Official leaderboard
SAGE (Vals)	48.7%	#26 of 81	Official leaderboard
ACCoRD	65.0	#72 of 150	Official leaderboard
Vals Multimodal Index	56.1%	#20 of 33	Official leaderboard
CAIS Risk Index	56.5	#42 of 65	Official leaderboard
SAGE v1.1 (Vals)	83.2%	#22 of 28	Official leaderboard
Vals Science Index	27.4%	#21 of 23	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 3.1 Pro model card 19 Feb 2026

Its system card

Every result in the longer documents the lab published with it. 10 of them aren't in the launch post.

Gemini 3.1 Pro

Gemini 3.1 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

Capabilities

Safety

Alignment

Bio and chem risk

AI R&D risk

Persuasion