Gemini 2.5 Pro Jun 2025

Gemini 2.5 Pro ranks first on 9 of the 187 benchmarks it has scores on.

Google DeepMind Released 5 Jun 2025 Family Gemini 2.5 The lab's model card

206

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Google DeepMind Jun 2025

Gemini 2.5 Pro

Jun 2025 snapshot Closed weights Flagship

145.3 #92 of 271

Epoch Capabilities Index

Humanity's Last Exam 21.6% #19 /47
SWE-bench Verified 57.6% #30 /32
Terminal-Bench 2.0 32.6% #31 /43

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
BuzzBench	71.1	#1 of 23	Official leaderboard
RewardBench 2	79.5%	#2 of 42	Official leaderboard
FaithJudge	6.65%	#2 of 37	Official leaderboard
IndicGenBench	77.1	#1 of 13	Official leaderboard
SuperGPQA	64.5%	#5 of 58	Official leaderboard
Fiction.LiveBench	91.7%	#5 of 57	Epoch AI
MMLU-Pro	86%	#26 of 212	Official leaderboard
Wer wird Millionär? LLM Benchmark	266667.0	#10 of 76	Official leaderboard
FACTS Grounding	87.8%	#2 of 15	Model card
Lech Mazur Creative Writing	8.38	#6 of 44	Epoch AI
LLM Confabulation Leaderboard	12.4%	#8 of 58	Official leaderboard
LOFT	87%	#1 of 6	Model card
FACTS Multimodal	46.9%	#7 of 39	Official leaderboard
SimpleQA	54%	#11 of 59	Model card
WritingBench	79.3	#9 of 45	Official leaderboard
ECLeKTic	46.8%	#2 of 10	Model card
LMArena (Elo)	1,445	#68 of 333	Official leaderboard
EQ-Bench 3	1,523	#19 of 78	Official leaderboard
FACTS Parametric	63.2%	#13 of 45	Official leaderboard
Vectara Hallucination Leaderboard (2025 dataset)	7.00%	#32 of 104	Official leaderboard
Global MMLU Lite	93.2%	#14 of 43	Official leaderboard
WideSearch	4.30%	#2 of 6	Official leaderboard
Creative Writing v3	72.3	#41 of 120	Official leaderboard
MultiNRC	45.1%	#14 of 38	Official leaderboard
Humanity's Last Exam	21.6%	#19 of 47	Official leaderboard
FACTS Benchmark Suite	46.9%	#19 of 40	Official leaderboard
Judgemark v2.1	72.1	#23 of 42	Official leaderboard
Longform Creative Writing (EQ-Bench)	58.8	#66 of 119	Official leaderboard
BullshitBench	23.6%	#63 of 107	Official leaderboard
MRCR v2	58%	#19 of 27	Model card
BullshitBench V2	20%	#86 of 122	Official leaderboard
FACTS Search	63.9%	#23 of 31	Official leaderboard
MultiChallenge	53.6%	#26 of 35	Official leaderboard
Vectara Hallucination Leaderboard (HHEM)	2.60%	#115 of 148	Official leaderboard
Phare	60.5%	#50 of 62	Official leaderboard
Document Arena	1,431	#33 of 37	Official leaderboard

Math and science

Benchmark	Score	Rank	Source
PHYBench	45.8%	#2 of 28	Official leaderboard
HiPhO	70.4%	#3 of 35	Official leaderboard
Misguided Attention	57.4%	#9 of 45	Official leaderboard
miniCTX-v2	36.2%	#1 of 4	Official leaderboard
AMO-Bench	38.7%	#6 of 21	Official leaderboard
SimpleBench	62.4%	#29 of 100	Official leaderboard
GPQA Diamond	85.3%	#71 of 219	Epoch AI
IMO 2025	31.6%	#2 of 6	Official leaderboard
OTIS Mock AIME 2024-2025	84.7%	#78 of 202	Epoch AI
ATLAS (OpenCompass)	35.3%	#2 of 5	Official leaderboard
AIME 2025	88%	#60 of 143	Model card
DTBench	70.7%	#79 of 178	Official leaderboard
FrontierMath	14.1%	#35 of 70	Epoch AI
HiddenMath-Hard	80.5%	#1 of 2	Model card
CritPt	2.00%	#84 of 160	Epoch AI
FrontierMath Tier 4	4.17%	#29 of 55	Epoch AI
CORE-Bench	22.2%	#11 of 17	Official leaderboard
ARC-AGI-2	4.86%	#65 of 95	Official leaderboard
ForecastBench	64.1	#63 of 86	Official leaderboard
ARC-AGI	41%	#68 of 92	Official leaderboard
General365	48.7%	#17 of 23	Official leaderboard
FrontierMath Tiers 1-3 v2	24.6%	#73 of 89	Epoch AI
MathArena (Apex, IMO, USAMO)	0.52%	#41 of 47	Official leaderboard
IMProofBench	6.08%	#9 of 10	Official leaderboard
HMMT Nov 2025	80%	#20 of 22	Official leaderboard
FrontierMath Tier 4 v2	0%	#70 of 71	Epoch AI
IMC 2025	94.5%	#1 of 1	Official leaderboard

Coding

Benchmark	Score	Rank	Source
Aider Polyglot	83.1%	#3 of 54	Epoch AI
LiveCodeBench v6	73.6%	#3 of 21	Official leaderboard
ArtifactsBench	57.7%	#3 of 20	Official leaderboard
LiveCodeBench v5	74%	#4 of 21	Official leaderboard
AutoCodeBench	48.7%	#7 of 34	Official leaderboard
MLE-bench	59.6%	#3 of 12	Official leaderboard
LiveCodeBench	74.2%	#20 of 73	Model card
LiveSQLBench	28.7%	#13 of 36	Official leaderboard
WeirdML	54%	#42 of 112	Official leaderboard
METR Time Horizon	40 min	#13 of 31	Official leaderboard
IOI (Vals)	17.1%	#26 of 55	Official leaderboard
ALE-Bench	786	#73 of 121	Epoch AI
AlgoTune	1.51×	#11 of 18	Official leaderboard
CodeClash	1,124	#6 of 8	Official leaderboard
GSO-Bench	3.92%	#25 of 30	Official leaderboard
Vibe Code Bench v1	0.40%	#15 of 17	Official leaderboard
SWE-bench Verified	57.6%	#30 of 32	Epoch AI
SWE-fficiency	3.13%	#16 of 17	Official leaderboard
Code Arena	1,226	#117 of 124	Official leaderboard
WebDev Arena	1,226	#100 of 105	Epoch AI
Vibe Code Bench	0.40%	#111 of 115	Official leaderboard
Image-to-WebDev Arena	1,285	#55 of 55	Official leaderboard
FrontierCS	20.3	#14 of 14	Official leaderboard

Agents and tools

Benchmark	Score	Rank	Source
Step Race	4	#7 of 59	Official leaderboard
SnakeBench	29	#40 of 183	Official leaderboard
Meta Agents Research Environments (ARE) / Gaia2	25.8%	#3 of 13	Official leaderboard
Terminal-Bench	32.6%	#7 of 18	Epoch AI
Elimination Game	4	#22 of 56	Official leaderboard
Galileo Agent Leaderboard v2	43%	#10 of 21	Official leaderboard
LisanBench	556.0	#66 of 133	Official leaderboard
OSWorld-Verified	45.8%	#19 of 33	Official leaderboard
Pencil Puzzle Bench	0%	#34 of 53	Official leaderboard
MCP-Universe	22.1%	#20 of 30	Official leaderboard
ITBench	42.3%	#9 of 13	Official leaderboard
VitaBench 2.0	33.1%	#14 of 20	Official leaderboard
DeepSearchQA	24.6%	#7 of 10	Official leaderboard
Agent Poker Bench	1,033	#12 of 17	Official leaderboard
LLM Chess	-147	#89 of 124	Official leaderboard
Terminal-Bench 2.0	32.6%	#31 of 43	Official leaderboard
PinchBench	63.1%	#36 of 48	Official leaderboard
MCPMark	15.8%	#21 of 28	Official leaderboard
DeepResearch Bench	42.8%	#18 of 24	Epoch AI
τ³-bench Banking	13.7%	#22 of 25	Official leaderboard
CompileBench	60%	#18 of 20	Official leaderboard
LMArena Search Arena	1,144	#34 of 35	Official leaderboard
Toolathlon	10.5%	#49 of 50	Official leaderboard
LiveResearchBench	61.6	#7 of 7	Official leaderboard

Professional work

Benchmark	Score	Rank	Source
LEXam	67.4%	#2 of 31	Official leaderboard
MortgageTax	68.9%	#8 of 86	Official leaderboard
MedCode	50.6%	#17 of 96	Official leaderboard
LegalBench	84.3%	#35 of 138	Official leaderboard
CaseLaw v2	63.9%	#15 of 53	Official leaderboard
FailureSensorIQ	67%	#7 of 24	Official leaderboard
ProfBench	52.1%	#23 of 72	Official leaderboard
TaxEval v2	72.9%	#55 of 129	Official leaderboard
Vals Finance Agent v1	29.4%	#25 of 47	Official leaderboard
CorpFin v2	60.8%	#64 of 119	Official leaderboard
MedHELM	51.9	#8 of 13	Official leaderboard
PRBench	41.4%	#28 of 44	Official leaderboard
MedScribe	73.5%	#77 of 98	Official leaderboard
Vals Finance Agent	41.6%	#39 of 49	Official leaderboard
Vending-Bench 2	$574	#54 of 66	Official leaderboard
GDPval	23.3%	#9 of 11	Epoch AI
Vending-Bench Arena	$773	#27 of 32	Official leaderboard
Remote Labor Index	0.83%	#17 of 17	Official leaderboard

Vision, audio and robotics

Benchmark	Score	Rank	Source
VHELM	87.1	#1 of 41	Official leaderboard
VISTA	54.6%	#2 of 54	Official leaderboard
ERQA	55.6%	#1 of 17	Official leaderboard
AHELM	80.3	#1 of 10	Official leaderboard
MMMU	82%	#11 of 97	Model card
Math-VR	64.7%	#3 of 26	Official leaderboard
ActivityNet-QA	66.7%	#1 of 8	Model card
SpatialViz-Bench	44.7%	#1 of 8	Epoch AI
OCRBench v2	59.3%	#10 of 65	Official leaderboard
Perception Test MCVQA	78.4%	#1 of 6	Model card
VisualPuzzles	49.5%	#5 of 29	Official leaderboard
LVBench	78.7%	#5 of 25	Model card
GeoBench	81%	#12 of 48	Official leaderboard
MADQA	73.1%	#4 of 16	Official leaderboard
Blueprint-Bench	0.42	#2 of 8	Official leaderboard
VATEX	71.3	#1 of 4	Model card
VATEX ZH	59.7	#1 of 4	Model card
YouCook2	188.3	#1 of 4	Model card
VPCT	46.4%	#9 of 28	Epoch AI
Video-MME	86.9%	#14 of 42	Model card
MMAU v05.15.25	71.6%	#3 of 9	Official leaderboard
Vibe-Eval	67.2%	#3 of 9	Model card
BetterChartQA	72.4%	#1 of 3	Model card
Vision Arena	1,248	#47 of 136	Official leaderboard
1H-VideoQA	79%	#7 of 20	Official leaderboard
OCR Arena	1,701	#4 of 11	Official leaderboard
RoboRewardBench	0.90	#7 of 19	Official leaderboard
Audio MC	46.9%	#7 of 16	Official leaderboard
Video-MMMU	83.6%	#15 of 30	Model card
MINERVA	67.6%	#3 of 6	Model card
Neptune	87.3%	#1 of 2	Model card
ClockBench	18.9%	#20 of 37	Official leaderboard
CoVoST2	38.5	#6 of 11	Model card
EnigmaEval	5.57%	#23 of 41	Epoch AI
OmniDocBench v1.5	88.0	#6 of 10	Official leaderboard
ZeroBench	5.00%	#42 of 66	Official leaderboard
Math Kangaroo 2025 (MathArena)	77.2%	#14 of 22	Official leaderboard
EgoTempo	44.3%	#4 of 5	Model card
QVHighlights	75%	#4 of 5	Model card
Drone-Bench	33.9%	#16 of 19	Official leaderboard
VoxelBench	1,167	#56 of 56	Official leaderboard

Safety and security

Benchmark	Score	Rank	Source
PCT (Polarized Contrastive Pairs)	37.3%	#9 of 46	Official leaderboard
In-house CTF suite (Phuong et al. 2024)	84.6%	#1 of 4	Model card
Anthropic Red Team	99.5%	#20 of 75	Official leaderboard
AIR-Bench 2024	73.6%	#31 of 82	Official leaderboard
WMDP Chemistry	80%	#2 of 5	Model card
BaxBench	33.3%	#14 of 34	Official leaderboard
WMDP Biology	86%	#3 of 7	Model card
LAB-Bench CloningScenarios	53%	#5 of 11	Model card
HELM Safety	91.4	#37 of 75	Official leaderboard
GDM Stealth	40%	#3 of 6	Model card
Cyber key skills benchmark v1	50%	#2 of 4	Model card
SecureBio VMQA, single choice	56%	#2 of 4	Model card
Dangerous Content policy violations (from ART)	24.3%	#1 of 2	Model card
Helpfulness violations (from ART)	6.10%	#1 of 2	Model card
Indirect prompt injection, TAP attack	30.8%	#1 of 2	Model card
BinaryAudit	21.1%	#11 of 20	Official leaderboard
KORA	29.1%	#28 of 42	Official leaderboard
LAB-Bench ProtocolQA	74%	#10 of 15	Model card
LAB-Bench SeqQA	71%	#8 of 12	Model card
Hack the Box challenge set (Google DeepMind)	7.70%	#3 of 4	Model card
InterCode-CTF	97.4%	#3 of 4	Model card
Spiral-Bench v1.2	28.3	#16 of 21	Official leaderboard
SimpleSafetyTests	97%	#58 of 75	Official leaderboard
Spiral-Bench v1.0	43.5	#11 of 13	Official leaderboard
FORTRESS	61.7%	#64 of 66	Official leaderboard
GDM Situational Awareness	18.2%	#8 of 8	Model card
Divergence attack (extractable memorization)	59%	#2 of 2	Model card
Indirect prompt injection, Actor Critic attack	61.4%	#2 of 2	Model card
Indirect prompt injection, Beam Search attack	63.8%	#2 of 2	Model card

Other

Benchmark	Score	Rank	Source
HELM Capabilities	74.5	#14 of 60	Official leaderboard
LMCA	34.8%	#71 of 139	Epoch AI
Conceptual Reasoning Index	47.5	#77 of 149	Official leaderboard
ACCoRD	62.7	#80 of 150	Official leaderboard
SAGE (Vals)	41.9%	#55 of 81	Official leaderboard
CAIS Vision Capabilities Index	45.7	#37 of 53	Official leaderboard
CAIS Text Capabilities Index	22.4	#47 of 66	Official leaderboard
CAIS Risk Index	64.3	#56 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 2.5 Pro model card (updated 2025-06-27) 17 Jun 2025

Its system card

Every result in the longer documents the lab published with it. 46 of them aren't in the launch post.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities 7 Jul 2025

Gemini 2.5 Pro Jun 2025

Gemini 2.5 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

Robustness

Alignment

Bio and chem risk

Cyber risk

AI R&D risk