Grok 3

Grok 3 places in the top three on 3 benchmarks.

xAI Released 9 Apr 2025 Family Grok 3 The lab's model card

Benchmarks with a score

Ranked first, out of five or more models

In the top three

xAI Apr 2025

Closed weights Flagship

138.3 #134 of 271

Epoch Capabilities Index

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.

Benchmark	Score	Rank	Source
Vectara Hallucination Leaderboard (2025 dataset)	5.80%	#23 of 104	Official leaderboard
ECLeKTic	29%	#8 of 35	Official leaderboard
LLM Confabulation Leaderboard	14.2%	#17 of 58	Official leaderboard
FaithJudge	15.3%	#11 of 37	Official leaderboard
SimpleQA	43.6%	#18 of 59	Model card
LOFT	83.3%	#2 of 6	Model card
LMArena (Elo)	1,411	#116 of 333	Official leaderboard
SimpleQA Verified	39.3%	#23 of 56	Official leaderboard
MMLU-Pro	79.9%	#77 of 151	Model card
WritingBench	71.7	#24 of 45	Official leaderboard
EQ-Bench 3	1,165	#46 of 78	Official leaderboard
Lech Mazur Creative Writing	7.64	#26 of 44	Epoch AI
Fiction.LiveBench	58.3%	#35 of 57	Epoch AI
FACTS Grounding	75.7%	#21 of 34	Official leaderboard
Creative Writing v3	62.2	#78 of 120	Official leaderboard
Vectara Hallucination Leaderboard (HHEM)	2.10%	#124 of 148	Official leaderboard
Phare	53.5%	#62 of 62	Official leaderboard

Benchmark	Score	Rank	Source
AIME 2024	93.3%	#5 of 87	Model card
MATH Level 5	88.8%	#19 of 94	Epoch AI
AIME 2025	93.3%	#31 of 143	Model card
Misguided Attention	55.1%	#14 of 45	Official leaderboard
PolyMath	35.2%	#16 of 38	Official leaderboard
GPQA Diamond	75.8%	#99 of 219	Epoch AI
USAMO 2025	4.76%	#5 of 10	Official leaderboard
OTIS Mock AIME 2024-2025	55.6%	#122 of 202	Epoch AI
PHYBench	21.2%	#17 of 28	Official leaderboard
SimpleBench	36.1%	#72 of 100	Official leaderboard
FrontierMath	3.79%	#52 of 70	Epoch AI
FrontierMath Tier 4	0%	#48 of 55	Epoch AI
ARC-AGI	5.50%	#85 of 92	Official leaderboard
ARC-AGI-2	0%	#91 of 95	Official leaderboard

Benchmark	Score	Rank	Source
BigCodeBench-Hard	33.1%	#7 of 96	Official leaderboard
LiveCodeBench	79.4%	#13 of 73	Model card
Aider Polyglot	53.3%	#24 of 54	Epoch AI
WeirdML	37.2%	#89 of 112	Official leaderboard

Benchmark	Score	Rank	Source
Elimination Game	5	#15 of 56	Official leaderboard
Berkeley Function Calling Leaderboard (BFCL)	63.3%	#21 of 67	Official leaderboard
LisanBench	739.0	#62 of 133	Official leaderboard
BALROG	29.5%	#17 of 35	Official leaderboard
LLM Chess	-137	#85 of 124	Official leaderboard
Step Race	1	#43 of 59	Official leaderboard

Benchmark	Score	Rank	Source
TaxEval v2	75.9%	#10 of 129	Official leaderboard
xbench-Marketing	46.5	#3 of 7	Official leaderboard
LegalBench	82.6%	#67 of 138	Official leaderboard
CorpFin v2	59.7%	#72 of 119	Official leaderboard
Vals Finance Agent v1	24.1%	#30 of 47	Official leaderboard
xbench-Recruitment	47.1	#7 of 8	Official leaderboard

Benchmark	Score		Rank	Source
MMMU	78%		#12 of 136	Official leaderboard
EgoSchema	74.5%		#2 of 12	Model card

Benchmark	Score	Rank	Source
BaxBench	33.9%	#13 of 34	Official leaderboard
Human Pathogen Capabilities Test v2 (HPCT v2)	49.3%	#45 of 71	Official leaderboard
AIR-Bench 2024	51.3%	#65 of 82	Official leaderboard
SimpleSafetyTests	96.8%	#60 of 75	Official leaderboard
HELM Safety	85.5	#63 of 75	Official leaderboard
KORA	18%	#36 of 42	Official leaderboard
Anthropic Red Team	95.5%	#69 of 75	Official leaderboard

Benchmark	Score		Rank	Source
HELM Capabilities	72.7		#15 of 60	Official leaderboard

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

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