GPT-4.1 mini

GPT-4.1 mini places in the top three on Galileo Agent Leaderboard v2.

OpenAI Released 14 Apr 2025

Benchmarks with a score

Ranked first, out of five or more models

In the top three

OpenAI Apr 2025

Closed weights

134.9 #147 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
MMLU	87.5%	#32 of 127	Model card
Phare	70.5%	#20 of 62	Official leaderboard
FaithJudge	15.7%	#12 of 37	Official leaderboard
MMBench-CN v1.1	78.6%	#59 of 178	Official leaderboard
LMArena (Elo)	1,383	#150 of 333	Official leaderboard
Arena-Hard v2.0	46.9%	#12 of 23	Official leaderboard
Wer wird Millionär? LLM Benchmark	2489.0	#43 of 76	Official leaderboard
RewardBench 2	65.7%	#24 of 42	Official leaderboard
Multi-IF	67%	#18 of 28	Model card
IFEval	84.1%	#83 of 126	Model card
MMMLU	78.5%	#42 of 62	Model card
HELM Arabic	76.8	#19 of 28	Official leaderboard
EQ-Bench 3	1,097	#53 of 78	Official leaderboard
OpenAI MRCR	47.2%	#7 of 10	Model card
Internal API instruction following (OpenAI)	45.1%	#3 of 4	Model card
Judgemark v2.1	57.3	#33 of 42	Official leaderboard
Creative Writing v3	55.5	#95 of 120	Official leaderboard
Vectara Hallucination Leaderboard (HHEM)	2.20%	#122 of 148	Official leaderboard
Fiction.LiveBench	44.4%	#47 of 57	Epoch AI
COLLIE	54.6%	#10 of 12	Model card
GraphWalks	61.7%	#18 of 21	Model card
SimpleQA Verified	12.7%	#78 of 84	Epoch AI
MultiChallenge	35.8%	#35 of 36	Model card

Benchmark	Score	Rank	Source
MATH Level 5	87.3%	#20 of 94	Epoch AI
Misguided Attention	48.7%	#20 of 45	Official leaderboard
GPQA Diamond	65.8%	#116 of 219	Epoch AI
PolyMath	28.8%	#22 of 38	Official leaderboard
OTIS Mock AIME 2024-2025	44.7%	#128 of 202	Epoch AI
DTBench	48%	#114 of 178	Official leaderboard
FrontierMath	4.48%	#47 of 70	Epoch AI
CritPt	0%	#132 of 160	Epoch AI
AIME 2024	49.6%	#74 of 87	Model card
FrontierMath Tiers 1-3 v2	6.67%	#84 of 89	Epoch AI
ARC-AGI-2	0%	#92 of 95	Official leaderboard
ARC-AGI	3.50%	#90 of 92	Official leaderboard

Benchmark	Score	Rank	Source
BigCodeBench-Hard	31.8%	#14 of 96	Official leaderboard
StructEval	76.1%	#11 of 28	Official leaderboard
Aider Polyglot	32.4%	#37 of 54	Epoch AI
WeirdML	37.6%	#87 of 112	Official leaderboard
SWE-bench Verified	23.9%	#51 of 60	Official leaderboard

Benchmark	Score	Rank	Source
Galileo Agent Leaderboard v2	56%	#3 of 21	Official leaderboard
Berkeley Function Calling Leaderboard (BFCL)	65.2%	#13 of 67	Official leaderboard
Galileo Agent Leaderboard	0.91	#7 of 31	Official leaderboard
BFCL V4	50.5%	#21 of 65	Official leaderboard
SnakeBench	25	#78 of 183	Official leaderboard
ComplexFuncBench	49.3%	#2 of 3	Model card
LLM Chess	-167	#91 of 124	Official leaderboard
CompileBench	66.7%	#15 of 20	Official leaderboard
LisanBench	126.3	#110 of 133	Official leaderboard
Mystery Game Puzzles	7.00%	#73 of 80	Epoch AI
tau-bench	45.9%	#22 of 23	Model card
MCPMark	3.94%	#27 of 28	Official leaderboard
Chess Puzzles	1.00%	#82 of 83	Epoch AI
tau2-bench	53%	#10 of 10	Official leaderboard

Benchmark	Score	Rank	Source
LEXam	54.6%	#11 of 31	Official leaderboard
MortgageTax	65.5%	#38 of 86	Official leaderboard
TaxEval v2	71.9%	#67 of 129	Official leaderboard
CorpFin v2	57.9%	#81 of 119	Official leaderboard
Vals Finance Agent v1	20.8%	#32 of 47	Official leaderboard
LegalBench	78%	#96 of 138	Official leaderboard
ProfBench	42.8%	#54 of 72	Official leaderboard
EnterpriseClawBench	28.6%	#8 of 9	Official leaderboard
CadEval	16%	#14 of 15	Epoch AI
PRBench	30.4%	#43 of 44	Official leaderboard

Benchmark	Score	Rank	Source
MMBench	86.9%	#10 of 155	Official leaderboard
A-Bench	77.4%	#14 of 116	Official leaderboard
MMBench-EN v1.1	83.2%	#30 of 178	Official leaderboard
CCBench (MMBench Chinese Culture)	64.3%	#31 of 152	Official leaderboard
VHELM	65.6	#11 of 41	Official leaderboard
MMStar	60.9%	#55 of 173	Official leaderboard
Math-VR	33.3%	#13 of 26	Official leaderboard
MMMU	72.7%	#50 of 97	Model card
MathVista	73.1%	#35 of 64	Model card
Vision Arena	1,201	#78 of 136	Official leaderboard
VISTA	41.1%	#32 of 54	Official leaderboard
MADQA	53%	#13 of 16	Official leaderboard
CharXiv	56.8%	#60 of 67	Model card

Benchmark	Score	Rank	Source
SimpleSafetyTests	100%	#11 of 75	Official leaderboard
HELM Safety	94.9	#22 of 75	Official leaderboard
Anthropic Red Team	99.3%	#27 of 75	Official leaderboard
BaxBench	31.8%	#16 of 34	Official leaderboard
AIR-Bench 2024	60.4%	#52 of 82	Official leaderboard
Human Pathogen Capabilities Test v2 (HPCT v2)	31.5%	#63 of 71	Official leaderboard
FORTRESS	59.2%	#60 of 66	Official leaderboard

Benchmark	Score	Rank	Source
OpenVLM Leaderboard	68.9	#40 of 173	Official leaderboard
HELM Capabilities	72.6	#18 of 60	Official leaderboard
LMCA	21.1%	#103 of 139	Epoch AI
Conceptual Reasoning Index	31.0	#112 of 149	Official leaderboard
ACCoRD	43.6	#123 of 150	Official leaderboard

OpenAI'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.