Benchmark Explorer

Explore how models perform on various benchmarks

Benchmarks

🔍

Capability Benchmarks

AA-LCR

AIME

Blended Price (USD/1M Tokens)

CaseLaw

Chatbot Arena (Win Rate)

Chatbot Arena Coding

Chatbot Arena Vision

ContractLaw

CorpFin

FinanceAgent

GPQA

HumanEval

Humanity's Last Exam

IFBench

IOI

LegalBench

LiveBench (Agentic Coding)

LiveBench (Average)

LiveBench (Coding)

LiveBench (Data Analysis)

LiveBench (Instruction Following)

LiveBench (Language)

LiveBench (Math)

LiveBench (Reasoning)

LiveCodeBench

MGSM

MMLU Pro

MMMU

Math500

Median Tokens/s

MortgageTax

SWE-bench

SciCode

SimpleBench

TaxEval

Terminal-Bench Hard

τ²-Bench Telecom

Safety Benchmarks

AIR-Bench-AcademicDishonesty

AIR-Bench-AdultContent

AIR-Bench-AdviceInHeavilyRegulatedIndustries

AIR-Bench-AutomatedDecisionmaking

AIR-Bench-AutonomousUnsafeOperations

AIR-Bench-Availability

AIR-Bench-CelebratingSuffering

AIR-Bench-ChildSexualAbuse

AIR-Bench-Confidentiality

AIR-Bench-DepictingViolence

AIR-Bench-DeterringDemocraticParticipation

AIR-Bench-DiscriminationprotectedCharacteristics

AIR-Bench-DisempoweringWorkers

AIR-Bench-DisruptingSocialOrder

AIR-Bench-EndangermentHarmOrLossOfLife

AIR-Bench-Erotic

AIR-Bench-Fraud

AIR-Bench-FraudulentSchemes

AIR-Bench-Harassment

AIR-Bench-HateSpeechIncitingViolence

AIR-Bench-HighRiskFinancialActivities

AIR-Bench-IllegalRegulatedSubstances

AIR-Bench-IllegalServicesExploitation

AIR-Bench-InfluencingPolitics

AIR-Bench-Integrity

AIR-Bench-MilitaryAndWarfare

AIR-Bench-Misdisinformation

AIR-Bench-Misrepresentation

AIR-Bench-Monetized

AIR-Bench-NonconsensualNudity

AIR-Bench-OffensiveLanguage

AIR-Bench-OtherIllegalunlawfulActivity

AIR-Bench-PerpetuatingHarmfulStereotypes

AIR-Bench-PoliticalPersuasion

AIR-Bench-SowingDivision

AIR-Bench-SpecificTypesOfRights

AIR-Bench-SuicidalAndNonsuicidalSelfinjury

AIR-Bench-SupportingMaliciousOperations

AIR-Bench-TypesOfDefamation

AIR-Bench-Unauthorizedprivacyviolationssensitivedata

AIR-Bench-UnfairMarketPractices

AIR-Bench-ViolentActs

AIR-Bench-WeaponUsageDevelopment

Capability & Safety Benchmarks

MedQA

MMLU Pro

An exact match accuracy metric on an enhanced version of the MMLU dataset, featuring more challenging, reasoning-focused questions with increased answer choices.

Source:

Model Performance

#1

Claude-4.1-Opus

86.4%

#2

Claude-4.1-Opus-Thinking

86.2%

#3

Claude-4.0-Opus

84.6%

#4

OpenAI-O3-high

84.0%

#5

OpenAI-O3-medium

84.0%

#6

Grok-4-Thinking

83.7%

#7

Grok-4

83.7%

#8

Gemini-2.5-Pro-0325

82.3%

#9

Gemini-2.5-Pro-Thinking

82.3%

#10

Claude-4.0-Sonnet-Thinking

82.0%

#11

OpenAI-O1-1217

81.7%

#12

Claude-3.7-Sonnet-Thinking

80.8%

#13

GPT-5-mini

80.6%

#14

Grok-3-Mini-Beta

79.3%

#15

Claude-3.7-Sonnet

78.6%

#16

OpenAI-O4-mini-high

78.4%

#17

OpenAI-O4-mini-medium

78.4%

#18

GPT-4.1

78.3%

#19

Qwen-3-Thinking

78.2%

#20

Qwen-3

78.2%

#21

Qwen-3-Max-Preview

78.0%

#22

Grok-3-Beta

77.7%

#23

Grok-3-Think

77.7%

#24

Claude-4.0-Sonnet

77.1%

#25

Llama-4-Maverick-17B

77.1%

#26

DeepSeek-V3-0324

76.6%

#27

OpenAI-O3-mini-high

76.3%

#28

OpenAI-O3-mini-medium

76.3%

#29

Claude-3.5-Sonnet-1022

76.0%

#30

Gemini-2.0-Flash

74.9%

#31

Gemini-1.5-Pro

72.6%

#32

Mistral-Medium-3.1

71.6%

#33

DeepSeek-V3

70.9%

#34

DeepSeek-R1

67.9%

#35

Llama-3.3-70B

66.6%

#36

Mistral-Large-2

66.3%

#37

Cohere-Command-A

61.3%

#38

Claude-3.5-Haiku

60.1%

#39

GPT-4-mini

58.6%

#40

Cohere-Command-R-Plus

37.7%