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

AIR-Bench-AdviceInHeavilyRegulatedIndustries

A measure of model refusal for Operational Misuses (Level-1: System and Operational Risks, Level-2: Operational Misuses) related to providing professional advice in heavily regulated industries. Includes Level-4 risks like legal, medical/pharmaceutical, accounting, financial, and government services advice.

Source:

Model Performance

#1

Claude-3.5-Sonnet-1022

29.3%

#2

GPT-3.5-Turbo

26.0%

#3

GPT-OSS-120B

22.7%

#4

OpenAI-O1-1217

22.0%

#5

OpenAI-O3-mini-medium

20.7%

#6

Claude-3-Opus

17.3%

#7

Grok-4

16.0%

#8

Grok-4-Thinking

16.0%

#9

Gemini-2.5-Flash

16.0%

#10

Gemini-2.0-Pro-0121

14.7%

#11

Grok-3-Mini-Beta

14.7%

#12

Gemini-2.5-Pro-0325

13.3%

#13

Gemini-2.5-Pro-Thinking

13.3%

#14

Claude-4.0-Sonnet

13.3%

#15

Claude-4.0-Sonnet-Thinking

13.3%

#16

OpenAI-O1-mini

12.0%

#17

Claude-3-Sonnet

10.7%

#18

OpenAI-O3-medium

10.7%

#19

Gemini-2.0-Flash

10.0%

#20

Granite-3.0

8.7%

#21

Llama-3.1-405B

7.3%

#22

Grok-3-Beta

6.7%

#23

Claude-3.7-Sonnet-Thinking

6.7%

#24

Claude-3.7-Sonnet

6.7%

#25

Claude-4.0-Opus-Thinking

6.0%

#26

Claude-4.0-Opus

6.0%

#27

Llama-4-Maverick-17B

6.0%

#28

Gemini-1.5-Pro

6.0%

#29

Qwen-3

5.3%

#30

Qwen-3-Thinking

5.3%

#31

DeepSeek-R1

5.3%

#32

OpenAI-O4-mini-medium

4.0%

#33

GPT-4o-0513

2.7%

#34

GPT-4-mini

2.0%

#35

GPT-4.5

1.3%

#36

Mistral-Large-2

0.7%

#37

DeepSeek-V3

0.0%

#38

Cohere-Command-R-Plus

0.0%

#39

GPT-4.1

0.0%

#40

Kimi-K2-Instruct

0.0%