Benchmark Explorer

Explore how models perform on various benchmarks

Benchmarks

🔍

Capability Benchmarks

AA-LCR

AIME

ARC-AGI

CaseLaw

Chatbot Arena (Win Rate)

Chatbot Arena AAII

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

MortgageTax

SAGE

SWE-bench

SciCode

SimpleBench

TaxEval

Terminal-Bench Hard

Vals Index

Vals Multimodal Index

Vibe Code Bench

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

Speed & Latency Metrics

Median Tokens/s

Cost & Pricing Metrics

Blended Price (USD/1M Tokens)

AIR-Bench-OtherIllegalunlawfulActivity

A measure of model refusal for Criminal Activities (Level-1: Legal and Rights-Related Risks, Level-2: Criminal Activities) related to other unlawful/criminal activities. Includes Level-4 risks like undermining national security or other government interests, undermining social stability, undermining international relations, and abetting/furthering activities violating any applicable law.

Model Performance

GPT-5 (Thinking)

100.0%

GPT-5

100.0%

OpenAI o3 (High Effort)

100.0%

OpenAI o3 (Medium Effort)

100.0%

Gemini 2.5 Pro

100.0%

Grok 3 (Thinking)

100.0%

Gemini 2.5 Pro (Thinking)

100.0%

Gemini 3.1 Pro Preview

100.0%

Grok 3

100.0%

#10

Claude 3.5 Sonnet

98.9%

#11

Kimi K2

98.3%

#12

GPT-4o Mini

96.7%

#13

Gemini 2.0 Flash Thinking (Jan 2025)

96.7%

#14

Gemini 2.0 Flash (Thinking)

96.7%

#15

Gemini 2.0 Flash

96.7%

#16

Claude 3.5 Haiku

96.3%

#17

Llama 3.1 405B

90.0%

#18

Claude Haiku 4.5 (Thinking)

90.0%

#19

Claude Haiku 4.5

90.0%

#20

Claude 4.0 Sonnet (Thinking)

90.0%

#21

Claude 3.7 Sonnet

90.0%

#22

Claude 4.0 Sonnet

90.0%

#23

Claude 3.7 Sonnet (Thinking)

90.0%

#24

Claude 3 Sonnet

90.0%

#25

Claude Sonnet 4.5 (Thinking)

88.9%

#26

Claude Sonnet 4.5

88.9%

#27

Claude 4.0 Opus

88.0%

#28

Claude 4.0 Opus (Thinking)

88.0%

#29

OpenAI o4 Mini (Medium Effort)

87.8%

#30

OpenAI o4 Mini (High Effort)

87.8%

#31

GPT-4.5

85.2%

#32

GPT-4o

85.0%

#33

Gemini 2.0 Pro

83.3%

#34

GPT OSS 120B

79.4%

#35

OpenAI o1

79.2%

#36

Claude 3 Opus

78.3%

#37

DeepSeek R1

76.7%

#38

Llama 4 Maverick 17B

76.3%

#39

Gemini 2.5 Flash (Thinking)

74.0%

#40

Gemini 2.5 Flash

74.0%

#41

OpenAI o3 Mini (Medium Effort)

72.5%

#42

OpenAI o3 Mini (High Effort)

72.5%

#43

Gemini 1.5 Pro

69.4%

#44

DeepSeek V3

68.3%

#45

GPT-4.1

66.7%

#46

Llama 3.3 70B

63.3%

#47

Grok 3 Mini

62.7%

#48

Granite 3.0

60.0%

#49

Qwen 3 (Thinking)

56.3%

#50

Qwen 3

56.3%

#51

GPT-3.5 Turbo

50.5%

#52

OpenAI o1 Mini

43.5%

#53

Grok 4

40.0%

#54

Grok 4 (Thinking)

40.0%

#55

Mistral Large 2

35.0%

#56

Cohere Command A

28.3%

#57

Cohere Command R+

18.3%