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

LiveCodeBench

Evaluates the model's ability to solve competitive programming problems using recent contest questions to avoid data contamination. Tests coding proficiency on algorithmic challenges that require understanding problem statements, implementing efficient solutions, and handling edge cases.

Source:

Model Performance

#1

GPT-5-mini

86.6%

#2

OpenAI-O3-high

83.9%

#3

OpenAI-O3-medium

83.9%

#4

Grok-4

83.2%

#5

Grok-4-Thinking

83.2%

#6

OpenAI-O4-mini-high

82.2%

#7

OpenAI-O4-mini-medium

82.2%

#8

Grok-3-Mini-Beta

76.2%

#9

OpenAI-O3-mini-high

71.5%

#10

OpenAI-O3-mini-medium

71.5%

#11

Qwen-3

70.6%

#12

Qwen-3-Thinking

70.6%

#13

Kimi-K2-Instruct

70.4%

#14

Claude-4.0-Opus-Thinking

70.2%

#15

DeepSeek-R1

70.2%

#16

Qwen-3-Max-Preview

66.9%

#17

Claude-4.1-Opus-Thinking

66.5%

#18

DeepSeek-V3-0324

65.5%

#19

Claude-4.1-Opus

64.6%

#20

Claude-4.0-Opus

62.6%

#21

Claude-4.0-Sonnet-Thinking

62.4%

#22

Claude-3.7-Sonnet-Thinking

60.4%

#23

Claude-4.0-Sonnet

59.7%

#24

Gemini-2.5-Flash

56.9%

#25

Claude-3.7-Sonnet

56.7%

#26

GPT-4.1

54.7%

#27

Grok-3-Think

52.9%

#28

Grok-3-Beta

52.9%

#29

OpenAI-O1-1217

50.3%

#30

Claude-3.5-Sonnet-1022

49.6%

#31

Llama-4-Maverick-17B

47.3%

#32

Gemini-2.5-Flash-Thinking

46.9%

#33

Mistral-Medium-3.1

44.8%

#34

Gemini-2.0-Flash

43.6%

#35

Claude-3.5-Haiku

41.9%

#36

Gemini-1.5-Pro

41.7%

#37

Mistral-Large-2

37.1%

#38

Llama-3.3-70B

36.3%

#39

Cohere-Command-A

35.1%

#40

GPT-4-mini

26.4%

#41

Cohere-Command-R-Plus

18.2%