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

LiveBench (Instruction Following)

Assesses ability to follow specific instructions while processing recent news articles, including paraphrasing, simplification, and story generation tasks.

Source:

Model Performance

#1

GPT-5

88.1%

#2

OpenAI-O3-high

86.2%

#3

Qwen-3

85.2%

#4

OpenAI-O4-mini-high

85.0%

#5

DeepSeek-V3

84.4%

#6

OpenAI-O3-medium

84.3%

#7

GPT-5-mini

84.3%

#8

Gemini-2.5-Flash-Thinking

84.2%

#9

Cohere-Command-A

82.9%

#10

Kimi-K2-Instruct

82.5%

#11

OpenAI-O4-mini-medium

81.8%

#12

Claude-3.7-Sonnet-Thinking

81.2%

#13

Claude-4.0-Opus-Thinking

80.7%

#14

Claude-4.0-Sonnet-Thinking

80.4%

#15

Claude-4.1-Opus-Thinking

80.4%

#16

DeepSeek-R1

80.0%

#17

Gemini-2.5-Flash

79.6%

#18

Grok-3-Mini-Beta

78.7%

#19

Gemini-2.5-Pro-0325

78.5%

#20

Claude-4.0-Opus

78.4%

#21

Claude-4.0-Sonnet

77.2%

#22

GPT-4.1

77.0%

#23

GPT-5-nano

76.9%

#24

Claude-3.7-Sonnet

76.5%

#25

Llama-4-Maverick-17B

75.8%

#26

Phi-4

73.2%

#27

GPT-4.5

72.3%

#28

GPT-4o-0513

71.9%

#29

Mistral-Medium-3.1

71.4%

#30

Claude-3.5-Sonnet-1022

69.3%

#31

Mistral-Large

67.9%

#32

GPT-OSS-120B

66.3%

#33

Claude-3.5-Haiku

61.9%

#34

Cohere-Command-R-Plus

57.6%