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 (Average)

Measures the model's overall performance across all LiveBench tasks, providing a comprehensive assessment of capabilities across reasoning, coding, math, data analysis, language, and instruction following.

Source:

Model Performance

#1

GPT-5

78.6%

#2

OpenAI-O3-high

74.6%

#3

Claude-4.1-Opus-Thinking

73.5%

#4

Claude-4.0-Opus-Thinking

72.9%

#5

Claude-4.0-Sonnet-Thinking

72.1%

#6

OpenAI-O3-medium

72.0%

#7

OpenAI-O4-mini-high

71.5%

#8

GPT-5-mini

70.7%

#9

DeepSeek-R1

70.1%

#10

Gemini-2.5-Pro-0325

69.4%

#11

Claude-3.7-Sonnet-Thinking

67.4%

#12

OpenAI-O4-mini-medium

66.9%

#13

Claude-4.0-Opus

65.9%

#14

Gemini-2.5-Flash

64.4%

#15

Qwen-3

63.7%

#16

Claude-4.0-Sonnet

63.4%

#17

Kimi-K2-Instruct

62.7%

#18

DeepSeek-V3

62.5%

#19

Grok-3-Mini-Beta

62.4%

#20

GPT-4.5

58.7%

#21

Claude-3.7-Sonnet

58.5%

#22

Gemini-2.5-Flash-Thinking

57.5%

#23

GPT-5-nano

56.5%

#24

GPT-4.1

55.9%

#25

GPT-4o-0513

54.7%

#26

GPT-OSS-120B

54.6%

#27

Claude-3.5-Sonnet-1022

51.8%

#28

Mistral-Medium-3.1

50.6%

#29

Phi-4

49.3%

#30

Llama-4-Maverick-17B

47.8%

#31

Cohere-Command-A

44.2%

#32

Mistral-Large

43.3%

#33

Claude-3.5-Haiku

39.5%

#34

Cohere-Command-R-Plus

30.1%