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

IFBench

A benchmark to evaluate precise instruction following generalization on 58 new, diverse, and challenging verifiable out-of-domain constraints. IFBench tests the ability of language models to follow human instructions precisely, particularly output constraints like 'only answer with yes or no' or 'mention the word abrakadabra at least 3 times'.

Source:

Model Performance

#1

GPT-5-mini-Thinking

75.0%

#2

GPT-5-Thinking

73.0%

#3

GPT-5

73.0%

#4

GPT-5-mini

71.0%

#5

OpenAI-O3-high

71.0%

#6

OpenAI-O3-medium

71.0%

#7

GPT-OSS-120B

69.0%

#8

OpenAI-O4-mini-medium

69.0%

#9

OpenAI-O4-mini-high

69.0%

#10

GPT-5-nano-Thinking

68.0%

#11

GPT-5-nano

66.0%

#12

Claude-4.1-Opus-Thinking

55.0%

#13

Claude-4.0-Sonnet-Thinking

55.0%

#14

Grok-4

54.0%

#15

Grok-4-Thinking

54.0%

#16

Claude-4.0-Opus-Thinking

54.0%

#17

Qwen-3-Thinking

51.0%

#18

Gemini-2.5-Flash-Thinking

50.0%

#19

Gemini-2.5-Pro-0325

49.0%

#20

Gemini-2.5-Pro-Thinking

49.0%

#21

Qwen-3-Max-Preview

48.0%

#22

Llama-3.3-70B

47.0%

#23

Qwen-3

46.0%

#24

Grok-3-Mini-Beta

46.0%

#25

Claude-4.0-Sonnet

45.0%

#26

Claude-4.0-Opus

43.0%

#27

Llama-4-Maverick-17B

43.0%

#28

GPT-4.1

43.0%

#29

Kimi-K2-Instruct

42.0%

#30

DeepSeek-V3-0324

41.0%

#31

Gemini-2.0-Flash

40.0%

#32

DeepSeek-R1

40.0%

#33

Mistral-Medium-3.1

40.0%

#34

Llama-3.1-405B

39.0%

#35

Gemini-2.5-Flash

39.0%

#36

Cohere-Command-A

37.0%

#37

DeepSeek-V3

35.0%

#38

GPT-4-mini

31.0%

#39

Mistral-Large-2

31.0%

#40

Magistral-Medium-3.1

25.0%

#41

Phi-4

24.0%