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)

LiveBench (Agentic Coding)

Evaluates the model's ability to operate in a real development environment to solve real-world repository issues.

Source:

Model Performance

Gemini 3.1 Pro Preview

65.0%

Claude Opus 4.5 (Thinking)

63.3%

Claude Opus 4.5

63.3%

Claude Opus 4.6 (Thinking)

61.7%

Claude Sonnet 4.6

60.0%

Claude Sonnet 4.5 (Thinking)

53.3%

GPT-5.1 Codex Max

53.3%

Claude 4.1 Opus

53.3%

GPT-5 (Thinking)

51.7%

#10

Claude Sonnet 4.5

48.3%

#11

Claude 4.1 Opus (Thinking)

48.3%

#12

GPT-5 Mini (Thinking)

46.7%

#13

DeepSeek V3.2

46.7%

#14

GPT-5

43.3%

#15

Claude Haiku 4.5 (Thinking)

41.7%

#16

DeepSeek V3.2 (Thinking)

40.0%

#17

GPT-5.2

40.0%

#18

Claude 4.0 Sonnet (Thinking)

40.0%

#19

Claude 4.0 Sonnet

38.3%

#20

OpenAI o3 (High Effort)

36.7%

#21

Claude Haiku 4.5

33.3%

#22

Claude 4.0 Opus (Thinking)

33.3%

#23

Gemini 2.5 Pro (Thinking)

33.3%

#24

Claude 4.0 Opus

31.7%

#25

Kimi K2

31.7%

#26

OpenAI o3 (Medium Effort)

28.3%

#27

OpenAI o4 Mini (High Effort)

28.3%

#28

GPT-5 Mini

28.3%

#29

DeepSeek R1

26.7%

#30

Claude 3.7 Sonnet (Thinking)

25.0%

#31

Gemini 2.5 Flash (Thinking)

23.3%

#32

GPT-5 Nano (Thinking)

23.3%

#33

OpenAI o4 Mini (Medium Effort)

21.7%

#34

Claude 3.7 Sonnet

21.7%

#35

DeepSeek V3

21.7%

#36

Gemini 2.5 Flash

18.3%

#37

GPT-5 Nano

18.3%

#38

GPT OSS 120B

16.7%

#39

Mistral Medium 3.1

15.0%

#40

Grok 3 Mini

15.0%

#41

GPT-4.5

15.0%

#42

Claude 3.5 Sonnet

15.0%

#43

GPT-4.1

13.3%

#44

Qwen 3 Max Preview

13.3%

#45

Gemini 2.5 Pro

13.3%

#46

GPT-4o

13.3%

#47

Claude 3.5 Haiku

6.7%

#48

Qwen 3 (Thinking)

6.7%

#49

Phi-4

5.0%

#50

Cohere Command A

5.0%

#51

Qwen 3

3.3%

#52

Llama 4 Maverick 17B

3.3%

#53

Cohere Command R+

1.7%

#54

Mistral Large

1.7%